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]

Orchard monitoring is a vital direction of scientific research and practical application for increasing fruit production in ecological conditions. Recently, due to the development of technology and the decrease in equipment cost, the use of unmanned aerial vehicles and artificial intelligence algorithms for image acquisition and processing has achieved tremendous progress in orchards monitoring. This paper highlights the new research trends in orchard monitoring, emphasizing neural networks, unmanned aerial vehicles (UAVs), and various concrete applications. For this purpose, papers on complex topics obtained by combining keywords from the field addressed were selected and analyzed. In particular, the review considered papers on the interval 2017-2022 on the use of neural networks (as an important exponent of artificial intelligence in image processing and understanding) and UAVs in orchard monitoring and production evaluation applications. Due to their complexity, the characteristics of UAV trajectories and flights in the orchard area were highlighted. The structure and implementations of the latest neural network systems used in such applications, the databases, the software, and the obtained performances are systematically analyzed. To recommend some suggestions for researchers and end users, the use of the new concepts and their implementations were surveyed in concrete applications, such as a) identification and segmentation of orchards, trees, and crowns; b) detection of tree diseases, harmful insects, and pests; c) evaluation of fruit production, and d) evaluation of development conditions. To show the necessity of this review, in the end, a comparison is made with review articles with a related theme. [ABSTRACT FROM AUTHOR]

Low-dose computed tomography (LDCT) is an effective way to reduce radiation exposure for patients. However, it will increase the noise of reconstructed CT images and affect the precision of clinical diagnosis. The majority of the current deep learning-based denoising methods are built on convolutional neural networks (CNNs), which concentrate on local information and have little capacity for multiple structures modeling. Transformer structures are capable of computing each pixel's response on a global scale, but their extensive computation requirements prevent them from being widely used in medical image processing. To reduce the impact of LDCT scans on patients, this paper aims to develop an image post-processing method by combining CNN and Transformer structures. This method can obtain a high-quality images from LDCT. A hybrid CNN-Transformer (HCformer) codec network model is proposed for LDCT image denoising. A neighborhood feature enhancement (NEF) module is designed to introduce the local information into the Transformer's operation, and the representation of adjacent pixel information in the LDCT image denoising task is increased. The shifting window method is utilized to lower the computational complexity of the network model and overcome the problems that come with computing the MSA (Multi-head self-attention) process in a fixed window. Meanwhile, W/SW-MSA (Windows/Shifted window Multi-head self-attention) is alternately used in two layers of the Transformer to gain the information interaction between various Transformer layers. This approach can successfully decrease the Transformer's overall computational cost. The AAPM 2016 LDCT grand challenge dataset is employed for ablation and comparison experiments to demonstrate the viability of the proposed LDCT denoising method. Per the experimental findings, HCformer can increase the image quality metrics SSIM, HuRMSE and FSIM from 0.8017, 34.1898, and 0.6885 to 0.8507, 17.7213, and 0.7247, respectively. Additionally, the proposed HCformer algorithm will preserves image details while it reduces noise. In this paper, an HCformer structure is proposed based on deep learning and evaluated by using the AAPM LDCT dataset. Both the qualitative and quantitative comparison results confirm that the proposed HCformer outperforms other methods. The contribution of each component of the HCformer is also confirmed by the ablation experiments. HCformer can combine the advantages of CNN and Transformer, and it has great potential for LDCT image denoising and other tasks. [ABSTRACT FROM AUTHOR]

Different from traditional images, light field images record not only spatial information but also angle information. Due to the large volume of light field data brings great difficulties to storage and compression, light field compression technology has attracted much attention. The epipolar plane image (EPI) contains a lot of low rank information, which is suitable for recovering the complete EPI from a part of EPI. In this paper, a light field image coding framework based on EPI restoration neural network has been proposed. Compared with previous algorithms, the proposed algorithm further takes advantage of the inherent similarity in light field images, and the proposed framework has higher performance and robustness. Experimental results show that the proposed method has superior performance compared to the state-of-the-art both in quantitatively and qualitatively. [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]

Chronic rhinosinusitis (CRS) is a global disease characterized by poor treatment outcomes and high recurrence rates, significantly affecting patients' quality of life. Due to its complex pathophysiology and diverse clinical presentations, CRS is categorized into various subtypes to facilitate more precise diagnosis, treatment, and prognosis prediction. Among these, CRS with nasal polyps (CRSwNP) is further divided into eosinophilic CRSwNP (eCRSwNP) and noneosinophilic CRSwNP (non‐eCRSwNP). However, there is a lack of precise predictive diagnostic and treatment methods, making research into accurate diagnostic techniques for CRSwNP endotypes crucial for achieving precision medicine in CRSwNP. This paper proposes a method using multiangle sinus computed tomography (CT) images combined with artificial intelligence (AI) to predict CRSwNP endotypes, distinguishing between patients with eCRSwNP and non‐eCRSwNP. The considered dataset comprises 22,265 CT images from 192 CRSwNP patients, including 13,203 images from non‐eCRSwNP patients and 9,062 images from eCRSwNP patients. Test results from the network model demonstrate that multiangle images provide more useful information for the network, achieving an accuracy of 98.43%, precision of 98.1%, recall of 98.1%, specificity of 98.7%, and an AUC value of 0.984. Compared to the limited learning capacity of single‐channel neural networks, our proposed multichannel feature adaptive fusion model captures multiscale spatial features, enhancing the model's focus on crucial sinus information within the CT images to maximize detection accuracy. This deep learning‐based diagnostic model for CRSwNP endotypes offers excellent classification performance, providing a noninvasive method for accurately predicting CRSwNP endotypes before treatment and paving the way for precision medicine in the new era of CRSwNP. [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]

Rock strength parameters such as uniaxial compressive strength and modulus of elasticity are crucial parameters in designing rock engineering structures. Owing to the importance of the aforementioned parameters, in this paper, image processing technique is coupled with artificial neural network (ANN) method for assessing the uniaxial compressive strength and modulus of elasticity of sandstones. For this reason, 102 core sandstone samples were prepared. Subsequently petrographic analyses and imaging operation for 102 images were performed. Principal component analysis was then conducted for feature reduction purposes. At last, an ANN model, which received its input data from image processing technique, was constructed for assessing the UCS and E of sandstone samples. Overall, the best performance of the network was obtained when 10 hidden nodes were used. The correlation coefficient (R) values of 0.9722 and 0.97062 for UCS and E, respectively, suggest the feasibility of the proposed model. [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]

Generative artificial intelligence, especially with regard to the generative adversarial network (GAN), is an important research area in radiology as evidenced by a number of literature reviews on the role of GAN in radiology published in the last few years. However, no review article about GAN in pediatric radiology has been published yet. The purpose of this paper is to systematically review applications of GAN in pediatric radiology, their performances, and methods for their performance evaluation. Electronic databases were used for a literature search on 6 April 2023. Thirty-seven papers met the selection criteria and were included. This review reveals that the GAN can be applied to magnetic resonance imaging, X-ray, computed tomography, ultrasound and positron emission tomography for image translation, segmentation, reconstruction, quality assessment, synthesis and data augmentation, and disease diagnosis. About 80% of the included studies compared their GAN model performances with those of other approaches and indicated that their GAN models outperformed the others by 0.1–158.6%. However, these study findings should be used with caution because of a number of methodological weaknesses. For future GAN studies, more robust methods will be essential for addressing these issues. Otherwise, this would affect the clinical adoption of the GAN-based applications in pediatric radiology and the potential advantages of GAN could not be realized widely. [ABSTRACT FROM AUTHOR]

Retinal vessel segmentation has high value for the research on the diagnosis of diabetic retinopathy, hypertension, and cardiovascular and cerebrovascular diseases. Most methods based on deep convolutional neural networks (DCNN) do not have large receptive fields or rich spatial information and cannot capture global context information of the larger areas. Therefore, it is difficult to identify the lesion area, and the segmentation efficiency is poor. This paper presents a butterfly fully convolutional neural network (BFCN). First, in view of the low contrast between blood vessels and the background in retinal blood vessel images, this paper uses automatic color enhancement (ACE) technology to increase the contrast between blood vessels and the background. Second, using the multiscale information extraction (MSIE) module in the backbone network can capture the global contextual information in a larger area to reduce the loss of feature information. At the same time, using the transfer layer (T_Layer) can not only alleviate gradient vanishing problem and repair the information loss in the downsampling process but also obtain rich spatial information. Finally, for the first time in the paper, the segmentation image is postprocessed, and the Laplacian sharpening method is used to improve the accuracy of vessel segmentation. The method mentioned in this paper has been verified by the DRIVE, STARE, and CHASE datasets, with the accuracy of 0.9627, 0.9735, and 0.9688, respectively. [ABSTRACT FROM AUTHOR]

This paper presents an in-depth study and analysis of students' role perceptions and their tendencies in classroom education using a visual inspection approach. A multi example learning student engagement assessment method based on a one-dimensional convolutional neural network is proposed. Based on the conceptual composition of student engagement, head posture, eye gaze, and eye-opening and closing states and the most used facial movement units are used as visual features. For feature extraction, the proposed view of relative change features, based on the video features extracted from the Open Face toolset, the standard deviation of the distance between adjacent multiple frames relative to the center point of the three visual features is used as the relative change features of the video. This results in the phenomenon that students are highly motivated in the early stage and significantly increase the rate of absenteeism in the later stage. With the development of information technology injecting new vitality into educational innovation, many researchers have introduced computer vision and image processing technology into students' online learning activities, and understand students' current learning situation by analyzing students' learning status. There are relatively few studies in this area in classroom teaching. Considering the low relative position correlation of the features in the examples, the examples are analyzed using a one-dimensional convolutional neural network to obtain the example-level student engagement, and a multi-example pooling layer is used to infer the student engagement in the video from the example-level student engagement. Finally, the experimental method is used to apply the student classroom attention evaluation detection system to actual classroom teaching activities, and the effectiveness and accuracy of the design of the student classroom attention evaluation detection system are investigated in depth through specific applications and example analysis, and the accuracy of the method of this paper is further verified by communicating feedback with teachers and students in the form of interviews. [ABSTRACT FROM AUTHOR]

The light field is an important way to record the spatial information of the target scene. The purpose of this paper is to obtain depth information through the processing of light field information and provide a basis for intelligent medical treatment. In this paper, we first design an attention module to extract the features of light field images and connect all the features as a feature map to generate an attention image. Then, the attention map is integrated with the convolution layer in the neural network in the form of weights to enhance the weight of the subaperture viewpoint, which is more meaningful for depth estimation. Finally, the obtained initial depth results were optimized. The experimental results show that the MSE, PSNR, and SSIM of the depth map obtained by this method are increased by about 13%, 10 dB, and 4%, respectively, in some scenarios with good performance. [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]

Diagnosis of brain tumor gliomas is a challenging task in medical image analysis due to its complexity, the less regularity of tumor structures, and the diversity of tissue textures and shapes. Semantic segmentation approaches using deep learning have consistently outperformed the previous methods in this challenging task. However, deep learning is insufficient to provide the required local features related to tissue texture changes due to tumor growth. This paper designs a hybrid method arising from this need, which incorporates machine-learned and hand-crafted features. A semantic segmentation network (SegNet) is used to generate the machine-learned features, while the grey-level co-occurrence matrix (GLCM)-based texture features construct the hand-crafted features. In addition, the proposed approach only takes the region of interest (ROI), which represents the extension of the complete tumor structure, as input, and suppresses the intensity of other irrelevant area. A decision tree (DT) is used to classify the pixels of ROI MRI images into different parts of tumors, i.e. edema, necrosis and enhanced tumor. The method was evaluated on BRATS 2017 dataset. The results demonstrate that the proposed model provides promising segmentation in brain tumor structure. The F-measures for automatic brain tumor segmentation against ground truth are 0.98, 0.75 and 0.69 for whole tumor, core and enhanced tumor, respectively. [ABSTRACT FROM AUTHOR]

Background/Objectives: Advancement in medical equipment has enabled accurate and quick diagnosis in medical field. However, an increase in the number of medical staff is slower than the rate of medical equipment development. It has resulted in increased risk of diagnostic misinterpretation. The purpose of this paper is to help diagnosis of medical staff through artificial neural network (ANN). Method/Statistical Analysis: We selected U-Net among artificial neural networks. U-Net is highly accurate in medical imaging. The dataset for learning the network was obtained from the Brain Tumor Segmentation Challenge (BraTS). This dataset contains four classes of brain tumor data and it is suitable for learning variety of brain tumors. We used F-Score to measure the accuracy of the learned network. Findings: In this paper, we compare the performance of the network by conducting two experiments. First, we checked the learning progress of the network. Second, we compared the results of learning with mixed and single datasets. In the first experiment, when allowing the network to learn for a total of 200 generations, it was confirmed that the results of 100 generations were the most accurate. In the second experiment, the network learned by three groups of datasets. The first group consisted of HGG data only, and the second group was composed of LGG data only, and the last group was made up of mixing HGG and LGG data. When comparing the results of the first group with the third group, the accuracy of HGG patient was 0.6696 and 0.6222, respectively. Subsequently, the results of the second and the third group were 0.6315 and 0.6228, respectively. Improvements/Applications: In this experiment, we compared the results obtained when the datasets were mixed and when they were used singly. The results show similar accuracy. However, when using a mixture of datasets, the accuracy is lower, which is enough to assist the diagnosis of the medical staff. It is expected that this will help the development of the medical image processing field by confirming the position and size of the brain tumor accurately regardless of the data of any grade for brain tumor. [ABSTRACT FROM AUTHOR]

Segmentation of tumor regions in H &E-stained slides is an important task for a pathologist while diagnosing different types of cancer, including oral squamous cell carcinoma (OSCC). Histological image segmentation is often constrained by the availability of labeled training data since labeling histological images is a highly skilled, complex, and time-consuming task. Thus, data augmentation strategies become essential to train convolutional neural networks models to overcome the overfitting problem when only a few training samples are available. This paper proposes a new data augmentation strategy, named Random Composition Augmentation (RCAug), to train fully convolutional networks (FCN) to segment OSCC tumor regions in H &E-stained histological images. Given the input image and their corresponding label, a pipeline with a random composition of geometric, distortion, color transfer, and generative image transformations is executed on the fly. Experimental evaluations were performed using an FCN-based method to segment OSCC regions through a set of different data augmentation transformations. By using RCAug, we improved the FCN-based segmentation method from 0.51 to 0.81 of intersection-over-union (IOU) in a whole slide image dataset and from 0.65 to 0.69 of IOU in a tissue microarray images dataset. [ABSTRACT FROM AUTHOR]

As a neurodevelopmental disorder, autism spectrum disorder (ASD) severely affects the living conditions of patients and their families. Early diagnosis of ASD can enable the disease to be effectively intervened in the early stage of development. In this paper, we present an ASD classification network defined as CNNG by combining of convolutional neural network (CNN) and gate recurrent unit (GRU). First, CNNG extracts the 3D spatial features of functional magnetic resonance imaging (fMRI) data by using the convolutional layer of the 3D CNN. Second, CNNG extracts the temporal features by using the GRU and finally classifies them by using the Sigmoid function. The performance of CNNG was validated on the international public data--autism brain imaging data exchange (ABIDE) dataset. According to the experiments, CNNG can be highly effective in extracting the spatio-temporal features of fMRI and achieving a classification accuracy of 72.46%. [ABSTRACT FROM AUTHOR]

Deep learning has become a research hotspot in multimedia, especially in the field of image processing. Pooling operation is an important operation in deep learning. Pooling operation can reduce the feature dimension, the number of parameters, the complexity of computation, and the complexity of time. With the development of deep learning models, pooling operation has made great progress. The main contributions of this paper on pooling operation are as follows: firstly, the steps of the pooling operation are summarized as the pooling domain, pooling kernel, step size, activation value, and response value. Secondly, the expression form of pooling operation is standardized. From the perspective of "invariable" to "variable," this paper analyzes the pooling domain and pooling kernel in the pooling operation. Pooling operation can be classified into four categories: invariable of pooling domain, variable of pooling domain, variable of pooling kernel, and the pooling of invariable "+" variable. Finally, the four types of pooling operation are summarized and discussed with their advantages and disadvantages. There is great significance to the research of pooling operations and the iterative updating of deep learning models. [ABSTRACT FROM AUTHOR]

Dense convolutional network (DenseNet) is a hot topic in deep learning research in recent years, which has good applications in medical image analysis. In this paper, DenseNet is summarized from the following aspects. First, the basic principle of DenseNet is introduced; second, the development of DenseNet is summarized and analyzed from five aspects: broaden DenseNet structure, lightweight DenseNet structure, dense unit, dense connection mode, and attention mechanism; finally, the application research of DenseNet in the field of medical image analysis is summarized from three aspects: pattern recognition, image segmentation, and object detection. The network structures of DenseNet are systematically summarized in this paper, which has certain positive significance for the research and development of DenseNet. [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]

Accurate prostate segmentation in ultrasound images is crucial for the clinical diagnosis of prostate cancer and for performing image-guided prostate surgery. However, it is challenging to accurately segment the prostate in ultrasound images due to their low signal-to-noise ratio, the low contrast between the prostate and neighboring tissues, and the diffuse or invisible boundaries of the prostate. In this paper, we develop a novel hybrid method for segmentation of the prostate in ultrasound images that generates accurate contours of the prostate from a range of datasets. Our method involves three key steps: (1) application of a principal curve-based method to obtain a data sequence comprising data coordinates and their corresponding projection index; (2) use of the projection index as training input for a fractional-order-based neural network that increases the accuracy of results; and (3) generation of a smooth mathematical map (expressed via the parameters of the neural network) that affords a smooth prostate boundary, which represents the output of the neural network (i.e., optimized vertices) and matches the ground truth contour. Experimental evaluation of our method and several other state-of-the-art segmentation methods on datasets of prostate ultrasound images generated at multiple institutions demonstrated that our method exhibited the best capability. Furthermore, our method is robust as it can be applied to segment prostate ultrasound images obtained at multiple institutions based on various evaluation metrics. [ABSTRACT FROM AUTHOR]

Developing a convolutional neural network (CNN) for medical image segmentation is a complex task, especially when dealing with the limited number of available labelled medical images and computational resources. This task can be even more difficult if the aim is to develop a deep network and using a complicated structure like attention blocks. Because of various types of noises, artefacts and diversity in medical images, using complicated network structures like attention mechanism to improve the accuracy of segmentation is inevitable. Therefore, it is necessary to develop techniques to address the above difficulties. Neuroevolution is the combination of evolutionary computation and neural networks to establish a network automatically. However, Neuroevolution is computationally expensive, specifically to create 3D networks. In this paper, an automatic, efficient, accurate, and robust technique is introduced to develop deep attention convolutional neural networks utilising Neuroevolution for both 2D and 3D medical image segmentation. The proposed evolutionary technique can find a very good combination of six attention modules to recover spatial information from downsampling section and transfer them to the upsampling section of a U-Net-based network—six different CT and MRI datasets are employed to evaluate the proposed model for both 2D and 3D image segmentation. The obtained results are compared to state-of-the-art manual and automatic models, while our proposed model outperformed all of them. [ABSTRACT FROM AUTHOR]

As one of the more difficult problems in the field of computer vision, utilizing object image detection technology in a complex environment includes other key technologies, such as pattern recognition, artificial intelligence, and digital image processing. However, because an environment can be complex, changeable, highly different, and easily confused with the target, the target is easily affected by other factors, such as insufficient light, partial occlusion, background interference, etc., making the detection of multiple targets extremely difficult and the robustness of the algorithm low. How to make full use of the rich spatial information and deep texture information in an image to accurately identify the target type and location is an urgent problem to be solved. The emergence of deep neural networks provides an effective way for image feature extraction and full utilization. By aiming at the above problems, this paper proposes an object detection model based on the mixed attention mechanism optimization of YOLOv5 (MAO-YOLOv5). The proposed method fuses the local features and global features in an image so as to better enrich the expression ability of the feature map and more effectively detect objects with large differences in size within the image. Then, the attention mechanism is added to the feature map to weigh each channel, enhance the key features, remove the redundant features, and improve the recognition ability of the feature network towards the target object and background. The results show that the proposed network model has higher precision and a faster running speed and can perform better in object-detection tasks. [ABSTRACT FROM AUTHOR]

Hair and ruler mark structures in dermoscopic images are an obstacle preventing accurate image segmentation and detection of critical network features. Recognition and removal of hairs from images can be challenging, especially for hairs that are thin, overlapping, faded, or of similar color as skin or overlaid on a textured lesion. This paper proposes a novel deep learning (DL) technique to detect hair and ruler marks in skin lesion images. Our proposed ChimeraNet is an encoder-decoder architecture that employs pretrained EfficientNet in the encoder and squeeze-and-excitation residual (SERes) structures in the decoder. We applied this approach at multiple image sizes and evaluated it using the publicly available HAM10000 (ISIC2018 Task 3) skin lesion dataset. Our test results show that the largest image size (448 × 448) gave the highest accuracy of 98.23 and Jaccard index of 0.65 on the HAM10000 (ISIC 2018 Task 3) skin lesion dataset, exhibiting better performance than for two well-known deep learning approaches, U-Net and ResUNet-a. We found the Dice loss function to give the best results for all measures. Further evaluated on 25 additional test images, the technique yields state-of-the-art accuracy compared to 8 previously reported classical techniques. We conclude that the proposed ChimeraNet architecture may enable improved detection of fine image structures. Further application of DL techniques to detect dermoscopy structures is warranted. [ABSTRACT FROM AUTHOR]

Retinal fundus images are non-invasively acquired and faced with low contrast, noise, and uneven illumination. The low-contrast problem makes objects in the retinal fundus image indistinguishable and the segmentation of blood vessels very challenging. Retinal blood vessels are significant because of their diagnostic importance in ophthalmologic diseases. This paper proposes improved retinal fundus images for optimal segmentation of blood vessels using convolutional neural networks (CNNs). This study explores some robust contrast enhancement tools on the RGB and the green channel of the retinal fundus images. The improved images undergo quality evaluation using mean square error (MSE), peak signal to noise ratio (PSNR), Similar Structure Index Matrix (SSIM), histogram, correlation, and intersection distance measures for histogram comparison before segmentation in the CNN-based model. The simulation results analysis reveals that the improved RGB quality outperforms the improved green channel. This revelation implies that the choice of RGB to the green channel for contrast enhancement is adequate and effectively improves the quality of the fundus images. This improved contrast will, in turn, boost the predictive accuracy of the CNN-based model during the segmentation process. The evaluation of the proposed method on the DRIVE dataset achieves an accuracy of 94.47, sensitivity of 70.92, specificity of 98.20, and AUC (ROC) of 97.56. [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]

The identification and characterization of lung diseases is one of the most interesting research topics in recent years. They require accurate and rapid diagnosis. Although lung imaging techniques have many advantages for disease diagnosis, the interpretation of medial lung images has always been a major problem for physicians and radiologists due to diagnostic errors. This has encouraged the use of modern artificial intelligence techniques such as deep learning. In this paper, a deep learning architecture based on EfficientNetB7, known as the most advanced architecture among convolutional networks, has been constructed for classification of medical X-ray and CT images of lungs into three classes namely: common pneumonia, coronavirus pneumonia and normal cases. In terms of accuracy, the proposed model is compared with recent pneumonia detection techniques. The results provided robust and consistent features to this system for pneumonia detection with predictive accuracy according to the three classes mentioned above for both imaging modalities: radiography at 99.81% and CT at 99.88%. This work implements an accurate computer-aided system for the analysis of radiographic and CT medical images. The results of the classification are promising and will certainly improve the diagnosis and decision making of lung diseases that keep appearing over time. [ABSTRACT FROM AUTHOR]

Under-sampling in diffusion-weighted imaging (DWI) decreases the scan time that helps to reduce off-resonance effects, geometric distortions, and susceptibility artifacts; however, it leads to under-sampling artifacts. In this paper, diffusion-weighted MR image (DWI-MR) reconstruction using deep learning (DWI U-Net) is proposed to recover artifact-free DW images from variable density highly under-sampled k-space data. Additionally, different optimizers, i.e., RMSProp, Adam, Adagrad, and Adadelta, have been investigated to choose the best optimizers for DWI U-Net. The reconstruction results are compared with the conventional Compressed Sensing (CS) reconstruction. The quality of the recovered images is assessed using mean artifact power (AP), mean root mean square error (RMSE), mean structural similarity index measure (SSIM), and mean apparent diffusion coefficient (ADC). The proposed method provides up to 61.1%, 60.0%, 30.4%, and 28.7% improvements in the mean AP value of the reconstructed images in our experiments with different optimizers, i.e., RMSProp, Adam, Adagrad, and Adadelta, respectively, as compared to the conventional CS at an acceleration factor of 6 (i.e., AF = 6). The results of DWI U-Net with the RMSProp, Adam, Adagrad, and Adadelta optimizers show 13.6%, 10.0%, 8.7%, and 8.74% improvements, respectively, in terms of mean SSIM with respect to the conventional CS at AF = 6. Also, the proposed technique shows 51.4%, 29.5%, 24.04%, and 18.0% improvements in terms of mean RMSE using the RMSProp, Adam, Adagrad, and Adadelta optimizers, respectively, with reference to the conventional CS at AF = 6. The results confirm that DWI U-Net performs better than the conventional CS reconstruction. Also, when comparing the different optimizers in DWI U-Net, RMSProp provides better results than the other optimizers. [ABSTRACT FROM AUTHOR]

Camera shake or target movement often leads to undesired blur effects in videos captured by a hand-held camera. Despite significant efforts having been devoted to video-deblur research, two major challenges remain: 1) how to model the spatio-temporal characteristics across both the spatial domain (i.e., image plane) and the temporal domain (i.e., neighboring frames) and 2) how to restore sharp image details with respect to the conventionally adopted metric of pixel-wise errors. In this paper, to address the first challenge, we propose a deblurring network (DBLRNet) for spatial-temporal learning by applying a 3D convolution to both the spatial and temporal domains. Our DBLRNet is able to capture jointly spatial and temporal information encoded in neighboring frames, which directly contributes to the improved video deblur performance. To tackle the second challenge, we leverage the developed DBLRNet as a generator in the generative adversarial network (GAN) architecture and employ a content loss in addition to an adversarial loss for efficient adversarial training. The developed network, which we name as deblurring GAN, is tested on two standard benchmarks and achieves the state-of-the-art performance. [ABSTRACT FROM AUTHOR]

Medical image semantic segmentation is essential in computer-aided diagnosis systems. It can separate tissues and lesions in the image and provide valuable information to radiologists and doctors. The breast ultrasound (BUS) images have advantages: no radiation, low cost, portable, etc. However, there are two unfavorable characteristics: (1) the dataset size is often small due to the difficulty in obtaining the ground truths, and (2) BUS images are usually in poor quality. Trustworthy BUS image segmentation is urgent in breast cancer computer-aided diagnosis systems, especially for fully understanding the BUS images and segmenting the breast anatomy, which supports breast cancer risk assessment. The main challenge for this task is uncertainty in both pixels and channels of the BUS images. In this paper, we propose a Spatial and Channel-wise Fuzzy Uncertainty Reduction Network (SCFURNet) for BUS image semantic segmentation. The proposed architecture can reduce the uncertainty in the original segmentation frameworks. We apply the proposed method to four datasets: (1) a five-category BUS image dataset with 325 images, and (2) three BUS image datasets with only tumor category (1830 images in total). The proposed approach compares state-of-the-art methods such as U-Net with VGG-16, ResNet-50/ResNet-101, Deeplab, FCN-8s, PSPNet, U-Net with information extension, attention U-Net, and U-Net with the self-attention mechanism. It achieves 2.03%, 1.84%, and 2.88% improvements in the Jaccard index on three public BUS datasets, and 6.72% improvement in the tumor category and 4.32% improvement in the overall performance on the five-category dataset compared with that of the original U-shape network with ResNet-101 since it can handle the uncertainty effectively and efficiently. [ABSTRACT FROM AUTHOR]

Statistics show that an estimated 64 million people worldwide suffer from glaucoma. To aid in the detection of this disease, this paper presents a new public dataset containing eye fundus images that was developed for glaucoma pattern-recognition studies using deep learning (DL). The dataset, denoted Brazil Glaucoma, comprises 2000 images obtained from 1000 volunteers categorized into two groups: those with glaucoma (50%) and those without glaucoma (50%). All images were captured with a smartphone attached to a Welch Allyn panoptic direct ophthalmoscope. Further, a DL approach for the automatic detection of glaucoma was developed using the new dataset as input to a convolutional neural network ensemble model. The accuracy between positive and negative glaucoma detection, sensitivity, and specificity were calculated using five-fold cross-validation to train and refine the classification model. The results showed that the proposed method can identify glaucoma from eye fundus images with an accuracy of 90.0%. Thus, the combination of fundus images obtained using a smartphone attached to a portable panoptic ophthalmoscope and artificial intelligence algorithms yielded satisfactory results in the overall accuracy of glaucoma detection tests. Consequently, the proposed approach can contribute to the development of technologies aimed at massive population screening of the disease. [ABSTRACT FROM AUTHOR]

This paper proposes a new network framework, which leverages EfficientNetB4, attention gate, and residual learning techniques to achieve automatic and accurate liver segmentation. First, we use EfficientNetB4 as the encoder to extract more feature information during the encoding stage. Then, an attention gate is introduced in the skip connection to eliminate irrelevant regions and highlight features of a specific segmentation task. Finally, to alleviate the problem of gradient vanishment, we replace the traditional convolution of the decoder with a residual block to improve the segmentation accuracy. We verified the proposed method on the LiTS17 and SLiver07 datasets and compared it with classical networks such as FCN, U-Net, attention U-Net, and attention Res-U-Net. In the Sliver07 evaluation, the proposed method achieved the best segmentation performance on all five standard metrics. Meanwhile, in the LiTS17 assessment, the best performance is obtained except for a slight inferior on RVD. The proposed method's qualitative and quantitative results demonstrated its applicability in liver segmentation and proved its good prospect in computer-assisted liver segmentation. [ABSTRACT FROM AUTHOR]

Bone age assessment (BAA) based on X-ray imaging of the left hand and wrist can accurately reflect the degree of the body's physiological development and physical condition. However, the traditional manual evaluation method relies too much on inefficient specialist labor. In this paper, to propose automatic BAA, we introduce a hierarchical convolutional neural network to detect the regions of interest (ROI) and classify the bone grade. Firstly, we establish a dataset of children's BAA containing 2518 left hand X-rays. Then, we use the fine-grained classification to obtain the grade of the region of interest via object detection. Specifically, fine-grained classifiers are based on context-aware attention pooling (CAP). Finally, we perform the model assessment of bone age using the third version of the Tanner–Whitehouse (TW3) methodology. The end-to-end BAA system provides bone age values, the detection results of 13 ROIs, and the bone maturity of the ROIs, which are convenient for doctors to obtain information for operation. Experimental results on the public dataset and clinical dataset show that the performance of the proposed method is competitive. The accuracy of bone grading is 86.93%, and the mean absolute error (MAE) of bone age is 7.68 months on the clinical dataset. On public dataset, the MAE is 6.53 months. The proposed method achieves good performance in bone age assessment and is superior to existing fine-grained image classification methods. [ABSTRACT FROM AUTHOR]

This paper surveys recent advances in pulse-coupled neural networks (PCNNs) and their applications in image processing. The PCNN is a neurology-inspired neural network model that aims to imitate the information analysis process of the biological cortex. In recent years, many PCNN-derived models have been developed. Research aims with respect to these models can be divided into three categories: (1) to reduce the number of manual parameters, (2) to achieve better real cortex imitation performance, and (3) to combine them with other methodologies. We provide a comprehensive and schematic review of these novel PCNN-derived models. Moreover, the PCNN has been widely used in the image processing field due to its outstanding information extraction ability. We review the recent applications of PCNN-derived models in image processing, providing a general framework for the state of the art and a better understanding of PCNNs with applications in image processing. In conclusion, PCNN models are developing rapidly, and it is projected that more applications of these novel emerging models will be seen in future. [ABSTRACT FROM AUTHOR]

The novel coronavirus 2019 (COVID-19) spread rapidly around the world and its outbreak has become a pandemic. Due to an increase in afflicted cases, the quantity of COVID-19 tests kits available in hospitals has decreased. Therefore, an autonomous detection system is an essential tool for reducing infection risks and spreading of the virus. In the literature, various models based on machine learning (ML) and deep learning (DL) are introduced to detect many pneumonias using chest X-ray images. The cornerstone in this paper is the use of pretrained deep learning CNN architectures to construct an automated system for COVID-19 detection and diagnosis. In this work, we used the deep feature concatenation (DFC) mechanism to combine features extracted from input images using the two modern pre-trained CNN models, AlexNet and Xception. Hence, we propose COVID-AleXception: a neural network that is a concatenation of the AlexNet and Xception models for the overall improvement of the prediction capability of this pandemic. To evaluate the proposed model and build a dataset of large-scale X-ray images, there was a careful selection of multiple X-ray images from several sources. The COVID-AleXception model can achieve a classification accuracy of 98.68%, which shows the superiority of the proposed model over AlexNet and Xception that achieved a classification accuracy of 94.86% and 95.63%, respectively. The performance results of this proposed model demonstrate its pertinence to help radiologists diagnose COVID-19 more quickly. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy is a pathological change of the retina that occurs for long-term diabetes. The patients become symptomatic in advanced stages of diabetic retinopathy resulting in severe non-proliferative diabetic retinopathy or proliferative diabetic retinopathy stages. There is a need of an automated screening tool for the early detection and treatment of patients with diabetic retinopathy. This paper focuses on the segmentation of red lesions using nested U-Net Zhou et al. (Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Springer, 2018) followed by removal of false positives based on the sub-image classification method. Different sizes of sub-images were studied for the reduction in false positives in the sub-image classification method. The network could capture semantic features and fine details due to dense convolutional blocks connected via skip connections in between down sampling and up sampling paths. False-negative candidates were very few and the sub-image classification network effectively reduced the falsely detected candidates. The proposed framework achieves a sensitivity of 88.79 % , precision of 71.50 % , and F1-Score of 79.21 % for the DIARETDB1 data set Kalviainen and Uusutalo (Medical Image Understanding and Analysis, Citeseer, 2007). It outperforms the state-of-the-art networks such as U-Net Ronneberger et al. (International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, 2015) and attention U-Net Oktay et al. (Attention u-net: Learning where to look for the pancreas, 2018). [ABSTRACT FROM AUTHOR]

Denoising, skull stripping, segmentation, feature extraction, and classification are five important processes in this paper's development of a brain tumor classification model. The brain tumor image will be imposed first using the entropy-based trilateral filter to de-noising and this image is imposed to skull stripping by means of morphological partition and Otsu thresholding. Adaptive contrast limited fuzzy adaptive histogram equalization (CLFAHE) is also used in the segmentation process. The gray-level co-occurrence matrix (GLCM) characteristics are derived from the segmented image. The collected GLCM features are used in a hybrid classifier that combines the neural network (NN) and deep belief network (DBN) ideas. As an innovation, the hidden neurons of the two classifiers are modified ideally to improve the prediction model's accuracy. The hidden neurons are optimized using a unique hybrid optimization technique known as lion with dragonfly separation update (L-DSU), which integrates the approaches from both DA and LA. Finally, the suggested model's performance is compared to that of the standard models concerning certain performance measures. [ABSTRACT FROM AUTHOR]

Applying machine learning technology to automatic image analysis and auxiliary diagnosis of whole slide image (WSI) may help to improve the efficiency, objectivity, and consistency of pathological diagnosis. Due to its extremely high resolution, it is still a great challenge to directly process WSI through deep neural networks. In this paper, we propose a novel model for the task of classification of WSIs. The model is composed of two parts. The first part is a self-supervised encoding network with a UNet-like architecture. Each patch from a WSI is encoded as a compressed latent representation. These features are placed according to their corresponding patch's original location in WSI, forming a feature cube. The second part is a classification network fused by 4 famous network blocks with heterogeneous architectures, with feature cube as input. Our model effectively expresses the feature and preserves location information of each patch. The fused network integrates heterogeneous features generated by different networks which yields robust classification results. The model is evaluated on two public datasets with comparison to baseline models. The evaluation results show the effectiveness of the proposed model. [ABSTRACT FROM AUTHOR]

Throughout the area of image processing, the new generation of convolutional neural networks CNNs has produced remarkable performances. The paper reflects on a new approach to the production of utilizing deep convolutionary networks of a model of the identification of plants centered on the picture classification of the surface. Throughout reality, a modern model of teaching and technique allows it simple and fast to introduce the program. With the ability to differentiate the plant leaves from the environment, the engineered model will recognise 13 specific forms of plant diseases from safe leaves. This approach for identifying plant disease was introduced for the first time, according to our understanding. The entire paper outlines all important measures possible for the introduction of this model for disease identification, beginning with the picture collection to establish a database reviewed by agricultural experts. The comprehensive CNN preparation was carried out by Caffe, a fundamental research system developed by Berkley Vision and Learning Center. On average, the experimental results of the built model were 91 to 98 percent reliable for separate class research. [ABSTRACT FROM AUTHOR]

Deep learning of multilayered computational models allowed processing to recognize the representation of data at multiple levels of abstraction. These technologies have significantly improved to identify breast cancer. Convolutional Neural Network (CNN) is a type of radiological basis for classification problems and is based on the Bayes decision-making base, which reduces the expected error in classification. In this paper,it is proposed to detect breast cancer using CNN of the mammography system to classify the mammogram to noncancerous abnormality and cancerous abnormality. The goal of Breast Cancer Detection based on CNN for speeding up diagnosis by helping a particular diagnose and classify breast cancer.A set of images of a mammogram is used to perform the pre-processing of the histogram equalization and adjust the appropriate parameters for the CNN work. Then, the whole changed images are set in CNN to classify as a training source. A CNN classifies can be produced as a model foridentifying the mammogram. the BCDCNN method with the mammography classification utilizing MCCANN comparison with BCDCNN improved the classificationaccuracy on mammographic. Therefore, the results showed that the proposed system has a higher resolution than the other recently existing systems, and the only mass containing all was maximized from 0.84 to 0.88 and 0.70 to 0.82 accuracy. [ABSTRACT FROM AUTHOR]

The super-resolution (SR) reconstruction of a single image is an important image synthesis task especially for medical applications. This paper is studying the application of image segmentation for lung cancer images. This research work is utilizing the power of deep learning for resolution reconstruction for lung cancer-based images. At present, the neural networks utilized for image segmentation and classification are suffering from the loss of information where information passes through one layer to another deep layer. The commonly used loss functions include content-based reconstruction loss and generative confrontation network. The sparse coding single-image super-resolution reconstruction algorithm can easily lead to the phenomenon of incorrect geometric structure in the reconstructed image. In order to solve the problem of excessive smoothness and blurring of the reconstructed image edges caused by the introduction of this self-similarity constraint, a two-layer reconstruction framework based on a smooth layer and a texture layer is proposed for a medical application of lung cancer. This method uses a global nonzero gradient number constrained reconstruction model to reconstruct the smooth layer. The proposed sparse coding method is used to reconstruct high-resolution texture images. Finally, a global and local optimization models are used to further improve the quality of the reconstructed image. An adaptive multiscale remote sensing image super-division reconstruction network is designed. The selective core network and adaptive gating unit are integrated to extract and fuse features to obtain a preliminary reconstruction. Through the proposed dual-drive module, the feature prior drive loss and task drive loss are transmitted to the super-resolution network. The proposed work not only improves the subjective visual effect but the robustness has also been enhanced with more accurate construction of edges. The statistical evaluators are used to test the viability of the proposed scheme. [ABSTRACT FROM AUTHOR]

Automatic and accurate segmentation of optic disc (OD) and optic cup (OC) in fundus images is a fundamental task in computer-aided ocular pathologies diagnosis. The complex structures, such as blood vessels and macular region, and the existence of lesions in fundus images bring great challenges to the segmentation task. Recently, the convolutional neural network-based methods have exhibited its potential in fundus image analysis. In this paper, we propose a cascaded two-stage network architecture for robust and accurate OD and OC segmentation in fundus images. In the first stage, the U-Net like framework with an improved attention mechanism and focal loss is proposed to detect accurate and reliable OD location from the full-scale resolution fundus images. Based on the outputs of the first stage, a refined segmentation network in the second stage that integrates multi-task framework and adversarial learning is further designed for OD and OC segmentation separately. The multi-task framework is conducted to predict the OD and OC masks by simultaneously estimating contours and distance maps as auxiliary tasks, which can guarantee the smoothness and shape of object in segmentation predictions. The adversarial learning technique is introduced to encourage the segmentation network to produce an output that is consistent with the true labels in space and shape distribution. We evaluate the performance of our method using two public retinal fundus image datasets (RIM-ONE-r3 and REFUGE). Extensive ablation studies and comparison experiments with existing methods demonstrate that our approach can produce competitive performance compared with state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The health management of the reciprocating compressor is crucial for its long term steady operation and safety. Online condition monitoring technology for the reciprocating compressor is almost mature, whereas the fault diagnosis technologies are still insufficient to meet the need. Therefore, in this paper, a novel fault detection method for the reciprocating compressor based on digital image processing and artificial neural network (ANN) was proposed. This method is implemented to the sectionalized pressure–volume (p–V) curves, which are obtained by dividing a working cycle in the cylinder into four thermal processes, including expansion, suction, compression and discharge. Hit-or-miss transform is adopted to extract the comprehensive gradients of expansion and compression curves, and vertical projection transform is applied to extract the vertical projection features. Finally, all of the features are fed to an ANN to do classification. To validate the proposed method, a seeded fault testing was conducted to collect real running data. The results showed that the new approach shows a good performance, with a high classification accuracy of 97.9%. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) is an age-related disease that affects a large proportion of the elderly. Currently, the neuroimaging techniques [e.g., magnetic resonance imaging (MRI) and positron emission tomography (PET)] are promising modalities for AD diagnosis. Since not all brain regions are affected by AD, a common technique is to study some region-of-interests (ROIs) that are believed to be closely related to AD. Conventional methods used ROIs, identified by the handcrafted features through Automated Anatomical Labeling (AAL) atlas rather than utilizing the original images which may induce missing informative features. In addition, they learned their framework based on the discriminative patches instead of full images for AD diagnosis in multistage learning scheme. In this paper, we integrate the original image features from MRI and PET with their ROIs features in one learning process. Furthermore, we use the ROIs features for forcing the network to focus on the regions that is highly related to AD and hence, the performance of the AD diagnosis can be improved. Specifically, we first obtain the ROIs features from the AAL, then we register every ROI with its corresponding region of the original image to get a synthetic image for each modality of every subject. Then, we employ the convolutional auto-encoder network for learning the synthetic image features and the convolutional neural network (CNN) for learning the original image features. Meanwhile, we concatenate the features from both networks after each convolution layer. Finally, the highly learned features from the MRI and PET are concatenated for brain disease classification. Experiments are carried out on the ADNI datasets including ADNI-1 and ADNI-2 to evaluate our method performance. Our method demonstrates a higher performance in brain disease classification than the recent studies. [ABSTRACT FROM AUTHOR]

Skin cancer is the most common type of cancer that affects humans and is usually diagnosed by initial clinical screening, which is followed by dermoscopic analysis. Automated classification of skin lesions is still a challenging task because of the high visual similarity between melanoma and benign lesions. This paper proposes a new residual deep convolutional neural network (RDCNN) for skin lesions diagnosis. The proposed neural network is trained and tested using six well-known skin cancer datasets, PH2, DermIS and Quest, MED-NODE, ISIC2016, ISIC2017, and ISIC2018. Three different experiments are carried out to measure the performance of the proposed RDCNN. In the first experiment, the proposed RDCNN is trained and tested using the original dataset images without any pre-processing or segmentation. In the second experiment, the proposed RDCNN is tested using segmented images. Finally, the utilized trained model in the second experiment is saved and reused in the third experiment as a pre-trained model. Then, it is trained again using a different dataset. The proposed RDCNN shows significant high performance and outperforms the existing deep convolutional networks. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy is a chronic condition that causes vision loss if not detected early. In the early stage, it can be diagnosed with the aid of exudates which are called lesions. However, it is arduous to detect the exudate lesion due to the availability of blood vessels and other distractions. To tackle these issues, we proposed a novel exudates classification from the fundus image known as hybrid convolutional neural network (CNN)-based binary local search optimizer–based particle swarm optimization algorithm. The proposed method from this paper exploits image augmentation to enlarge the fundus image to the required size without losing any features. The features from the resized fundus images are extracted as a feature vector and fed into the feed-forward CNN as the input. Henceforth, it classifies the exudates from the fundus image. Further, the hyperparameters are optimized to reduce the computational complexities by utilization of binary local search optimizer (BLSO) and particle swarm optimization (PSO). The experimental analysis is conducted on the public ROC and real-time ARA400 datasets and compared with the state-of-art works such as support vector machine classifiers, multi-modal/multi-scale, random forest, and CNN for the performance metrics. The classification accuracy is high for the proposed work, and thus, our proposed outperforms all the other approaches. [ABSTRACT FROM AUTHOR]

Defocus blur detection is an important and challenging task in computer vision and digital imaging fields. Previous work on defocus blur detection has put a lot of effort into designing local sharpness metric maps. This paper presents a simple yet effective method to automatically obtain the local metric map for defocus blur detection, which based on the feature learning of multiple convolutional neural networks (ConvNets). The ConvNets automatically learn the most locally relevant features at the super-pixel level of the image in a supervised manner. By extracting convolution kernels from the trained neural network structures and processing it with principal component analysis, we can automatically obtain the local sharpness metric by reshaping the principal component vector. Meanwhile, an effective iterative updating mechanism is proposed to refine the defocus blur detection result from coarse to fine by exploiting the intrinsic peculiarity of the hyperbolic tangent function. The experimental results demonstrate that our proposed method consistently performed better than the previous state-of-the-art methods. [ABSTRACT FROM AUTHOR]