Search

Simple Summary: Automatic segmentation of organs and other regions of interest is a promising approach for reducing the workload of doctors in radiotherapeutic planning, but it can be hard for doctors and researchers to keep up with current developments. This review evaluates 807 papers and reveals trends, commonalities, and gaps in the existing corpus. A set of recommendations for conducting effective segmentation studies is also provided. This review provides a formal overview of current automatic segmentation studies that use deep learning in radiotherapy. It covers 807 published papers and includes multiple cancer sites, image types (CT/MRI/PET), and segmentation methods. We collect key statistics about the papers to uncover commonalities, trends, and methods, and identify areas where more research might be needed. Moreover, we analyzed the corpus by posing explicit questions aimed at providing high-quality and actionable insights, including: "What should researchers think about when starting a segmentation study?", "How can research practices in medical image segmentation be improved?", "What is missing from the current corpus?", and more. This allowed us to provide practical guidelines on how to conduct a good segmentation study in today's competitive environment that will be useful for future research within the field, regardless of the specific radiotherapeutic subfield. To aid in our analysis, we used the large language model ChatGPT to condense information. [ABSTRACT FROM AUTHOR]

Simple Summary: This paper presents a novel approach to produce virtual contrast enhanced (VCE) images for nasopharyngeal cancer (NPC) without the use of contrast agents, which carry certain risks. This model uses pixelwise gradient term to capture the shape and a GAN terms to capture the texture of the real contrast enhanced T1C images With similar accuracy to existing models, our method shows an advantage in reproducing texture closer to the realistic contrast-enhanced images. This results are tested by various measures, including mean absolute error (MAE), mean square error (MSE) and structural similarity index (SSIM) for similarity accuracy; total mean square variation per mean intensity (TMSVPMI), the total absolute vari-ation per mean intensity (TAVPMI), Tenengrad function per mean intensity (TFPMI) and variance function per mean intensity (VFPMI) Various variations of the model, including fine-tuning of the hyperparameters, normalization methods on the images and using single modality, have also been investigated to test the optimal performance. Background: The development of advanced computational models for medical imaging is crucial for improving diagnostic accuracy in healthcare. This paper introduces a novel approach for virtual contrast enhancement (VCE) in magnetic resonance imaging (MRI), particularly focusing on nasopharyngeal cancer (NPC). Methods: The proposed model, Pixelwise Gradient Model with GAN for Virtual Contrast Enhancement (PGMGVCE), makes use of pixelwise gradient methods with Generative Adversarial Networks (GANs) to enhance T1-weighted (T1-w) and T2-weighted (T2-w) MRI images. This approach combines the benefits of both modalities to simulate the effects of gadolinium-based contrast agents, thereby reducing associated risks. Various modifications of PGMGVCE, including changing hyperparameters, using normalization methods (z-score, Sigmoid and Tanh) and training the model with T1-w or T2-w images only, were tested to optimize the model's performance. Results: PGMGVCE demonstrated a similar accuracy to the existing model in terms of mean absolute error (MAE) (8.56 ± 0.45 for Li's model; 8.72 ± 0.48 for PGMGVCE), mean square error (MSE) (12.43 ± 0.67 for Li's model; 12.81 ± 0.73 for PGMGVCE) and structural similarity index (SSIM) (0.71 ± 0.08 for Li's model; 0.73 ± 0.12 for PGMGVCE). However, it showed improvements in texture representation, as indicated by total mean square variation per mean intensity (TMSVPMI) (0.124 ± 0.022 for ground truth; 0.079 ± 0.024 for Li's model; 0.120 ± 0.027 for PGMGVCE), total absolute variation per mean intensity (TAVPMI) (0.159 ± 0.031 for ground truth; 0.100 ± 0.032 for Li's model; 0.153 ± 0.029 for PGMGVCE), Tenengrad function per mean intensity (TFPMI) (1.222 ± 0.241 for ground truth; 0.981 ± 0.213 for Li's model; 1.194 ± 0.223 for PGMGVCE) and variance function per mean intensity (VFPMI) (0.0811 ± 0.005 for ground truth; 0.0667   ± 0.006 for Li's model; 0.0761   ± 0.006 for PGMGVCE). Conclusions: PGMGVCE presents an innovative and safe approach to VCE in MRI, demonstrating the power of deep learning in enhancing medical imaging. This model paves the way for more accurate and risk-free diagnostic tools in medical imaging. [ABSTRACT FROM AUTHOR]

Simple Summary: Nonlinear curve fitting of the pharmacokinetic model to DCE-MRI concentration curves is highly time-consuming. The estimation of highly non-linear dispersion-related parameter in MR dispersion imaging (MRDI) makes the process even more tedious. The fast MRDI (fMRDI) model is proposed to simplify and accelerate the MRDI model by representing the dispersion-applied arterial input function (AIF) as the weighted-sum of a fast and a slow population-based AIFs. A deep learning-based two-stage inference method is proposed to accelerate quantitative MRDI. The deep learning model makes a initial estimation of the parameters directly from the concentration curves and the parameters is then refined by a number of iterative optimization. Dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) measures microvascular perfusion by capturing the temporal changes of an MRI contrast agent in a target tissue, and it provides valuable information for the diagnosis and prognosis of a wide range of tumors. Quantitative DCE-MRI analysis commonly relies on the nonlinear least square (NLLS) fitting of a pharmacokinetic (PK) model to concentration curves. However, the voxel-wise application of such nonlinear curve fitting is highly time-consuming. The arterial input function (AIF) needs to be utilized in quantitative DCE-MRI analysis. and in practice, a population-based arterial AIF is often used in PK modeling. The contribution of intravascular dispersion to the measured signal enhancement is assumed to be negligible. The MR dispersion imaging (MRDI) model was recently proposed to account for intravascular dispersion, enabling more accurate PK modeling. However, the complexity of the MRDI hinders its practical usability and makes quantitative PK modeling even more time-consuming. In this paper, we propose fast MR dispersion imaging (fMRDI) to effectively represent the intravascular dispersion and highly accelerated PK parameter estimation. We also propose a deep learning-based, two-stage framework to accelerate PK parameter estimation. We used a deep neural network (NN) to estimate PK parameters directly from enhancement curves. The estimation from NN was further refined using several steps of NLLS, which is significantly faster than performing NLLS from random initializations. A data synthesis module is proposed to generate synthetic training data for the NN. Two data-processing modules were introduced to improve the model's stability against noise and variations. Experiments on our in-house clinical prostate MRI dataset demonstrated that our method significantly reduces the processing time, produces a better distinction between normal and clinically significant prostate cancer (csPCa) lesions, and is more robust against noise than conventional DCE-MRI analysis methods. [ABSTRACT FROM AUTHOR]

Simple Summary: Breast cancer is a significant cause of female cancer-related deaths in the US. Checking how severe the cancer is helps in planning treatment. Modern AI methods are good at grading cancer, but they are not used much in hospitals yet. We developed and utilized ensemble deep learning algorithms for addressing the tasks of classifying (1) breast cancer subtype and (2) breast cancer invasiveness from whole slide image (WSI) histopathology slides. The ensemble models used were based on convolutional neural networks (CNNs) known for extracting distinctive features crucial for accurate classification. In this paper, we provide a comprehensive analysis of these models and the used methodology for breast cancer diagnosis tasks. Cancer diagnosis and classification are pivotal for effective patient management and treatment planning. In this study, a comprehensive approach is presented utilizing ensemble deep learning techniques to analyze breast cancer histopathology images. Our datasets were based on two widely employed datasets from different centers for two different tasks: BACH and BreakHis. Within the BACH dataset, a proposed ensemble strategy was employed, incorporating VGG16 and ResNet50 architectures to achieve precise classification of breast cancer histopathology images. Introducing a novel image patching technique to preprocess a high-resolution image facilitated a focused analysis of localized regions of interest. The annotated BACH dataset encompassed 400 WSIs across four distinct classes: Normal, Benign, In Situ Carcinoma, and Invasive Carcinoma. In addition, the proposed ensemble was used on the BreakHis dataset, utilizing VGG16, ResNet34, and ResNet50 models to classify microscopic images into eight distinct categories (four benign and four malignant). For both datasets, a five-fold cross-validation approach was employed for rigorous training and testing. Preliminary experimental results indicated a patch classification accuracy of 95.31% (for the BACH dataset) and WSI image classification accuracy of 98.43% (BreakHis). This research significantly contributes to ongoing endeavors in harnessing artificial intelligence to advance breast cancer diagnosis, potentially fostering improved patient outcomes and alleviating healthcare burdens. [ABSTRACT FROM AUTHOR]

Simple Summary: The diagnosis of oral cancer can require multiple biopsies to increase the likelihood of sampling the most pathologic site within a lesion. Optical coherence tomography (OCT) enables the examination of subsurface morphology and has shown potential in biopsy guidance. OCT captures changes in tissue stratification related to depth, topology, and presence of the epithelial-stromal boundary, which are structural biomarkers for pre-invasive and invasive oral cancer. This study presents a neural network pipeline to simplify OCT interpretation by providing information about epithelial depth and stratification through simple en face maps. U-net models were employed to segment the boundaries of the epithelial layer, and supporting convolutional neural networks were used for identification of the imaging field and artifacts. Non-cancerous, precancerous, and cancerous pathologies across the oral cavity were evaluated. The predictions demonstrate as-good-as or better agreement than inter-rater agreement, suggesting strong predictive power. This paper aims to simplify the application of optical coherence tomography (OCT) for the examination of subsurface morphology in the oral cavity and reduce barriers towards the adoption of OCT as a biopsy guidance device. The aim of this work was to develop automated software tools for the simplified analysis of the large volume of data collected during OCT. Imaging and corresponding histopathology were acquired in-clinic using a wide-field endoscopic OCT system. An annotated dataset (n = 294 images) from 60 patients (34 male and 26 female) was assembled to train four unique neural networks. A deep learning pipeline was built using convolutional and modified u-net models to detect the imaging field of view (network 1), detect artifacts (network 2), identify the tissue surface (network 3), and identify the presence and location of the epithelial–stromal boundary (network 4). The area under the curve of the image and artifact detection networks was 1.00 and 0.94, respectively. The Dice similarity score for the surface and epithelial–stromal boundary segmentation networks was 0.98 and 0.83, respectively. Deep learning (DL) techniques can identify the location and variations in the epithelial surface and epithelial–stromal boundary in OCT images of the oral mucosa. Segmentation results can be synthesized into accessible en face maps to allow easier visualization of changes. [ABSTRACT FROM AUTHOR]

Simple Summary: Risk assessment in early breast cancer is critical for clinical decisions, but defining risk categories poses a significant challenge. The integration of conventional histopathology and biomarkers with artificial intelligence (AI) techniques, including machine learning and deep learning, has the potential to offer more precise information. AI applications extend beyond detection to histological subtyping, grading, and molecular feature identification. The successful integration of AI into clinical practice requires collaboration between histopathologists, molecular pathologists, computational pathologists, and oncologists to optimize patient outcomes. Effective risk assessment in early breast cancer is essential for informed clinical decision-making, yet consensus on defining risk categories remains challenging. This paper explores evolving approaches in risk stratification, encompassing histopathological, immunohistochemical, and molecular biomarkers alongside cutting-edge artificial intelligence (AI) techniques. Leveraging machine learning, deep learning, and convolutional neural networks, AI is reshaping predictive algorithms for recurrence risk, thereby revolutionizing diagnostic accuracy and treatment planning. Beyond detection, AI applications extend to histological subtyping, grading, lymph node assessment, and molecular feature identification, fostering personalized therapy decisions. With rising cancer rates, it is crucial to implement AI to accelerate breakthroughs in clinical practice, benefiting both patients and healthcare providers. However, it is important to recognize that while AI offers powerful automation and analysis tools, it lacks the nuanced understanding, clinical context, and ethical considerations inherent to human pathologists in patient care. Hence, the successful integration of AI into clinical practice demands collaborative efforts between medical experts and computational pathologists to optimize patient outcomes. [ABSTRACT FROM AUTHOR]

Simple Summary: Due to various causes, such as the thinning of the ozone layer, climate change, or the fashion for artificial tanning, the incidence of skin cancer has increased recently. Early detection of cancerous skin lesions is the only chance to prevent dangerous developments. This paper proposes two models of support systems for the detection of some skin lesions including dangerous melanoma, based on two different methods of assembling neural networks and making global decisions by fusing individual decisions. The system based on the fusion of some intermediate binary classification subsystems is a new solution and offers an accuracy of 91.04%, better than that offered by the classic system based on the vote with multiple weights of the constituent networks. In addition, it is found that the individual performance indicators depend on the type of skin lesion. For example, the F1 score varied from 81.36% to 94.17%. Today, skin cancer, and especially melanoma, is an increasing and dangerous health disease. The high mortality rate of some types of skin cancers needs to be detected in the early stages and treated urgently. The use of neural network ensembles for the detection of objects of interest in images has gained more and more interest due to the increased performance of the results. In this sense, this paper proposes two ensembles of neural networks, based on the fusion of the decisions of the component neural networks for the detection of four skin lesions (basal cancer cell, melanoma, benign keratosis, and melanocytic nevi). The first system is based on separate learning of three neural networks (MobileNet V2, DenseNet 169, and EfficientNet B2), with multiple weights for the four classes of lesions and weighted overall prediction. The second system is made up of six binary models (one for each pair of classes) for each network; the fusion and prediction are conducted by weighted summation per class and per model. In total, 18 such binary models will be considered. The 91.04% global accuracy of this set of binary models is superior to the first system (89.62%). Separately, only for the binary classifications within the system was the individual accuracy better. The individual F1 score for each class and the global system varied from 81.36% to 94.17%. Finally, a critical comparison is made with similar works from the literature. [ABSTRACT FROM AUTHOR]

Simple Summary: This paper introduces a novel graph neural network (a hierarchical graph pooling model), SANEpool, to effectively detect core sub-networks of significant genes for predicting the synergy score of drug/drug combinations in cancer. SANEpool successfully addresses the limitations of the un-transparency in the prediction process of previous computational AI models for drug synergy prediction, while providing the superior predictive performance than popular baselines on numerous drug-synergy prediction datasets. The success of SANEpool indicates that significant gene-gene interactions and gene-drug interactions play a crucial role in designing powerful deep learning models to provide accurate prediction and to reveal the mechanism of the synergy (MoS). Synergistic drug combinations provide huge potentials to enhance therapeutic efficacy and to reduce adverse reactions. However, effective and synergistic drug combination prediction remains an open question because of the unknown causal disease signaling pathways. Though various deep learning (AI) models have been proposed to quantitatively predict the synergism of drug combinations, the major limitation of existing deep learning methods is that they are inherently not interpretable, which makes the conclusions of AI models untransparent to human experts, henceforth limiting the robustness of the model conclusion and the implementation ability of these models in real-world human–AI healthcare. In this paper, we develop an interpretable graph neural network (GNN) that reveals the underlying essential therapeutic targets and the mechanism of the synergy (MoS) by mining the sub-molecular network of great importance. The key point of the interpretable GNN prediction model is a novel graph pooling layer, a self-attention-based node and edge pool (henceforth SANEpool), that can compute the attention score (importance) of genes and connections based on the genomic features and topology. As such, the proposed GNN model provides a systematic way to predict and interpret the drug combination synergism based on the detected crucial sub-molecular network. Experiments on various well-adopted drug-synergy-prediction datasets demonstrate that (1) the SANEpool model has superior predictive ability to generate accurate synergy score prediction, and (2) the sub-molecular networks detected by the SANEpool are self-explainable and salient for identifying synergistic drug combinations. [ABSTRACT FROM AUTHOR]

Simple Summary: In this paper, we introduce a new technique for enhancing medical image diagnosis through transfer learning (TL). The approach addresses the issue of limited labelled images by pre-training deep learning models on similar medical images and then refining them with a small set of annotated medical images. Our method demonstrated excellent results in classifying the humerus and wrist, surpassing previous methods, and showing greater robustness in various experiments. Furthermore, we demonstrate the adaptability of the approach with a CT case, which showed improvements in the results. Medical image classification poses significant challenges in real-world scenarios. One major obstacle is the scarcity of labelled training data, which hampers the performance of image-classification algorithms and generalisation. Gathering sufficient labelled data is often difficult and time-consuming in the medical domain, but deep learning (DL) has shown remarkable performance, although it typically requires a large amount of labelled data to achieve optimal results. Transfer learning (TL) has played a pivotal role in reducing the time, cost, and need for a large number of labelled images. This paper presents a novel TL approach that aims to overcome the limitations and disadvantages of TL that are characteristic of an ImageNet dataset, which belongs to a different domain. Our proposed TL approach involves training DL models on numerous medical images that are similar to the target dataset. These models were then fine-tuned using a small set of annotated medical images to leverage the knowledge gained from the pre-training phase. We specifically focused on medical X-ray imaging scenarios that involve the humerus and wrist from the musculoskeletal radiographs (MURA) dataset. Both of these tasks face significant challenges regarding accurate classification. The models trained with the proposed TL were used to extract features and were subsequently fused to train several machine learning (ML) classifiers. We combined these diverse features to represent various relevant characteristics in a comprehensive way. Through extensive evaluation, our proposed TL and feature-fusion approach using ML classifiers achieved remarkable results. For the classification of the humerus, we achieved an accuracy of 87.85%, an F1-score of 87.63%, and a Cohen's Kappa coefficient of 75.69%. For wrist classification, our approach achieved an accuracy of 85.58%, an F1-score of 82.70%, and a Cohen's Kappa coefficient of 70.46%. The results demonstrated that the models trained using our proposed TL approach outperformed those trained with ImageNet TL. We employed visualisation techniques to further validate these findings, including a gradient-based class activation heat map (Grad-CAM) and locally interpretable model-independent explanations (LIME). These visualisation tools provided additional evidence to support the superior accuracy of models trained with our proposed TL approach compared to those trained with ImageNet TL. Furthermore, our proposed TL approach exhibited greater robustness in various experiments compared to ImageNet TL. Importantly, the proposed TL approach and the feature-fusion technique are not limited to specific tasks. They can be applied to various medical image applications, thus extending their utility and potential impact. To demonstrate the concept of reusability, a computed tomography (CT) case was adopted. The results obtained from the proposed method showed improvements. [ABSTRACT FROM AUTHOR]

Simple Summary: This paper proposes a deep learning-based skin cancer classification network (DSCC_Net) that is based on a convolutional neural network (CNN) and implemented on three publicly available benchmark datasets (ISIC 2020, HAM10000, and DermIS). The proposed DSCC_Net obtained a 99.43% AUC, along with a 94.17% accuracy, a recall of 93.76%, a precision of 94.28%, and an F1-score of 93.93% in categorizing the four distinct types of skin cancer diseases. The accuracies of ResNet-152, Vgg-19, MobileNet, and Vgg-16, EfficientNet-B0, and Inception-V3 are 89.68%, 92.51%, 91.46%, 89.12%, 89.46%, and 91.82%, respectively. The results showed that the proposed DSCC_Net model performs better as compared to baseline models, thus offering significant support to dermatologists and health experts to diagnose skin cancer. Skin cancer is one of the most lethal kinds of human illness. In the present state of the health care system, skin cancer identification is a time-consuming procedure and if it is not diagnosed initially then it can be threatening to human life. To attain a high prospect of complete recovery, early detection of skin cancer is crucial. In the last several years, the application of deep learning (DL) algorithms for the detection of skin cancer has grown in popularity. Based on a DL model, this work intended to build a multi-classification technique for diagnosing skin cancers such as melanoma (MEL), basal cell carcinoma (BCC), squamous cell carcinoma (SCC), and melanocytic nevi (MN). In this paper, we have proposed a novel model, a deep learning-based skin cancer classification network (DSCC_Net) that is based on a convolutional neural network (CNN), and evaluated it on three publicly available benchmark datasets (i.e., ISIC 2020, HAM10000, and DermIS). For the skin cancer diagnosis, the classification performance of the proposed DSCC_Net model is compared with six baseline deep networks, including ResNet-152, Vgg-16, Vgg-19, Inception-V3, EfficientNet-B0, and MobileNet. In addition, we used SMOTE Tomek to handle the minority classes issue that exists in this dataset. The proposed DSCC_Net obtained a 99.43% AUC, along with a 94.17%, accuracy, a recall of 93.76%, a precision of 94.28%, and an F1-score of 93.93% in categorizing the four distinct types of skin cancer diseases. The rates of accuracy for ResNet-152, Vgg-19, MobileNet, Vgg-16, EfficientNet-B0, and Inception-V3 are 89.32%, 91.68%, 92.51%, 91.12%, 89.46% and 91.82%, respectively. The results showed that our proposed DSCC_Net model performs better as compared to baseline models, thus offering significant support to dermatologists and health experts to diagnose skin cancer. [ABSTRACT FROM AUTHOR]

Simple Summary: In radiotherapy treatment, organs at risk and target volumes are contoured by the clinicians to prepare a dosimetry plan. In retrospective data, these structures are not often standardised to universal names across the patients plans, which is required to enable data mining and analysis. In this paper, a new method was proposed and evaluated to automatically standardise radiotherapy structures names using machine learning algorithms. The proposed approach was deployed over a dataset with 1613 patients collected from Liverpool & Macarthur Cancer Therapy Centres, New South Wales, Australia. It was concluded that machine learning techniques can standardise the dosimetry plan structures, taking into consideration the integration of multiple modalities representing each structure during the training process. In progressing the use of big data in health systems, standardised nomenclature is required to enable data pooling and analyses. In many radiotherapy planning systems and their data archives, target volumes (TV) and organ-at-risk (OAR) structure nomenclature has not been standardised. Machine learning (ML) has been utilised to standardise volumes nomenclature in retrospective datasets. However, only subsets of the structures have been targeted. Within this paper, we proposed a new approach for standardising all the structures nomenclature by using multi-modal artificial neural networks. A cohort consisting of 1613 breast cancer patients treated with radiotherapy was identified from Liverpool & Macarthur Cancer Therapy Centres, NSW, Australia. Four types of volume characteristics were generated to represent each target and OAR volume: textual features, geometric features, dosimetry features, and imaging data. Five datasets were created from the original cohort, the first four represented different subsets of volumes and the last one represented the whole list of volumes. For each dataset, 15 sets of combinations of features were generated to investigate the effect of using different characteristics on the standardisation performance. The best model reported 99.416% classification accuracy over the hold-out sample when used to standardise all the nomenclatures in a breast cancer radiotherapy plan into 21 classes. Our results showed that ML based automation methods can be used for standardising naming conventions in a radiotherapy plan taking into consideration the inclusion of multiple modalities to better represent each volume. [ABSTRACT FROM AUTHOR]

Simple Summary: In this paper, we present an artificial Intelligence (AI) based automatic detection of mitoses in Uterine Leiomyosarcoma. Mitotic count is one of the important biomarkers in the field of histopathology. A dataset is also made available to research community which consists of images having moitotically active region. These regions are labeled by a trained AI expert in coordination with a senior histopathologist. Preliminary results show AI as promising solution for detection of mitotically active regions mitotic region in Uterine leiomyosarcoma cases and can be used as a second opinion system. Uterine leiomyosarcoma (ULMS) is the most common sarcoma of the uterus, It is aggressive and has poor prognosis. Its diagnosis is sometimes challenging owing to its resemblance by benign smooth muscle neoplasms of the uterus. Pathologists diagnose and grade leiomyosarcoma based on three standard criteria (i.e., mitosis count, necrosis, and nuclear atypia). Among these, mitosis count is the most important and challenging biomarker. In general, pathologists use the traditional manual counting method for the detection and counting of mitosis. This procedure is very time-consuming, tedious, and subjective. To overcome these challenges, artificial intelligence (AI) based methods have been developed that automatically detect mitosis. In this paper, we propose a new ULMS dataset and an AI-based approach for mitosis detection. We collected our dataset from a local medical facility in collaboration with highly trained pathologists. Preprocessing and annotations are performed using standard procedures, and a deep learning-based method is applied to provide baseline accuracies. The experimental results showed 0.7462 precision, 0.8981 recall, and 0.8151 F1-score. For research and development, the code and dataset have been made publicly available. [ABSTRACT FROM AUTHOR]

Simple Summary: Melanoma is the most dangerous type of skin cancer worldwide. Early detection of melanoma is crucial for better outcomes, but this often can be challenging. This research explores the use of artificial intelligence (AI) techniques combined with non-invasive imaging methods to improve melanoma detection. The authors aim to evaluate the current state of AI-based techniques using tools including dermoscopy, optical coherence tomography (OCT), and reflectance confocal microscopy (RCM). The findings demonstrate that several AI algorithms perform as well as or better than dermatologists in detecting melanoma, particularly in the analysis of dermoscopy images. This research highlights the potential of AI to enhance diagnostic accuracy, leading to improved patient outcomes. Further studies are needed to address limitations and ensure the reliability and effectiveness of AI-based techniques. Background: Melanoma, the deadliest form of skin cancer, poses a significant public health challenge worldwide. Early detection is crucial for improved patient outcomes. Non-invasive skin imaging techniques allow for improved diagnostic accuracy; however, their use is often limited due to the need for skilled practitioners trained to interpret images in a standardized fashion. Recent innovations in artificial intelligence (AI)-based techniques for skin lesion image interpretation show potential for the use of AI in the early detection of melanoma. Objective: The aim of this study was to evaluate the current state of AI-based techniques used in combination with non-invasive diagnostic imaging modalities including reflectance confocal microscopy (RCM), optical coherence tomography (OCT), and dermoscopy. We also aimed to determine whether the application of AI-based techniques can lead to improved diagnostic accuracy of melanoma. Methods: A systematic search was conducted via the Medline/PubMed, Cochrane, and Embase databases for eligible publications between 2018 and 2022. Screening methods adhered to the 2020 version of the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. Included studies utilized AI-based algorithms for melanoma detection and directly addressed the review objectives. Results: We retrieved 40 papers amongst the three databases. All studies directly comparing the performance of AI-based techniques with dermatologists reported the superior or equivalent performance of AI-based techniques in improving the detection of melanoma. In studies directly comparing algorithm performance on dermoscopy images to dermatologists, AI-based algorithms achieved a higher ROC (>80%) in the detection of melanoma. In these comparative studies using dermoscopic images, the mean algorithm sensitivity was 83.01% and the mean algorithm specificity was 85.58%. Studies evaluating machine learning in conjunction with OCT boasted accuracy of 95%, while studies evaluating RCM reported a mean accuracy rate of 82.72%. Conclusions: Our results demonstrate the robust potential of AI-based techniques to improve diagnostic accuracy and patient outcomes through the early identification of melanoma. Further studies are needed to assess the generalizability of these AI-based techniques across different populations and skin types, improve standardization in image processing, and further compare the performance of AI-based techniques with board-certified dermatologists to evaluate clinical applicability. [ABSTRACT FROM AUTHOR]

Simple Summary: Cancer research has been increasingly focusing on identifying genes and molecular pathways that drive the disease. In this context, protein–protein interaction networks, which provide insights into the interactions among proteins within a cell, have proven particularly useful. However, the effectiveness of existing approaches can be influenced by the specific network used, as different networks can have different topological structures. In addition, newer context-specific networks often come with incomplete structures, which complicates the analysis. To address these challenges, we propose a new method, called MultiFDRnet, that can identify driver genes and pathways using multiple protein–protein interaction (PPI) networks. Here, the false discovery rate (FDR) refers to the proportion of non-cancer genes within identified subnetworks. Our method, tested on both simulated and real cancer data, has been able to identify important subnetworks that are supported by multiple PPI networks and reveal novel modular structures in context-specific PPI networks. The software that we developed to implement this method is freely available for other researchers to use. Background: The identification of cancer driver genes and key molecular pathways has been the focus of large-scale cancer genome studies. Network-based methods detect significantly perturbed subnetworks as putative cancer pathways by incorporating genomics data with the topological information of PPI networks. However, commonly used PPI networks have distinct topological structures, making the results of the same method vary widely when applied to different networks. Furthermore, emerging context-specific PPI networks often have incomplete topological structures, which pose serious challenges for existing subnetwork detection algorithms. Methods: In this paper, we propose a novel method, referred to as MultiFDRnet, to address the above issues. The basic idea is to model a set of PPI networks as a multiplex network to preserve the topological structure of individual networks, while introducing dependencies among them, and, then, to detect significantly perturbed subnetworks on the modeled multiplex network using all the structural information simultaneously. Results: To illustrate the effectiveness of the proposed approach, an extensive benchmark analysis was conducted on both simulated and real cancer data. The experimental results showed that the proposed method is able to detect significantly perturbed subnetworks jointly supported by multiple PPI networks and to identify novel modular structures in context-specific PPI networks. [ABSTRACT FROM AUTHOR]

Simple Summary: Deep learning has succeeded greatly in medical image-based cancer diagnosis. To help readers better understand the current research status and ideas, this article provides a detailed overview of the working mechanisms and use cases of commonly used radiological imaging and histopathology, the basic architecture of deep learning, classical pretrained models, common methods to overcome overfitting, and the application of deep learning in medical image-based cancer diagnosis. Finally, the data, label, model, and radiomics were discussed specifically and the current challenges and future research hotspots were discussed and analyzed. (1) Background: The application of deep learning technology to realize cancer diagnosis based on medical images is one of the research hotspots in the field of artificial intelligence and computer vision. Due to the rapid development of deep learning methods, cancer diagnosis requires very high accuracy and timeliness as well as the inherent particularity and complexity of medical imaging. A comprehensive review of relevant studies is necessary to help readers better understand the current research status and ideas. (2) Methods: Five radiological images, including X-ray, ultrasound (US), computed tomography (CT), magnetic resonance imaging (MRI), positron emission computed tomography (PET), and histopathological images, are reviewed in this paper. The basic architecture of deep learning and classical pretrained models are comprehensively reviewed. In particular, advanced neural networks emerging in recent years, including transfer learning, ensemble learning (EL), graph neural network, and vision transformer (ViT), are introduced. Five overfitting prevention methods are summarized: batch normalization, dropout, weight initialization, and data augmentation. The application of deep learning technology in medical image-based cancer analysis is sorted out. (3) Results: Deep learning has achieved great success in medical image-based cancer diagnosis, showing good results in image classification, image reconstruction, image detection, image segmentation, image registration, and image synthesis. However, the lack of high-quality labeled datasets limits the role of deep learning and faces challenges in rare cancer diagnosis, multi-modal image fusion, model explainability, and generalization. (4) Conclusions: There is a need for more public standard databases for cancer. The pre-training model based on deep neural networks has the potential to be improved, and special attention should be paid to the research of multimodal data fusion and supervised paradigm. Technologies such as ViT, ensemble learning, and few-shot learning will bring surprises to cancer diagnosis based on medical images. [ABSTRACT FROM AUTHOR]

Simple Summary: Brain MRI scans often require different imaging sequences based on tissue types, posing a common challenge. In our research, we propose a method that utilizes Generative Adversarial Networks (GAN) to translate T2-weighted-Fluid-attenuated-Inversion-Recovery (FLAIR) MRI volumes into T2-Weighted (T2W) volumes, and vice versa. To evaluate the effectiveness of our approach, we introduce a novel evaluation schema that incorporates radiomic features. We train two distinct GAN-based architectures, namely Cycle GAN and Dual Cycle-Consistent Adversarial network (DC2Anet), using 510 pair-slices from 102 patients. Our findings indicate that the generative methods can produce results similar to the original sequence without significant changes in radiometric features. This method has the potential to assist clinicians in making informed decisions based on generated images when alternative sequences are unavailable, or time constraints prevent re-scanning MRI patients. One of the most common challenges in brain MRI scans is to perform different MRI sequences depending on the type and properties of tissues. In this paper, we propose a generative method to translate T2-Weighted (T2W) Magnetic Resonance Imaging (MRI) volume from T2-weight-Fluid-attenuated-Inversion-Recovery (FLAIR) and vice versa using Generative Adversarial Networks (GAN). To evaluate the proposed method, we propose a novel evaluation schema for generative and synthetic approaches based on radiomic features. For the evaluation purpose, we consider 510 pair-slices from 102 patients to train two different GAN-based architectures Cycle GAN and Dual Cycle-Consistent Adversarial network (DC2Anet). The results indicate that generative methods can produce similar results to the original sequence without significant change in the radiometric feature. Therefore, such a method can assist clinics to make decisions based on the generated image when different sequences are not available or there is not enough time to re-perform the MRI scans. [ABSTRACT FROM AUTHOR]

Simple Summary: Accurately grading gliomas, which are the most common and aggressive malignant brain tumors in adults, poses a significant challenge for radiologists. This study explores the application of Deep Learning techniques in assisting tumor grading using Magnetic Resonance Images (MRIs). By analyzing a glioma database sourced from multiple public datasets and comparing different settings, the aim of this study is to develop a robust and reliable grading system. The study demonstrates that by focusing on the tumor region of interest and augmenting the available data, there is a significant improvement in both the accuracy and confidence of tumor grade classifications. While successful in differentiating low-grade gliomas from high-grade gliomas, the accurate classification of grades 2, 3, and 4 remains challenging. The research findings have significant implications for advancing the development of a non-invasive, robust, and trustworthy data-driven system to support clinicians in the diagnosis and therapy planning of glioma patients. Glioma is the most common type of tumor in humans originating in the brain. According to the World Health Organization, gliomas can be graded on a four-stage scale, ranging from the most benign to the most malignant. The grading of these tumors from image information is a far from trivial task for radiologists and one in which they could be assisted by machine-learning-based decision support. However, the machine learning analytical pipeline is also fraught with perils stemming from different sources, such as inadvertent data leakage, adequacy of 2D image sampling, or classifier assessment biases. In this paper, we analyze a glioma database sourced from multiple datasets using a simple classifier, aiming to obtain a reliable tumor grading and, on the way, we provide a few guidelines to ensure such reliability. Our results reveal that by focusing on the tumor region of interest and using data augmentation techniques we significantly enhanced the accuracy and confidence in tumor classifications. Evaluation on an independent test set resulted in an AUC-ROC of 0.932 in the discrimination of low-grade gliomas from high-grade gliomas, and an AUC-ROC of 0.893 in the classification of grades 2, 3, and 4. The study also highlights the importance of providing, beyond generic classification performance, measures of how reliable and trustworthy the model's output is, thus assessing the model's certainty and robustness. [ABSTRACT FROM AUTHOR]

Simple Summary: Breast cancer is one of the leading causes of cancer death among women. Developing machine learning-based diagnosis models receives great attention from researchers and scientists using histopathology images. Deep learning (DL) algorithms automatically extract features from raw data through convolutional operations. The generalization of the DL models' results relies on large datasets, although they eliminate the expert knowledge in the feature extraction stage. This work aimed to compare the performance of the features extracted via deep learning and a knowledge-based approach in breast cancer detection from histopathology images. Cancer develops when a single or a group of cells grows and spreads uncontrollably. Histopathology images are used in cancer diagnosis since they show tissue and cell structures under a microscope. Knowledge-based and deep learning-based computer-aided detection is an ongoing research field in cancer diagnosis using histopathology images. Feature extraction is vital in both approaches since the feature set is fed to a classifier and determines the performance. This paper evaluates three feature extraction methods and their performance in breast cancer diagnosis. Features are extracted by (1) a Convolutional Neural Network, (2) a transfer learning architecture VGG16, and (3) a knowledge-based system. The feature sets are tested by seven classifiers, including Neural Network (64 units), Random Forest, Multilayer Perceptron, Decision Tree, Support Vector Machines, K-Nearest Neighbors, and Narrow Neural Network (10 units) on the BreakHis 400× image dataset. The CNN achieved up to 85% for the Neural Network and Random Forest, the VGG16 method achieved up to 86% for the Neural Network, and the knowledge-based features achieved up to 98% for Neural Network, Random Forest, Multilayer Perceptron classifiers. [ABSTRACT FROM AUTHOR]

Simple Summary: This paper discusses the importance of early detection of brain tumors and the limitations of traditional diagnosis methods. The use of deep learning models for brain tumor detection is introduced as a potential solution, but the high computing costs and potential biases in training data pose challenges. The study proposes a new, end-to-end, lightweight deep learning model for brain tumor detection that outperforms other models and is suitable for real-time applications. The study also provides a framework for secure data transfer of medical lab results and security recommendations to ensure security on the Internet of Medical Things (IoMT). In the field of medical imaging, deep learning has made considerable strides, particularly in the diagnosis of brain tumors. The Internet of Medical Things (IoMT) has made it possible to combine these deep learning models into advanced medical devices for more accurate and efficient diagnosis. Convolutional neural networks (CNNs) are a popular deep learning technique for brain tumor detection because they can be trained on vast medical imaging datasets to recognize cancers in new images. Despite its benefits, which include greater accuracy and efficiency, deep learning has disadvantages, such as high computing costs and the possibility of skewed findings due to inadequate training data. Further study is needed to fully understand the potential and limitations of deep learning in brain tumor detection in the IoMT and to overcome the obstacles associated with real-world implementation. In this study, we propose a new CNN-based deep learning model for brain tumor detection. The suggested model is an end-to-end model, which reduces the system's complexity in comparison to earlier deep learning models. In addition, our model is lightweight, as it is built from a small number of layers compared to other previous models, which makes the model suitable for real-time applications. The optimistic findings of a rapid increase in accuracy (99.48% for binary class and 96.86% for multi-class) demonstrate that the new framework model has excelled in the competition. This study demonstrates that the suggested deep model outperforms other CNNs for detecting brain tumors. Additionally, the study provides a framework for secure data transfer of medical lab results with security recommendations to ensure security in the IoMT. [ABSTRACT FROM AUTHOR]

Simple Summary: In this paper, we investigate the application of deep learning for classifying whole-slide images of cutaneous histopathological specimens into melanoma and non-melanoma. To do so, we used a total of 66 images (33 melanomas and 33 non-melanomas) to train models and evaluated them on 90 whole-slide images (40 melanomas and 50 non-melanomas). The best model achieved ROC–AUC at 0.821 for the whole-slide image level and 0.936 for the tile level. Although the histopathological diagnosis of cutaneous melanocytic lesions is fairly accurate and reliable among experienced surgical pathologists, it is not perfect in every case (especially melanoma). Microscopic examination–clinicopathological correlation is the gold standard for the definitive diagnosis of melanoma. Pathologists may encounter diagnostic controversies when melanoma closely mimics Spitz's nevus or blue nevus, exhibits amelanotic histopathology, or is in situ. It would be beneficial if diagnosing cutaneous melanocytic lesions can be automated by using deep learning, particularly when assisting surgical pathologists with their workloads. In this preliminary study, we investigated the application of deep learning for classifying cutaneous melanoma in whole-slide images (WSIs). We trained models via weakly supervised learning using a dataset of 66 WSIs (33 melanomas and 33 non-melanomas). We evaluated the models on a test set of 90 WSIs (40 melanomas and 50 non-melanomas), achieving ROC–AUC at 0.821 for the WSI level and 0.936 for the tile level by the best model. [ABSTRACT FROM AUTHOR]

Simple Summary: To investigate the adoption of machine learning in palliative care research and clinical practice, we systematically searched for published research papers on the topic. We found several publications that used different kinds of machine learning in palliative care for different use cases. However, on average, there needs to be more rigorous testing of the models to ensure that they work well in different settings. Objective: To summarize the available literature on using machine learning (ML) for palliative care practice as well as research and to assess the adherence of the published studies to the most important ML best practices. Methods: The MEDLINE database was searched for the use of ML in palliative care practice or research, and the records were screened according to PRISMA guidelines. Results: In total, 22 publications using machine learning for mortality prediction (n = 15), data annotation (n = 5), predicting morbidity under palliative therapy (n = 1), and predicting response to palliative therapy (n = 1) were included. Publications used a variety of supervised or unsupervised models, but mostly tree-based classifiers and neural networks. Two publications had code uploaded to a public repository, and one publication uploaded the dataset. Conclusions: Machine learning in palliative care is mainly used to predict mortality. Similarly to other applications of ML, external test sets and prospective validations are the exception. [ABSTRACT FROM AUTHOR]

Simple Summary: The classification is performed later by an interactively learning Swin Transformer block, the core unit for feature representation and long-range semantic information. In particular, the proposed strategy improved significantly and was very resilient while dealing with small liver pieces, discontinuous liver regions, and fuzzy liver boundaries. The experimental results confirm that the proposed APESTNet is more effective in classifying liver tumours than the current state-of-the-art models. Without compromising accuracy, the proposed method conserved resources. However, the proposed method is prone to slight over-segmentation or under-segmentation errors when dealing with lesions or tumours at the liver boundary. Therefore, our future work will concentrate on completely utilizing the z-axis information in 3D to reduce errors. Diagnosis and treatment of hepatocellular carcinoma or metastases rely heavily on accurate segmentation and classification of liver tumours. However, due to the liver tumor's hazy borders and wide range of possible shapes, sizes, and positions, accurate and automatic tumour segmentation and classification remains a difficult challenge. With the advancement of computing, new models in artificial intelligence have evolved. Following its success in Natural language processing (NLP), the transformer paradigm has been adopted by the computer vision (CV) community of the NLP. While there are already accepted approaches to classifying the liver, especially in clinical settings, there is room for advancement in terms of their precision. This paper makes an effort to apply a novel model for segmenting and classifying liver tumours built on deep learning. In order to accomplish this, the created model follows a three-stage procedure consisting of (a) pre-processing, (b) liver segmentation, and (c) classification. In the first phase, the collected Computed Tomography (CT) images undergo three stages of pre-processing, including contrast improvement via histogram equalization and noise reduction via the median filter. Next, an enhanced mask region-based convolutional neural networks (Mask R-CNN) model is used to separate the liver from the CT abdominal image. To prevent overfitting, the segmented picture is fed onto an Enhanced Swin Transformer Network with Adversarial Propagation (APESTNet). The experimental results prove the superior performance of the proposed perfect on a wide variety of CT images, as well as its efficiency and low sensitivity to noise. [ABSTRACT FROM AUTHOR]

Simple Summary: Skin cancer is a life-threatening condition. It is difficult to diagnose in its early stages; therefore, we proposed an easy-to-use telemedicine device to tackle skin cancer without expert intervention. The deep learning model automatically detects skin cancer patches on lesions with a credit-card-sized device named Raspberry Pi and a small camera. This paper also presents a digital hair removal algorithm to enhance the quality of medical images for better analysis by medical experts and AI methods. Our method does not need an expert operator; even ordinary people can use it with the instruction manual. It will be useful for developing countries or remote places when there is a scarcity of oncologists. Cancer remains a deadly disease. We developed a lightweight, accurate, general-purpose deep learning algorithm for skin cancer classification. Squeeze-MNet combines a Squeeze algorithm for digital hair removal during preprocessing and a MobileNet deep learning model with predefined weights. The Squeeze algorithm extracts important image features from the image, and the black-hat filter operation removes noise. The MobileNet model (with a dense neural network) was developed using the International Skin Imaging Collaboration (ISIC) dataset to fine-tune the model. The proposed model is lightweight; the prototype was tested on a Raspberry Pi 4 Internet of Things device with a Neo pixel 8-bit LED ring; a medical doctor validated the device. The average precision (AP) for benign and malignant diagnoses was 99.76% and 98.02%, respectively. Using our approach, the required dataset size decreased by 66%. The hair removal algorithm increased the accuracy of skin cancer detection to 99.36% with the ISIC dataset. The area under the receiver operating curve was 98.9%. [ABSTRACT FROM AUTHOR]

Simple Summary: This paper presents a breast cancer detection approach where the convoluted features from a convolutional neural network are utilized to train a machine learning model. Results demonstrate that use of convoluted features yields better results than the original features to classify malignant and benign tumors. Breast cancer is a common cause of female mortality in developing countries. Screening and early diagnosis can play an important role in the prevention and treatment of these cancers. This study proposes an ensemble learning-based voting classifier that combines the logistic regression and stochastic gradient descent classifier with deep convoluted features for the accurate detection of cancerous patients. Deep convoluted features are extracted from the microscopic features and fed to the ensemble voting classifier. This idea provides an optimized framework that accurately classifies malignant and benign tumors with improved accuracy. Results obtained using the voting classifier with convoluted features demonstrate that the highest classification accuracy of 100% is achieved. The proposed approach revealed the accuracy enhancement in comparison with the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Simple Summary: This paper aims to develops a new Manta Ray Foraging Optimization Transfer Learning technique that is based on Gastric Cancer Diagnosis and Classification (MRFOTL-GCDC) using endoscopic images. Gastric cancer (GC) diagnoses using endoscopic images have gained significant attention in the healthcare sector. The recent advancements of computer vision (CV) and deep learning (DL) technologies pave the way for the design of automated GC diagnosis models. Therefore, this study develops a new Manta Ray Foraging Optimization Transfer Learning technique that is based on Gastric Cancer Diagnosis and Classification (MRFOTL-GCDC) using endoscopic images. For enhancing the quality of the endoscopic images, the presented MRFOTL-GCDC technique executes the Wiener filter (WF) to perform a noise removal process. In the presented MRFOTL-GCDC technique, MRFO with SqueezeNet model is used to derive the feature vectors. Since the trial-and-error hyperparameter tuning is a tedious process, the MRFO algorithm-based hyperparameter tuning results in enhanced classification results. Finally, the Elman Neural Network (ENN) model is utilized for the GC classification. To depict the enhanced performance of the presented MRFOTL-GCDC technique, a widespread simulation analysis is executed. The comparison study reported the improvement of the MRFOTL-GCDC technique for endoscopic image classification purposes with an improved accuracy of 99.25%. [ABSTRACT FROM AUTHOR]

Simple Summary: This study investigates the latest achievements, challenges, and future research directions of deep learning techniques for lung cancer and pulmonary nodule detection. Hopefully, these research findings will help scientists, investigators, and clinicians develop new and effective medical imaging tools to improve lung nodule diagnosis accuracy, sensitivity, and specificity. Medical imaging tools are essential in early-stage lung cancer diagnostics and the monitoring of lung cancer during treatment. Various medical imaging modalities, such as chest X-ray, magnetic resonance imaging, positron emission tomography, computed tomography, and molecular imaging techniques, have been extensively studied for lung cancer detection. These techniques have some limitations, including not classifying cancer images automatically, which is unsuitable for patients with other pathologies. It is urgently necessary to develop a sensitive and accurate approach to the early diagnosis of lung cancer. Deep learning is one of the fastest-growing topics in medical imaging, with rapidly emerging applications spanning medical image-based and textural data modalities. With the help of deep learning-based medical imaging tools, clinicians can detect and classify lung nodules more accurately and quickly. This paper presents the recent development of deep learning-based imaging techniques for early lung cancer detection. [ABSTRACT FROM AUTHOR]

Simple Summary: A total laryngectomy involves the full and permanent separation of the upper and lower airways, resulting in the loss of voice and inability to interact vocally. To identify, extract, and evaluate replacement voicing following laryngeal oncosurgery, we propose employing convolutional neural networks for categorization of speech representations (spectrograms). With an overall accuracy of 89.47 percent, our technique has the greatest true-positive rate of any of the tested state-of-the-art methodologies. Laryngeal carcinoma is the most common malignant tumor of the upper respiratory tract. Total laryngectomy provides complete and permanent detachment of the upper and lower airways that causes the loss of voice, leading to a patient's inability to verbally communicate in the postoperative period. This paper aims to exploit modern areas of deep learning research to objectively classify, extract and measure the substitution voicing after laryngeal oncosurgery from the audio signal. We propose using well-known convolutional neural networks (CNNs) applied for image classification for the analysis of voice audio signal. Our approach takes an input of Mel-frequency spectrogram (MFCC) as an input of deep neural network architecture. A database of digital speech recordings of 367 male subjects (279 normal speech samples and 88 pathological speech samples) was used. Our approach has shown the best true-positive rate of any of the compared state-of-the-art approaches, achieving an overall accuracy of 89.47%. [ABSTRACT FROM AUTHOR]

Simple Summary: Cancer develops through a complex process involving genetic changes that can lead to uncontrolled cell growth and tumor formation. This research focuses on developing an advanced approach to classify tumors into meaningful subgroups based on somatic mutations. Using machine learning techniques, specifically a deep neural network, and integrating genetic data with known gene interaction networks, we propose a framework for tumor stratification, called D3NS (deep neural network integrated into network-based stratification). This framework identifies patient subtypes predictive for survival and significantly associated with several clinical outcomes (tumor stage, grade and treatment response). We applied D3NS to real-world data from the Cancer Genome Atlas for bladder, ovarian, and kidney cancers. The results demonstrate the potential of this approach to improve cancer stratification, positioning it as a useful base model for cancer research and a promising tool in clinical settings. (1) Background: The identification of tumor subtypes is fundamental in precision medicine for accurate diagnoses and personalized therapies. Cancer development is often driven by the accumulation of somatic mutations that can cause alterations in tissue functions and morphologies. In this work, a method based on a deep neural network integrated into a network-based stratification framework (D3NS) is proposed to stratify tumors according to somatic mutations. (2) Methods: This approach leverages the power of deep neural networks to detect hidden information in the data by combining the knowledge contained in a network of gene interactions, as typical of network-based stratification methods. D3NS was applied using real-world data from The Cancer Genome Atlas for bladder, ovarian, and kidney cancers. (3) Results: This technique allows for the identification of tumor subtypes characterized by different survival rates and significant associations with several clinical outcomes (tumor stage, grade or response to therapy). (4) Conclusion: D3NS can provide a base model in cancer research and could be considered as a useful tool for tumor stratification, offering potential support in clinical settings. [ABSTRACT FROM AUTHOR]

This review provides a formal overview of current automatic segmentation studies that use deep learning in radiotherapy. It covers 807 published papers and includes multiple cancer sites, image types (CT/MRI/PET), and segmentation methods. We collect key statistics about the papers to uncover commonalities, trends, and methods, and identify areas where more research might be needed. Moreover, we analyzed the corpus by posing explicit questions aimed at providing high-quality and actionable insights, including: “What should researchers think about when starting a segmentation study?”, “How can research practices in medical image segmentation be improved?”, “What is missing from the current corpus?”, and more. This allowed us to provide practical guidelines on how to conduct a good segmentation study in today’s competitive environment that will be useful for future research within the field, regardless of the specific radiotherapeutic subfield. To aid in our analysis, we used the large language model ChatGPT to condense information.

Simple Summary: The prediction of tumor response after neoadjuvant FLOT therapy is highly necessary. The use of deep learning on gastroesophageal biopsies enabled us to extract predictive information. This prediction model could be easily applied in clinical decision making. Patients could avoid unnecessary treatment or receive an intensified FLOT therapy. Background: The aim of this study was to establish a deep learning prediction model for neoadjuvant FLOT chemotherapy response. The neural network utilized clinical data and visual information from whole-slide images (WSIs) of therapy-naïve gastroesophageal cancer biopsies. Methods: This study included 78 patients from the University Hospital of Cologne and 59 patients from the University Hospital of Heidelberg used as external validation. Results: After surgical resection, 33 patients from Cologne (42.3%) were ypN0 and 45 patients (57.7%) were ypN+, while 23 patients from Heidelberg (39.0%) were ypN0 and 36 patients (61.0%) were ypN+ (p = 0.695). The neural network had an accuracy of 92.1% to predict lymph node metastasis and the area under the curve (AUC) was 0.726. A total of 43 patients from Cologne (55.1%) had less than 50% residual vital tumor (RVT) compared to 34 patients from Heidelberg (57.6%, p = 0.955). The model was able to predict tumor regression with an error of ±14.1% and an AUC of 0.648. Conclusions: This study demonstrates that visual features extracted by deep learning from therapy-naïve biopsies of gastroesophageal adenocarcinomas correlate with positive lymph nodes and tumor regression. The results will be confirmed in prospective studies to achieve early allocation of patients to the most promising treatment. [ABSTRACT FROM AUTHOR]

Simple Summary: This research aims to evaluate the effectiveness of a machine learning algorithm, XGBoost, in predicting treatment recommendations for patients with hepatocellular carcinoma (HCC). The study uses clinical and imaging data from patients discussed at a multidisciplinary tumor board. The findings suggest that the algorithm can accurately predict all eight treatment recommendations made by the board, potentially aiding clinical decision-making in settings lacking subspecialty expertise. This study addresses the potential of machine learning in predicting treatment recommendations for patients with hepatocellular carcinoma (HCC). Using an IRB-approved retrospective study of patients discussed at a multidisciplinary tumor board, clinical and imaging variables were extracted and used in a gradient-boosting machine learning algorithm, XGBoost. The algorithm's performance was assessed using confusion matrix metrics and the area under the Receiver Operating Characteristics (ROC) curve. The study included 140 patients (mean age 67.7 ± 8.9 years), and the algorithm was found to be predictive of all eight treatment recommendations made by the board. The model's predictions were more accurate than those based on published therapeutic guidelines by ESMO and NCCN. The study concludes that a machine learning model incorporating clinical and imaging variables can predict treatment recommendations made by an expert multidisciplinary tumor board, potentially aiding clinical decision-making in settings lacking subspecialty expertise. [ABSTRACT FROM AUTHOR]

Simple Summary: A prolonged diagnosis of lung cancer can hinder effective treatment processes for cancer patients. Artificial intelligence-based models significantly impact the healthcare system; deep-learning algorithms in the diagnostic process can save time and money and provide high-accuracy results that accelerate and improve the treatment journey. Lung cancer is the leading cause of cancer-related deaths worldwide. Two of the crucial factors contributing to these fatalities are delayed diagnosis and suboptimal prognosis. The rapid advancement of deep learning (DL) approaches provides a significant opportunity for medical imaging techniques to play a pivotal role in the early detection of lung tumors and subsequent monitoring during treatment. This study presents a DL-based model for efficient lung cancer detection using whole-slide images. Our methodology combines convolutional neural networks (CNNs) and separable CNNs with residual blocks, thereby improving classification performance. Our model improves accuracy (96% to 98%) and robustness in distinguishing between cancerous and non-cancerous lung cell images in less than 10 s. Moreover, the model's overall performance surpassed that of active pathologists, with an accuracy of 100% vs. 79%. There was a significant linear correlation between pathologists' accuracy and years of experience (r Pearson = 0.71, 95% CI 0.14 to 0.93, p = 0.022). We conclude that this model enhances the accuracy of cancer detection and can be used to train junior pathologists. [ABSTRACT FROM AUTHOR]

Simple Summary: Early detection of malignant melanoma (MM) has the potential to significantly reduce morbidity and mortality as the thickness of the lesion is closely associated with prognosis. Artificial intelligence (AI) is a non-invasive technology that has the potential to aid clinicians in the early diagnosis of skin cancers, including melanoma. Performance metrics of machine-based AI have been shown to rival or improve upon clinician diagnosis. However, many studies have limited this scope to pre-build image databases that may not replicate real-world settings experienced in general practice. This systematic review aimed to report the performance of commercial or market-approved dermatoscopic systems with AI in the form of convolutional neural networks (CNNs) when tasked with classifying melanoma. The sensitivity and specificity of CNNs are highly varied and illustrate the necessity of clinician-to-patient interaction in the diagnosis process. Clinicians working in unison with AI show the most promise for better performance when classifying MM. Background: Cutaneous melanoma remains an increasing global public health burden, particularly in fair-skinned populations. Advancing technologies, particularly artificial intelligence (AI), may provide an additional tool for clinicians to help detect malignancies with a more accurate success rate. This systematic review aimed to report the performance metrics of commercially available convolutional neural networks (CNNs) tasked with detecting MM. Methods: A systematic literature search was performed using CINAHL, Medline, Scopus, ScienceDirect and Web of Science databases. Results: A total of 16 articles reporting MM were included in this review. The combined number of melanomas detected was 1160, and non-melanoma lesions were 33,010. The performance of market-approved technology and clinician performance for classifying melanoma was highly heterogeneous, with sensitivity ranging from 16.4 to 100.0%, specificity between 40.0 and 98.3% and accuracy between 44.0 and 92.0%. Less heterogeneity was observed when clinicians worked in unison with AI, with sensitivity ranging between 83.3 and 100.0%, specificity between 83.7 and 87.3%, and accuracy between 86.4 and 86.9%. Conclusion: Instead of focusing on the performance of AI versus clinicians for classifying melanoma, more consistent performance has been obtained when clinicians' work is supported by AI, facilitating management decisions and improving health outcomes. [ABSTRACT FROM AUTHOR]

Simple Summary: Breast cancer is one of the deadliest forms of cancer, but early and accurate diagnosis can significantly boost patient survival rates. Traditional classification models struggle with the diverse characteristics of breast tumor pathology images, leading to misdiagnoses. To tackle this challenge, our study introduces a new model, combining Single-Task Meta Learning and an auxiliary network to enhance diagnosis accuracy. This innovative approach enables the model to better generalize, recognizing and categorizing varied image data effectively. Our findings reveal that it surpasses current methods, boosting classification accuracy in complex tasks by at least 1.85%. Moreover, a 31.85% increase in the Silhouette Score for the model's learned features indicates an improved ability to identify critical differences between tumor types. This advancement not only promises more accurate early diagnoses but also holds the potential to save lives, showcasing a significant leap forward in the clinical management of breast cancer. Breast cancer has a high mortality rate among cancers. If the type of breast tumor can be correctly diagnosed at an early stage, the survival rate of the patients will be greatly improved. Considering the actual clinical needs, the classification model of breast pathology images needs to have the ability to make a correct classification, even in facing image data with different characteristics. The existing convolutional neural network (CNN)-based models for the classification of breast tumor pathology images lack the requisite generalization capability to maintain high accuracy when confronted with pathology images of varied characteristics. Consequently, this study introduces a new classification model, STMLAN (Single-Task Meta Learning with Auxiliary Network), which integrates Meta Learning and an auxiliary network. Single-Task Meta Learning was proposed to endow the model with generalization ability, and the auxiliary network was used to enhance the feature characteristics of breast pathology images. The experimental results demonstrate that the STMLAN model proposed in this study improves accuracy by at least 1.85% in challenging multi-classification tasks compared to the existing methods. Furthermore, the Silhouette Score corresponding to the features learned by the model has increased by 31.85%, reflecting that the proposed model can learn more discriminative features, and the generalization ability of the overall model is also improved. [ABSTRACT FROM AUTHOR]

Simple Summary: According to the World Fund for Research on Cancer, skin cancer is one of the most common cancers. The early diagnosis of skin cancer lesions plays an essential role in the patient's recovery. Nevertheless, recognizing skin cancer and differentiating it from benign skin lesions is a challenging task for dermatologists due to the visual similarities of benign nevi, seborrheic keratoses, and malignant melanomas. In this context, image-based skin lesion recognition systems have appeared as a solution to recognize these lesions and therefore reduce the number of biopsy procedures. This research investigated the performance of the latest versions of the You Only Look Once (YOLO) deep learning models. Unlike classification-based solutions, the proposed YOLO-based approach locates the skin lesions and categorizes them into the predefined classes. The experiments were conducted using 2750 images from the publicly accessible International Skin Imaging Collaboration (ISIC) dataset. The incidence of skin cancer is rising globally, posing a significant public health threat. An early and accurate diagnosis is crucial for patient prognoses. However, discriminating between malignant melanoma and benign lesions, such as nevi and keratoses, remains a challenging task due to their visual similarities. Image-based recognition systems offer a promising solution to aid dermatologists and potentially reduce unnecessary biopsies. This research investigated the performance of four unified convolutional neural networks, namely, YOLOv3, YOLOv4, YOLOv5, and YOLOv7, in classifying skin lesions. Each model was trained on a benchmark dataset, and the obtained performances were compared based on lesion localization, classification accuracy, and inference time. In particular, YOLOv7 achieved superior performance with an Intersection over Union (IoU) of 86.3%, a mean Average Precision (mAP) of 75.4%, an F1-measure of 80%, and an inference time of 0.32 s per image. These findings demonstrated the potential of YOLOv7 as a valuable tool for aiding dermatologists in early skin cancer diagnosis and potentially reducing unnecessary biopsies. [ABSTRACT FROM AUTHOR]

Simple Summary: Transformer models, originally successful in natural language processing, have found application in computer vision, demonstrating promising results in tasks related to cancer image analysis. Despite being one of the prevalent and swiftly spreading cancers globally, there is a pressing need for accurate automated analysis methods for oral cancer. This need is particularly critical for high-risk populations residing in low- and middle-income countries. In this study, we evaluated the performance of the Vision Transformer (ViT) and the Swin Transformer in the classification of mobile-based oral cancer images we collected from high-risk populations. The results showed that the Swin Transformer model achieved higher accuracy than the ViT model, and both transformer models work better than the conventional convolution model VGG19. Oral cancer, a pervasive and rapidly growing malignant disease, poses a significant global health concern. Early and accurate diagnosis is pivotal for improving patient outcomes. Automatic diagnosis methods based on artificial intelligence have shown promising results in the oral cancer field, but the accuracy still needs to be improved for realistic diagnostic scenarios. Vision Transformers (ViT) have outperformed learning CNN models recently in many computer vision benchmark tasks. This study explores the effectiveness of the Vision Transformer and the Swin Transformer, two cutting-edge variants of the transformer architecture, for the mobile-based oral cancer image classification application. The pre-trained Swin transformer model achieved 88.7% accuracy in the binary classification task, outperforming the ViT model by 2.3%, while the conventional convolutional network model VGG19 and ResNet50 achieved 85.2% and 84.5% accuracy. Our experiments demonstrate that these transformer-based architectures outperform traditional convolutional neural networks in terms of oral cancer image classification, and underscore the potential of the ViT and the Swin Transformer in advancing the state of the art in oral cancer image analysis. [ABSTRACT FROM AUTHOR]

Simple Summary: Stimulated Raman Histology (SRH) is a technique that uses laser light to create detailed images of tissues without the need for traditional staining. This study aimed to use deep learning to classify oral squamous cell carcinoma (OSCC) and different non-malignant tissue types using SRH images. The performances of the classifications between SRH images and the original images obtained from stimulated Raman scattering (SRS) were compared. A deep learning model was trained on 64 images and tested on 16, showing that it could effectively identify tissue types during surgery, potentially speeding up decision making in oral cancer surgery. Stimulated Raman Histology (SRH) employs the stimulated Raman scattering (SRS) of photons at biomolecules in tissue samples to generate histological images. Subsequent pathological analysis allows for an intraoperative evaluation without the need for sectioning and staining. The objective of this study was to investigate a deep learning-based classification of oral squamous cell carcinoma (OSCC) and the sub-classification of non-malignant tissue types, as well as to compare the performances of the classifier between SRS and SRH images. Raman shifts were measured at wavenumbers k1 = 2845 cm−1 and k2 = 2930 cm−1. SRS images were transformed into SRH images resembling traditional H&E-stained frozen sections. The annotation of 6 tissue types was performed on images obtained from 80 tissue samples from eight OSCC patients. A VGG19-based convolutional neural network was then trained on 64 SRS images (and corresponding SRH images) and tested on 16. A balanced accuracy of 0.90 (0.87 for SRH images) and F1-scores of 0.91 (0.91 for SRH) for stroma, 0.98 (0.96 for SRH) for adipose tissue, 0.90 (0.87 for SRH) for squamous epithelium, 0.92 (0.76 for SRH) for muscle, 0.87 (0.90 for SRH) for glandular tissue, and 0.88 (0.87 for SRH) for tumor were achieved. The results of this study demonstrate the suitability of deep learning for the intraoperative identification of tissue types directly on SRS and SRH images. [ABSTRACT FROM AUTHOR]

Simple Summary: Topic modeling was introduced to classify texts of natural language by inferring their topic structure from the frequency of words. This paper assumes that analogously the cancer subtype identity, which is crucial for the correct diagnosis and treatment plan, can be extracted from gene expression patterns with similar techniques. Focusing on breast and lung cancer, we show that state-of-the-art topic modeling techniques can successfully classify known subtypes and identify cohorts of patients with different survival probabilities. The topic structure hidden in expression data can be looked at as a biologically relevant low-dimensional data representation that can be used to build efficient classifiers of expression patterns. Topic modeling is a widely used technique to extract relevant information from large arrays of data. The problem of finding a topic structure in a dataset was recently recognized to be analogous to the community detection problem in network theory. Leveraging on this analogy, a new class of topic modeling strategies has been introduced to overcome some of the limitations of classical methods. This paper applies these recent ideas to TCGA transcriptomic data on breast and lung cancer. The established cancer subtype organization is well reconstructed in the inferred latent topic structure. Moreover, we identify specific topics that are enriched in genes known to play a role in the corresponding disease and are strongly related to the survival probability of patients. Finally, we show that a simple neural network classifier operating in the low dimensional topic space is able to predict with high accuracy the cancer subtype of a test expression sample. [ABSTRACT FROM AUTHOR]

Simple Summary: This study proposes an innovative approach to automatically identify invasive carcinoma regions in breast cancer immunohistochemistry whole-slide images, which is crucial for fully automated immunohistochemistry quantification. The proposed method leverages a neural network that combines multi-scale morphological features with boundary features, enabling precise segmentation of invasive carcinoma regions without the need for additional staining slides. The model demonstrated an impressive intersection over union score on the test set, and a fully automated Ki-67 scoring system based on the model's predictions exhibited high consistency with the scores given by experienced pathologists. The proposed method brings the breast cancer fully immunohistochemistry quantitative scoring system one step closer to clinical application. Aims: The automation of quantitative evaluation for breast immunohistochemistry (IHC) plays a crucial role in reducing the workload of pathologists and enhancing the objectivity of diagnoses. However, current methods face challenges in achieving fully automated immunohistochemistry quantification due to the complexity of segmenting the tumor area into distinct ductal carcinoma in situ (DCIS) and invasive carcinoma (IC) regions. Moreover, the quantitative analysis of immunohistochemistry requires a specific focus on invasive carcinoma regions. Methods and Results: In this study, we propose an innovative approach to automatically identify invasive carcinoma regions in breast cancer immunohistochemistry whole-slide images (WSIs). Our method leverages a neural network that combines multi-scale morphological features with boundary features, enabling precise segmentation of invasive carcinoma regions without the need for additional H&E and P63 staining slides. In addition, we introduced an advanced semi-supervised learning algorithm, allowing efficient training of the model using unlabeled data. To evaluate the effectiveness of our approach, we constructed a dataset consisting of 618 IHC-stained WSIs from 170 cases, including four types of staining (ER, PR, HER2, and Ki-67). Notably, the model demonstrated an impressive intersection over union (IoU) score exceeding 80% on the test set. Furthermore, to ascertain the practical utility of our model in IHC quantitative evaluation, we constructed a fully automated Ki-67 scoring system based on the model's predictions. Comparative experiments convincingly demonstrated that our system exhibited high consistency with the scores given by experienced pathologists. Conclusions: Our developed model excels in accurately distinguishing between DCIS and invasive carcinoma regions in breast cancer immunohistochemistry WSIs. This method paves the way for a clinically available, fully automated immunohistochemistry quantitative scoring system. [ABSTRACT FROM AUTHOR]

Simple Summary: While melanoma accounts for 4% of skin cancer cases, it causes 75% of skin-cancer-related deaths. The survival rate for melanoma is higher for early-identified cases, so improved access to diagnosis and screening programs is essential for addressing skin cancer deaths. Computer-aided diagnosis utilizing machine learning can be used to differentiate malignant and benign skin lesions. There is significant research into the use of convolutional neural networks to classify skin lesions from dermoscopic images. However, to provide cost-effective and accessible options for early detection of malignant melanoma, smartphone applications capable of accurately classifying skin lesions from images taken on a smartphone would be beneficial. This research investigates a previously underexplored dataset of smartphone images and develops a novel multi-layer deep convolutional neural network model, named SkinLesNet, to classify three types of skin lesions, including melanoma. Further studies to validate the model should be conducted as other image datasets become available. Skin cancer is a widespread disease that typically develops on the skin due to frequent exposure to sunlight. Although cancer can appear on any part of the human body, skin cancer accounts for a significant proportion of all new cancer diagnoses worldwide. There are substantial obstacles to the precise diagnosis and classification of skin lesions because of morphological variety and indistinguishable characteristics across skin malignancies. Recently, deep learning models have been used in the field of image-based skin-lesion diagnosis and have demonstrated diagnostic efficiency on par with that of dermatologists. To increase classification efficiency and accuracy for skin lesions, a cutting-edge multi-layer deep convolutional neural network termed SkinLesNet was built in this study. The dataset used in this study was extracted from the PAD-UFES-20 dataset and was augmented. The PAD-UFES-20-Modified dataset includes three common forms of skin lesions: seborrheic keratosis, nevus, and melanoma. To comprehensively assess SkinLesNet's performance, its evaluation was expanded beyond the PAD-UFES-20-Modified dataset. Two additional datasets, HAM10000 and ISIC2017, were included, and SkinLesNet was compared to the widely used ResNet50 and VGG16 models. This broader evaluation confirmed SkinLesNet's effectiveness, as it consistently outperformed both benchmarks across all datasets. [ABSTRACT FROM AUTHOR]

Simple Summary: Prognosis of patients after surgical resection for hepatocellular carcinoma (HCC) is often obscured by the variable impact of the tumor and remaining liver properties. We applied a convolutional neural network and hexagonal grid analytics to extract prognostic indicators from collagen microarchitecture within the tumor and adjacent liver tissue. By associating the extracted features from two distinct fiber types with clinical outcomes, we have developed two computational models to predict the overall survival of the patients. We report the independent prognostic roles for reticulin in HCC and fibrillary collagen in the peritumoral liver, highlighting the significance of assessing region-specific and type-specific fiber features. Our study provides evidence that the predictive power of prognostic models of HCC can be enhanced by artificial intelligence solutions generating computational image-based biomarkers. Despite advances in diagnostic and treatment technologies, predicting outcomes of patients with hepatocellular carcinoma (HCC) remains a challenge. Prognostic models are further obscured by the variable impact of the tumor properties and the remaining liver parenchyma, often affected by cirrhosis or non-alcoholic fatty liver disease that tend to precede HCC. This study investigated the prognostic value of reticulin and collagen microarchitecture in liver resection samples. We analyzed 105 scanned tissue sections that were stained using a Gordon and Sweet's silver impregnation protocol combined with Picric Acid–Sirius Red. A convolutional neural network was utilized to segment the red-staining collagen and black linear reticulin strands, generating a detailed map of the fiber structure within the HCC and adjacent liver tissue. Subsequent hexagonal grid subsampling coupled with automated epithelial edge detection and computational fiber morphometry provided the foundation for region-specific tissue analysis. Two penalized Cox regression models using LASSO achieved a concordance index (C-index) greater than 0.7. These models incorporated variables such as patient age, tumor multifocality, and fiber-derived features from the epithelial edge in both the tumor and liver compartments. The prognostic value at the tumor edge was derived from the reticulin structure, while collagen characteristics were significant at the epithelial edge of peritumoral liver. The prognostic performance of these models was superior to models solely reliant on conventional clinicopathologic parameters, highlighting the utility of AI-extracted microarchitectural features for the management of HCC. [ABSTRACT FROM AUTHOR]

Simple Summary: The exponential growth in artificial intelligence development, particularly its application in capsule endoscopy, serves as a compelling model for gastroenterologists. This review focusses on the latest advancements in capsule endoscopy, analyzing the possible benefits and ethical challenges that artificial intelligence may bring to the field of minimally invasive capsule panendoscopy, while also offering insights into future directions. Specifically in the context of oncological gastrointestinal screening, there is still a need to explore alternative strategies for enhancing this process. Artificial intelligence-enhanced capsule panendoscopy has the potential to positively impact the future by addressing time constraints and improve accessibility through the use of highly efficient diagnostic models. In the early 2000s, the introduction of single-camera wireless capsule endoscopy (CE) redefined small bowel study. Progress continued with the development of double-camera devices, first for the colon and rectum, and then, for panenteric assessment. Advancements continued with magnetic capsule endoscopy (MCE), particularly when assisted by a robotic arm, designed to enhance gastric evaluation. Indeed, as CE provides full visualization of the entire gastrointestinal (GI) tract, a minimally invasive capsule panendoscopy (CPE) could be a feasible alternative, despite its time-consuming nature and learning curve, assuming appropriate bowel cleansing has been carried out. Recent progress in artificial intelligence (AI), particularly in the development of convolutional neural networks (CNN) for CE auxiliary reading (detecting and diagnosing), may provide the missing link in fulfilling the goal of establishing the use of panendoscopy, although prospective studies are still needed to validate these models in actual clinical scenarios. Recent CE advancements will be discussed, focusing on the current evidence on CNN developments, and their real-life implementation potential and associated ethical challenges. [ABSTRACT FROM AUTHOR]

Simple Summary: Current auto-segmentation methods for glioblastoma utilize mainly pre-operative 1.5T and 3T MRI. The first commercial MRI-linear accelerator (linac) radiation treatment platform acquires low-field (0.35T) post-operative MRI at the delivery of each treatment. This study presents the first automatic brain lesion segmentation network developed for MRI-linac to track tumor changes during radiotherapy. The tumors and resection cavities are automatically segmented using a deep learning network, allowing for daily monitoring of tumor volume changes, creation of tools necessary for adaptive radiotherapy of glioblastoma, and providing MRI regions of interest for further analyses that may discover prognostic markers. Glioblastoma changes during chemoradiotherapy are inferred from high-field MRI before and after treatment but are rarely investigated during radiotherapy. The purpose of this study was to develop a deep learning network to automatically segment glioblastoma tumors on daily treatment set-up scans from the first glioblastoma patients treated on MRI-linac. Glioblastoma patients were prospectively imaged daily during chemoradiotherapy on 0.35T MRI-linac. Tumor and edema (tumor lesion) and resection cavity kinetics throughout the treatment were manually segmented on these daily MRI. Utilizing a convolutional neural network, an automatic segmentation deep learning network was built. A nine-fold cross-validation schema was used to train the network using 80:10:10 for training, validation, and testing. Thirty-six glioblastoma patients were imaged pre-treatment and 30 times during radiotherapy (n = 31 volumes, total of 930 MRIs). The average tumor lesion and resection cavity volumes were 94.56 ± 64.68 cc and 72.44 ± 35.08 cc, respectively. The average Dice similarity coefficient between manual and auto-segmentation for tumor lesion and resection cavity across all patients was 0.67 and 0.84, respectively. This is the first brain lesion segmentation network developed for MRI-linac. The network performed comparably to the only other published network for auto-segmentation of post-operative glioblastoma lesions. Segmented volumes can be utilized for adaptive radiotherapy and propagated across multiple MRI contrasts to create a prognostic model for glioblastoma based on multiparametric MRI. [ABSTRACT FROM AUTHOR]

Simple Summary: Increasing treatment efficacy for head and neck cancer requires the utilization of patient-specific biomarkers to personalize therapy. Deep neural networks show promise for extracting prognostic biomarkers from medical imaging data to predict loco-regional tumor recurrence or disease progression. However, training these networks can be challenging due to limited available data, potentially affecting prediction quality. To address these challenges, we investigated the effectiveness of multiple multitask learning strategies, where two distinct outcome tasks and an auxiliary tumor segmentation objective were simultaneously optimized. This approach aimed to enhance the training process, leading to better parameter configurations and improved predictive performance. Our analysis, conducted on two multicentric datasets using convolutional neural networks and vision transformers, indicated performance benefits of outcome models trained using multitask strategies over models trained solely on a single outcome task. Neural-network-based outcome predictions may enable further treatment personalization of patients with head and neck cancer. The development of neural networks can prove challenging when a limited number of cases is available. Therefore, we investigated whether multitask learning strategies, implemented through the simultaneous optimization of two distinct outcome objectives (multi-outcome) and combined with a tumor segmentation task, can lead to improved performance of convolutional neural networks (CNNs) and vision transformers (ViTs). Model training was conducted on two distinct multicenter datasets for the endpoints loco-regional control (LRC) and progression-free survival (PFS), respectively. The first dataset consisted of pre-treatment computed tomography (CT) imaging for 290 patients and the second dataset contained combined positron emission tomography (PET)/CT data of 224 patients. Discriminative performance was assessed by the concordance index (C-index). Risk stratification was evaluated using log-rank tests. Across both datasets, CNN and ViT model ensembles achieved similar results. Multitask approaches showed favorable performance in most investigations. Multi-outcome CNN models trained with segmentation loss were identified as the optimal strategy across cohorts. On the PET/CT dataset, an ensemble of multi-outcome CNNs trained with segmentation loss achieved the best discrimination (C-index: 0.29, 95% confidence interval (CI): 0.22–0.36) and successfully stratified patients into groups with low and high risk of disease progression ( p = 0.003 ). On the CT dataset, ensembles of multi-outcome CNNs and of single-outcome ViTs trained with segmentation loss performed best (C-index: 0.26 and 0.26, CI: 0.18–0.34 and 0.18–0.35, respectively), both with significant risk stratification for LRC in independent validation ( p = 0.002 and p = 0.011 ). Further validation of the developed multitask-learning models is planned based on a prospective validation study, which has recently completed recruitment. [ABSTRACT FROM AUTHOR]

Simple Summary: This study presents an AI system for the automatic diagnosis of lung cancer based on lung nodule images from CT scans. Lung cancer is the leading cause of cancer-related deaths in Taiwan, and early detection can improve the survival rate of patients. The system uses a 3D interpretable hierarchical semantic convolutional neural network (HSNet) that can recognize different features of lung nodules, such as calcification, margin, texture, sphericity, and malignancy. The system achieves better performance than previous methods, with high accuracy and interpretability. Lung cancer is typically classified into small-cell carcinoma and non-small-cell carcinoma. Non-small-cell carcinoma accounts for approximately 85% of all lung cancers. Low-dose chest computed tomography (CT) can quickly and non-invasively diagnose lung cancer. In the era of deep learning, an artificial intelligence (AI) computer-aided diagnosis system can be developed for the automatic recognition of CT images of patients, creating a new form of intelligent medical service. For many years, lung cancer has been the leading cause of cancer-related deaths in Taiwan, with smoking and air pollution increasing the likelihood of developing the disease. The incidence of lung adenocarcinoma in never-smoking women has also increased significantly in recent years, resulting in an important public health problem. Early detection of lung cancer and prompt treatment can help reduce the mortality rate of patients with lung cancer. In this study, an improved 3D interpretable hierarchical semantic convolutional neural network named HSNet was developed and validated for the automatic diagnosis of lung cancer based on a collection of lung nodule images. The interpretable AI model proposed in this study, with different training strategies and adjustment of model parameters, such as cyclic learning rate and random weight averaging, demonstrated better diagnostic performance than the previous literature, with results of a four-fold cross-validation procedure showing calcification: 0.9873 ± 0.006, margin: 0.9207 ± 0.009, subtlety: 0.9026 ± 0.014, texture: 0.9685 ± 0.006, sphericity: 0.8652 ± 0.021, and malignancy: 0.9685 ± 0.006. [ABSTRACT FROM AUTHOR]

Simple Summary: Our study provides an overview of the current state of artificial intelligence applications in urooncology and explores potential future advancements in this field. With remarkable progress already achieved, artificial intelligence has revolutionized urooncology by facilitating image analysis, grading, biomarker research, and treatment planning. We also discuss types of artificial intelligence and their possible applications in the management of cancers such as prostate, kidney, bladder, and testicular. As artificial intelligence technology continues to evolve, it holds immense promise for further advancing urooncology and enhancing the care of patients with cancer. Introduction: Artificial intelligence is transforming healthcare by driving innovation, automation, and optimization across various fields of medicine. The aim of this study was to determine whether artificial intelligence (AI) techniques can be used in the diagnosis, treatment planning, and monitoring of urological cancers. Methodology: We conducted a thorough search for original and review articles published until 31 May 2022 in the PUBMED/Scopus database. Our search included several terms related to AI and urooncology. Articles were selected with the consensus of all authors. Results: Several types of AI can be used in the medical field. The most common forms of AI are machine learning (ML), deep learning (DL), neural networks (NNs), natural language processing (NLP) systems, and computer vision. AI can improve various domains related to the management of urologic cancers, such as imaging, grading, and nodal staging. AI can also help identify appropriate diagnoses, treatment options, and even biomarkers. In the majority of these instances, AI is as accurate as or sometimes even superior to medical doctors. Conclusions: AI techniques have the potential to revolutionize the diagnosis, treatment, and monitoring of urologic cancers. The use of AI in urooncology care is expected to increase in the future, leading to improved patient outcomes and better overall management of these tumors. [ABSTRACT FROM AUTHOR]

Simple Summary: In this research, we addressed the challenging task of brain tumor detection in MRI scans using a large collection of brain tumor images. We demonstrated that fine tuning a state-of-the-art YOLOv7 model through transfer learning significantly improved its performance in detecting gliomas, meningioma, and pituitary brain tumors. Our proposed deep learning model showed promising results, accurately identifying the presence and precise location of brain tumors in MRI images. The proposed approach achieved better accuracy compared to standard techniques, with a remarkable 99.5% accuracy in our analysis. However, we acknowledge that additional investigation and testing are essential to ensure the effectiveness of our method for detecting small tumors. The complexity of small tumor identification warrants ongoing research in brain tumor identification and continuous refinement of our detection systems. By pursuing this avenue, we aim to enhance the diagnostic capabilities for patients and medical practitioners in the challenging battle against brain cancers. The rapid development of abnormal brain cells that characterizes a brain tumor is a major health risk for adults since it can cause severe impairment of organ function and even death. These tumors come in a wide variety of sizes, textures, and locations. When trying to locate cancerous tumors, magnetic resonance imaging (MRI) is a crucial tool. However, detecting brain tumors manually is a difficult and time-consuming activity that might lead to inaccuracies. In order to solve this, we provide a refined You Only Look Once version 7 (YOLOv7) model for the accurate detection of meningioma, glioma, and pituitary gland tumors within an improved detection of brain tumors system. The visual representation of the MRI scans is enhanced by the use of image enhancement methods that apply different filters to the original pictures. To further improve the training of our proposed model, we apply data augmentation techniques to the openly accessible brain tumor dataset. The curated data include a wide variety of cases, such as 2548 images of gliomas, 2658 images of pituitary, 2582 images of meningioma, and 2500 images of non-tumors. We included the Convolutional Block Attention Module (CBAM) attention mechanism into YOLOv7 to further enhance its feature extraction capabilities, allowing for better emphasis on salient regions linked with brain malignancies. To further improve the model's sensitivity, we have added a Spatial Pyramid Pooling Fast+ (SPPF+) layer to the network's core infrastructure. YOLOv7 now includes decoupled heads, which allow it to efficiently glean useful insights from a wide variety of data. In addition, a Bi-directional Feature Pyramid Network (BiFPN) is used to speed up multi-scale feature fusion and to better collect features associated with tumors. The outcomes verify the efficiency of our suggested method, which achieves a higher overall accuracy in tumor detection than previous state-of-the-art models. As a result, this framework has a lot of potential as a helpful decision-making tool for experts in the field of diagnosing brain tumors. [ABSTRACT FROM AUTHOR]

Simple Summary: Ovarian cancer remains the leading cause of mortality from gynecologic cancer. In this study, we present a deep-learning artificial intelligence framework that uses pre-treatment histopathology images of high-grade ovarian cancers to predict the cancer's sensitivity or resistance to subsequent platinum-based chemotherapy. Analyses of this type could provide fast, inexpensive prediction of response to therapy at the time of initial pathological diagnosis. Background: Ovarian cancer remains the leading gynecological cause of cancer mortality. Predicting the sensitivity of ovarian cancer to chemotherapy at the time of pathological diagnosis is a goal of precision medicine research that we have addressed in this study using a novel deep-learning neural network framework to analyze the histopathological images. Methods: We have developed a method based on the Inception V3 deep learning algorithm that complements other methods for predicting response to standard platinum-based therapy of the disease. For the study, we used histopathological H&E images (pre-treatment) of high-grade serous carcinoma from The Cancer Genome Atlas (TCGA) Genomic Data Commons portal to train the Inception V3 convolutional neural network system to predict whether cancers had independently been labeled as sensitive or resistant to subsequent platinum-based chemotherapy. The trained model was then tested using data from patients left out of the training process. We used receiver operating characteristic (ROC) and confusion matrix analyses to evaluate model performance and Kaplan–Meier survival analysis to correlate the predicted probability of resistance with patient outcome. Finally, occlusion sensitivity analysis was piloted as a start toward correlating histopathological features with a response. Results: The study dataset consisted of 248 patients with stage 2 to 4 serous ovarian cancer. For a held-out test set of forty patients, the trained deep learning network model distinguished sensitive from resistant cancers with an area under the curve (AUC) of 0.846 ± 0.009 (SE). The probability of resistance calculated from the deep-learning network was also significantly correlated with patient survival and progression-free survival. In confusion matrix analysis, the network classifier achieved an overall predictive accuracy of 85% with a sensitivity of 73% and specificity of 90% for this cohort based on the Youden-J cut-off. Stage, grade, and patient age were not statistically significant for this cohort size. Occlusion sensitivity analysis suggested histopathological features learned by the network that may be associated with sensitivity or resistance to the chemotherapy, but multiple marker studies will be necessary to follow up on those preliminary results. Conclusions: This type of analysis has the potential, if further developed, to improve the prediction of response to therapy of high-grade serous ovarian cancer and perhaps be useful as a factor in deciding between platinum-based and other therapies. More broadly, it may increase our understanding of the histopathological variables that predict response and may be adaptable to other cancer types and imaging modalities. [ABSTRACT FROM AUTHOR]

Simple Summary: Glioblastoma (GB) is a malignant brain tumour with no cure, even after the best treatment. The evaluation of a therapy response is usually based on magnetic resonance imaging (MRI), but it lacks precision in early stages, and doctors must wait several weeks until they are confident information is produced, facing an uncertain time window. Magnetic resonance spectroscopy (MRS/MRSI) can provide additional information about tumours and their environment but is not widely used in clinical settings since the spectroscopy format is not standardised as MRI is, and doctors are not familiarised with outputs/interpretation. This study aims to improve the assessment of the treatment response in GB using MRSI data and machine learning, including state-of-the-art one-dimensional convolutional neural networks. Preclinical (murine) GB data were used for developing models that successfully identified tumour regions regarding their response to treatment (or the lack thereof). These models were accurate and outperformed previous methods, potentially providing new opportunities for GB patient management. Background: Glioblastoma (GB) is a malignant brain tumour that is challenging to treat, often relapsing even after aggressive therapy. Evaluating therapy response relies on magnetic resonance imaging (MRI) following the Response Assessment in Neuro-Oncology (RANO) criteria. However, early assessment is hindered by phenomena such as pseudoprogression and pseudoresponse. Magnetic resonance spectroscopy (MRS/MRSI) provides metabolomics information but is underutilised due to a lack of familiarity and standardisation. Methods: This study explores the potential of spectroscopic imaging (MRSI) in combination with several machine learning approaches, including one-dimensional convolutional neural networks (1D-CNNs), to improve therapy response assessment. Preclinical GB (GL261-bearing mice) were studied for method optimisation and validation. Results: The proposed 1D-CNN models successfully identify different regions of tumours sampled by MRSI, i.e., normal brain (N), control/unresponsive tumour (T), and tumour responding to treatment (R). Class activation maps using Grad-CAM enabled the study of the key areas relevant to the models, providing model explainability. The generated colour-coded maps showing the N, T and R regions were highly accurate (according to Dice scores) when compared against ground truth and outperformed our previous method. Conclusions: The proposed methodology may provide new and better opportunities for therapy response assessment, potentially providing earlier hints of tumour relapsing stages. [ABSTRACT FROM AUTHOR]

Simple Summary: Cancer results from aberrant cellular signaling caused by somatic genomic alterations (SGAs). However, inferring how SGAs cause aberrations in cellular signaling and lead to cancer remains challenging. We designed an interpretable deep learning model to encode the impact of SGAs on cellular signaling systems (represented by hidden nodes in the model) and eventually on tumor gene expression. The transparent deep learning architecture enabled the model to discover drivers affecting common signaling pathways and partially resolve the causal structure of signaling proteins. This is an early attempt to use transparent deep learning model, in contrast to conventional "black box" approach, to learn interpretable insights into cancer cell signaling systems. A better representation of signaling system of a cancer cell sheds light on the disease mechanisms of the cancer and can guide precision medicine. Cancer is a disease of aberrant cellular signaling resulting from somatic genomic alterations (SGAs). Heterogeneous SGA events in tumors lead to tumor-specific signaling system aberrations. We interpret the cancer signaling system as a causal graphical model, where SGAs affect signaling proteins, propagate their effects through signal transduction, and ultimately change gene expression. To represent such a system, we developed a deep learning model called redundant-input neural network (RINN) with a transparent redundant-input architecture. Our findings demonstrate that by utilizing SGAs as inputs, the RINN can encode their impact on the signaling system and predict gene expression accurately when measured as the area under ROC curves. Moreover, the RINN can discover the shared functional impact (similar embeddings) of SGAs that perturb a common signaling pathway (e.g., PI3K, Nrf2, and TGF). Furthermore, the RINN exhibits the ability to discover known relationships in cellular signaling systems. [ABSTRACT FROM AUTHOR]