Search

Dermatological conditions are primarily prevalent in humans and are primarily caused by environmental and climatic fluctuations, as well as various other reasons. Timely identification is the most effective remedy to avert minor ailments from escalating into severe conditions. Diagnosing skin illnesses is consistently challenging for health practitioners. Presently, they rely on conventional methods, such as examining the condition of the skin. State-of-the-art technologies can enhance the accuracy of skin disease diagnosis by utilizing data-driven approaches. This paper presents a Computer Assisted Diagnosis (CAD) framework that has been developed to detect skin illnesses at an early stage. We suggest a computationally efficient and lightweight deep learning model that utilizes a CNN architecture. We then do thorough experiments to compare the performance of shallow and deep learning models. The CNN model under consideration consists of seven convolutional layers and has obtained an accuracy of 87.64% when applied to three distinct disease categories. The studies were conducted using the International Skin Imaging Collaboration (ISIC) dataset, which exclusively consists of dermoscopic images. This study enhances the field of skin disease diagnostics by utilizing state-of-the-art technology, attaining exceptional levels of accuracy, and striving for efficiency improvements. The unique features and future considerations of this technology create opportunities for additional advancements in the automated diagnosis of skin diseases and tailored treatment. [ABSTRACT FROM AUTHOR]

In recent years, deep convolutional neural networks (DCNNs) have shown promising performance in medical image analysis, including breast lesion classification in 2D ultrasound (US) images. Despite the outstanding performance of DCNN solutions, explaining their decisions remains an open investigation. Yet, the explainability of DCNN models has become essential for healthcare systems to accept and trust the models. This paper presents a novel framework for explaining DCNN classification decisions of lesions in ultrasound images using the saliency maps linking the DCNN decisions to known cancer characteristics in the medical domain. The proposed framework consists of three main phases. First, DCNN models for classification in ultrasound images are built. Next, selected methods for visualization are applied to obtain saliency maps on the input images of the DCNN models. In the final phase, the visualization outputs and domain-known cancer characteristics are mapped. The paper then demonstrates the use of the framework for breast lesion classification from ultrasound images. We first follow the transfer learning approach and build two DCNN models. We then analyze the visualization outputs of the trained DCNN models using the EGrad-CAM and Ablation-CAM methods. We map the DCNN model decisions of benign and malignant lesions through the visualization outputs to the characteristics such as echogenicity, calcification, shape, and margin. A retrospective dataset of 1298 US images collected from different hospitals is used to evaluate the effectiveness of the framework. The test results show that these characteristics contribute differently to the benign and malignant lesions' decisions. Our study provides the foundation for other researchers to explain the DCNN classification decisions of other cancer types. [ABSTRACT FROM AUTHOR]

Human-machine interfaces hold promise in enhancing rehabilitation by predicting and responding to subjects' movement intent. In gait rehabilitation, neural network architectures utilize lower-limb muscle and brain activity to predict continuous kinematics and kinetics during stepping and walking. This systematic review, spanning five databases, assessed 16 papers meeting inclusion criteria. Studies predicted lower-limb kinematics and kinetics using electroencephalograms (EEGs), electromyograms (EMGs), or a combination with kinematic data and anthropological parameters. Long short-term memory (LSTM) and convolutional neural network (CNN) tools demonstrated highest accuracies. EEG focused on joint angles, while EMG predicted moments and torque joints. Useful EEG electrode locations included C3, C4, Cz, P3, F4, and F8. Vastus Lateralis, Rectus Femoris, and Gastrocnemius were the most commonly accessed muscles for kinematic and kinetic prediction using EMGs. No studies combining EEGs and EMGs to predict lower-limb kinematics and kinetics during stepping or walking were found, suggesting a potential avenue for future development in this technology. [ABSTRACT FROM AUTHOR]

Cervical cancer (CCa) is the fourth most prevalent and common cancer affecting women worldwide, with increasing incidence and mortality rates. Hence, early detection of CCa plays a crucial role in improving outcomes. Non-invasive imaging procedures with good diagnostic performance are desirable and have the potential to lessen the degree of intervention associated with the gold standard, biopsy. Recently, artificial intelligence-based diagnostic models such as Vision Transformers (ViT) have shown promising performance in image classification tasks, rivaling or surpassing traditional convolutional neural networks (CNNs). This paper studies the effect of applying a ViT to predict CCa using different image benchmark datasets. A newly developed approach (ViT-PSO-SVM) was presented for boosting the results of the ViT based on integrating the ViT with particle swarm optimization (PSO), and support vector machine (SVM). First, the proposed framework extracts features from the Vision Transformer. Then, PSO is used to reduce the complexity of extracted features and optimize feature representation. Finally, a softmax classification layer is replaced with an SVM classification model to precisely predict CCa. The models are evaluated using two benchmark cervical cell image datasets, namely SipakMed and Herlev, with different classification scenarios: two, three, and five classes. The proposed approach achieved 99.112% accuracy and 99.113% F1-score for SipakMed with two classes and achieved 97.778% accuracy and 97.805% F1-score for Herlev with two classes outperforming other Vision Transformers, CNN models, and pre-trained models. Finally, GradCAM is used as an explainable artificial intelligence (XAI) tool to visualize and understand the regions of a given image that are important for a model's prediction. The obtained experimental results demonstrate the feasibility and efficacy of the developed ViT-PSO-SVM approach and hold the promise of providing a robust, reliable, accurate, and non-invasive diagnostic tool that will lead to improved healthcare outcomes worldwide. [ABSTRACT FROM AUTHOR]

Accurate inferior alveolar nerve (IAN) canal segmentation has been considered a crucial task in dentistry. Failing to accurately identify the position of the IAN canal may lead to nerve injury during dental procedures. While IAN canals can be detected from dental cone beam computed tomography, they are usually difficult for dentists to precisely identify as the canals are thin, small, and span across many slices. This paper focuses on improving accuracy in segmenting the IAN canals. By integrating our proposed frequency-domain attention mechanism in UNet, the proposed frequency attention UNet (FAUNet) is able to achieve 75.55 % and 81.35 % in the Dice and surface Dice coefficients, respectively, which are much higher than other competitive methods, by adding only 224 parameters to the classical UNet. Compared to the classical UNet, our proposed FAUNet achieves a 2.39 % and 2.82 % gain in the Dice coefficient and the surface Dice coefficient, respectively. The potential advantage of developing attention in the frequency domain is also discussed, which revealed that the frequency-domain attention mechanisms can achieve better performance than their spatial-domain counterparts. [ABSTRACT FROM AUTHOR]

Blood oxygen saturation (SpO2) is an essential physiological parameter for evaluating a person's health. While conventional SpO2 measurement devices like pulse oximeters require skin contact, advanced computer vision technology can enable remote SpO2 monitoring through a regular camera without skin contact. In this paper, we propose novel deep learning models to measure SpO2 remotely from facial videos and evaluate them using a public benchmark database, VIPL-HR. We utilize a spatial–temporal representation to encode SpO2 information recorded by conventional RGB cameras and directly pass it into selected convolutional neural networks to predict SpO2. The best deep learning model achieves 1.274% in mean absolute error and 1.71% in root mean squared error, which exceed the international standard of 4% for an approved pulse oximeter. Our results significantly outperform the conventional analytical Ratio of Ratios model for contactless SpO2 measurement. Results of sensitivity analyses of the influence of spatial–temporal representation color spaces, subject scenarios, acquisition devices, and SpO2 ranges on the model performance are reported with explainability analyses to provide more insights for this emerging research field. [ABSTRACT FROM AUTHOR]

Accurate and reliable estimation of the pelvic tilt is one of the essential pre-planning factors for total hip arthroplasty to prevent common post-operative complications such as implant impingement and dislocation. Inspired by the latest advances in deep learning-based systems, our focus in this paper has been to present an innovative and accurate method for estimating the functional pelvic tilt (PT) from a standing anterior–posterior (AP) radiography image. We introduce an encoder–decoder-style network based on a concurrent learning approach called VGG-UNET (VGG embedded in U-NET), where a deep fully convolutional network known as VGG is embedded at the encoder part of an image segmentation network, i.e., U-NET. In the bottleneck of the VGG-UNET, in addition to the decoder path, we use another path utilizing light-weight convolutional and fully connected layers to combine all extracted feature maps from the final convolution layer of VGG and thus regress PT. In the test phase, we exclude the decoder path and consider only a single target task i.e., PT estimation. The absolute errors obtained using VGG-UNET, VGG, and Mask R-CNN are 3.04 ± 2.49, 3.92 ± 2.92, and 4.97 ± 3.87, respectively. It is observed that the VGG-UNET leads to a more accurate prediction with a lower standard deviation (STD). Our experimental results demonstrate that the proposed multi-task network leads to a significantly improved performance compared to the best-reported results based on cascaded networks. [ABSTRACT FROM AUTHOR]

The influence of the coupled electroencephalography (EEG) signal in electrooculography (EOG) on EOG-based automatic sleep staging has been ignored. Since the EOG and prefrontal EEG are collected at close range, it is not clear whether EEG couples in EOG or not, and whether or not the EOG signal can achieve good sleep staging results due to its intrinsic characteristics. In this paper, the effect of a coupled EEG signal in an EOG signal on automatic sleep staging is explored. The blind source separation algorithm was used to extract a clean prefrontal EEG signal. Then the raw EOG signal and clean prefrontal EEG signal were processed to obtain EOG signals coupled with different EEG signal contents. Afterwards, the coupled EOG signals were fed into a hierarchical neural network, including a convolutional neural network and recurrent neural network for automatic sleep staging. Finally, an exploration was performed using two public datasets and one clinical dataset. The results showed that using a coupled EOG signal could achieve an accuracy of 80.4%, 81.1%, and 78.9% for the three datasets, slightly better than the accuracy of sleep staging using the EOG signal without coupled EEG. Thus, an appropriate content of coupled EEG signal in an EOG signal improved the sleep staging results. This paper provides an experimental basis for sleep staging with EOG signals. [ABSTRACT FROM AUTHOR]

Precise surveillance and assessment of spinal disorders are important for improving health care and patient survival rates. The assessment of spinal disorders, such as scoliosis assessment, depends heavily on precise vertebra landmark localization. However, existing methods usually search for only a handful of keypoints in a high-resolution image. In this paper, we propose the S2D-VLI VLDet network, a unified end-to-end vertebra landmark detection network for the assessment of scoliosis. The proposed network considers the spatially relevant information both from inside and between vertebrae. The new vertebral line interpolation method converts the training labels from sparse to dense, which can improve the network learning process and method performance. In addition, through the combined use of the Cartesian and polar coordinate systems in our method, the symmetric mean absolute percentage error (SMAPE) in scoliosis assessment can be reduced substantially. Specifically, as shown in the experiments, the SMAPE value decreases from 9.82 to 8.28. The experimental results indicate that our proposed approach is beneficial for estimating the Cobb angle and identifying landmarks in X-ray scans with low contrast. [ABSTRACT FROM AUTHOR]

Radar signal has been shown as a promising source for human identification. In daily home sleep-monitoring scenarios, large-scale motion features may not always be practical, and the heart motion or respiration data may not be as ideal as they are in a controlled laboratory setting. Human identification from radar sequences is still a challenging task. Furthermore, there is a need to address the open-set recognition problem for radar sequences, which has not been sufficiently studied. In this paper, we propose a deep learning-based approach for human identification using radar sequences captured during sleep in a daily home-monitoring setup. To enhance robustness, we preprocess the sequences to mitigate environmental interference before employing a deep convolution neural network for human identification. We introduce a Principal Component Space feature representation to detect unknown sequences. Our method is rigorously evaluated using both a public data set and a set of experimentally acquired radar sequences. We report a labeling accuracy of 98.2% and 96.8% on average for the two data sets, respectively, which outperforms the state-of-the-art techniques. Our method excels at accurately distinguishing unknown sequences from labeled ones, with nearly 100% detection of unknown samples and minimal misclassification of labeled samples as unknown. [ABSTRACT FROM AUTHOR]

Background: Breast cancer is arguably one of the leading causes of death among women around the world. The automation of the early detection process and classification of breast masses has been a prominent focus for researchers in the past decade. The utilization of ultrasound imaging is prevalent in the diagnostic evaluation of breast cancer, with its predictive accuracy being dependent on the expertise of the specialist. Therefore, there is an urgent need to create fast and reliable ultrasound image detection algorithms to address this issue. Methods: This paper aims to compare the efficiency of six state-of-the-art, fine-tuned deep learning models that can classify breast tissue from ultrasound images into three classes: benign, malignant, and normal, using transfer learning. Additionally, the architecture of a custom model is introduced and trained from the ground up on a public dataset containing 780 images, which was further augmented to 3900 and 7800 images, respectively. What is more, the custom model is further validated on another private dataset containing 163 ultrasound images divided into two classes: benign and malignant. The pre-trained architectures used in this work are ResNet-50, Inception-V3, Inception-ResNet-V2, MobileNet-V2, VGG-16, and DenseNet-121. The performance evaluation metrics that are used in this study are as follows: Precision, Recall, F1-Score and Specificity. Results: The experimental results show that the models trained on the augmented dataset with 7800 images obtained the best performance on the test set, having 94.95 ± 0.64%, 97.69 ± 0.52%, 97.69 ± 0.13%, 97.77 ± 0.29%, 95.07 ± 0.41%, 98.11 ± 0.10%, and 96.75 ± 0.26% accuracy for the ResNet-50, MobileNet-V2, InceptionResNet-V2, VGG-16, Inception-V3, DenseNet-121, and our model, respectively. Conclusion: Our proposed model obtains competitive results, outperforming some state-of-the-art models in terms of accuracy and training time. [ABSTRACT FROM AUTHOR]

This paper provides an in-depth overview of Deep Neural Networks and their application in the segmentation and analysis of lung Magnetic Resonance Imaging (MRI) scans, specifically focusing on hyperpolarized gas MRI and the quantification of lung ventilation defects. An in-depth understanding of Deep Neural Networks is presented, laying the groundwork for the exploration of their use in hyperpolarized gas MRI and the quantification of lung ventilation defects. Five distinct studies are examined, each leveraging unique deep learning architectures and data augmentation techniques to optimize model performance. These studies encompass a range of approaches, including the use of 3D Convolutional Neural Networks, cascaded U-Net models, Generative Adversarial Networks, and nnU-net for hyperpolarized gas MRI segmentation. The findings highlight the potential of deep learning methods in the segmentation and analysis of lung MRI scans, emphasizing the need for consensus on lung ventilation segmentation methods. [ABSTRACT FROM AUTHOR]

End-to-end deep learning models have shown promising results for the automatic screening of Parkinson's disease by voice and speech. However, these models often suffer degradation in their performance when applied to scenarios involving multiple corpora. In addition, they also show corpus-dependent clusterings. These facts indicate a lack of generalisation or the presence of certain shortcuts in the decision, and also suggest the need for developing new corpus-independent models. In this respect, this work explores the use of domain adversarial training as a viable strategy to develop models that retain their discriminative capacity to detect Parkinson's disease across diverse datasets. The paper presents three deep learning architectures and their domain adversarial counterparts. The models were evaluated with sustained vowels and diadochokinetic recordings extracted from four corpora with different demographics, dialects or languages, and recording conditions. The results showed that the space distribution of the embedding features extracted by the domain adversarial networks exhibits a higher intra-class cohesion. This behaviour is supported by a decrease in the variability and inter-domain divergence computed within each class. The findings suggest that domain adversarial networks are able to learn the common characteristics present in Parkinsonian voice and speech, which are supposed to be corpus, and consequently, language independent. Overall, this effort provides evidence that domain adaptation techniques refine the existing end-to-end deep learning approaches for Parkinson's disease detection from voice and speech, achieving more generalizable models. [ABSTRACT FROM AUTHOR]

In recent decades, medical imaging techniques have revolutionized the field of disease diagnosis, enabling healthcare professionals to noninvasively observe the internal structures of the human body. Among these techniques, optical coherence tomography (OCT) has emerged as a powerful and versatile tool that allows high-resolution, non-invasive, and real-time imaging of biological tissues. Deep learning algorithms have been successfully employed to detect and classify various retinal diseases in OCT images, enabling early diagnosis and treatment planning. However, existing deep learning algorithms are primarily designed for single-disease diagnosis, which limits their practical application in clinical settings where OCT images often contain symptoms of multiple diseases. In this paper, we propose an effective approach for multi-disease diagnosis in OCT images using a multi-scale learning (MSL) method and a sparse residual network (SRN). Specifically, the MSL method extracts and fuses useful features from images of different sizes to enhance the discriminative capability of a classifier and make the disease predictions interpretable. The SRN is a minimal residual network, where convolutional layers with large kernel sizes are replaced with multiple convolutional layers that have smaller kernel sizes, thereby reducing model complexity while achieving a performance similar to that of existing convolutional neural networks. The proposed multi-scale sparse residual network significantly outperforms existing methods, exhibiting 97.40% accuracy, 95.38% sensitivity, and 98.25% specificity. Experimental results show the potential of our method to improve explainable diagnosis systems for various eye diseases via visual discrimination. [ABSTRACT FROM AUTHOR]

Early detection is crucial for the survival and recovery of lung cancer patients. Computer-aided diagnosis system can assist in the early diagnosis of lung cancer by providing decision support. While deep learning methods are increasingly being applied to tasks such as CAD (Computer-aided diagnosis system), these models lack interpretability. In this paper, we propose a convolutional neural network model that combines semantic characteristics (SCCNN) to predict whether a given pulmonary nodule is malignant. The model synthesizes the advantages of multi-view, multi-task and attention modules in order to fully simulate the actual diagnostic process of radiologists. The 3D (three dimensional) multi-view samples of lung nodules are extracted by spatial sampling method. Meanwhile, semantic characteristics commonly used in radiology reports are used as an auxiliary task and serve to explain how the model interprets. The introduction of the attention module in the feature fusion stage improves the classification of lung nodules as benign or malignant. Our experimental results using the LIDC-IDRI (Lung Image Database Consortium and Image Database Resource Initiative) show that this study achieves 95.45% accuracy and 97.26% ROC (Receiver Operating Characteristic) curve area. The results show that the method we proposed not only realize the classification of benign and malignant compared to standard 3D CNN approaches but can also be used to intuitively explain how the model makes predictions, which can assist clinical diagnosis. [ABSTRACT FROM AUTHOR]

A brain stroke is a life-threatening medical disorder caused by the inadequate blood supply to the brain. After the stroke, the damaged area of the brain will not operate normally. As a result, early detection is crucial for more effective therapy. Computed tomography (CT) images supply a rapid diagnosis of brain stroke. However, while doctors are analyzing each brain CT image, time is running fast. This circumstance may lead to result in a delay in treatment and making errors. Therefore, we targeted the utilization of an efficient artificial intelligence algorithm in stroke detection. In this paper, we designed hybrid algorithms that include a new convolution neural networks (CNN) architecture called OzNet and various machine learning algorithms for binary classification of real brain stroke CT images. When we classified the dataset with OzNet, we acquired successful performance. However, for this target, we combined it with a minimum Redundancy Maximum Relevance (mRMR) method and Decision Tree (DT), k-Nearest Neighbors (kNN), Linear Discriminant Analysis (LDA), Naïve Bayes (NB), and Support Vector Machines (SVM). In addition, 4096 significant features were obtained from the fully connected layer of OzNet, and we reduced the dimension of features from 4096 to 250 using the mRMR method. Finally, we utilized these machine learning algorithms to classify important features. As a result, OzNet-mRMR-NB was an excellent hybrid algorithm and achieved an accuracy of 98.42% and AUC of 0.99 to detect stroke from brain CT images. [ABSTRACT FROM AUTHOR]

Alzheimer's disease (AD) is a progressive neurodegenerative disorder that affects millions of people worldwide. Early and accurate prediction of AD progression is crucial for early intervention and personalized treatment planning. Although AD does not yet have a reliable therapy, several medications help slow down the disease's progression. However, more study is still needed to develop reliable methods for detecting AD and its phases. In the recent past, biomarkers associated with AD have been identified using neuroimaging methods. To uncover biomarkers, deep learning techniques have quickly emerged as a crucial methodology. A functional molecular imaging technique known as fluorodeoxyglucose positron emission tomography (18F-FDG-PET) has been shown to be effective in assisting researchers in understanding the morphological and neurological alterations to the brain associated with AD. Convolutional neural networks (CNNs) have also long dominated the field of AD progression and have been the subject of substantial research, while more recent approaches like vision transformers (ViT) have not yet been fully investigated. In this paper, we present a self-supervised learning (SSL) method to automatically acquire meaningful AD characteristics using the ViT architecture by pretraining the feature extractor using the self-distillation with no labels (DINO) and extreme learning machine (ELM) as classifier models. In this work, we examined a technique for predicting mild cognitive impairment (MCI) to AD utilizing an SSL model which learns powerful representations from unlabeled 18F-FDG PET images, thus reducing the need for large-labeled datasets. In comparison to several earlier approaches, our strategy showed state-of-the-art classification performance in terms of accuracy (92.31%), specificity (90.21%), and sensitivity (95.50%). Then, to make the suggested model easier to understand, we highlighted the brain regions that significantly influence the prediction of MCI development. Our methods offer a precise and efficient strategy for predicting the transition from MCI to AD. In conclusion, this research presents a novel Explainable SSL-ViT model that can accurately predict AD progress based on 18F-FDG PET scans. SSL, attention, and ELM mechanisms are integrated into the model to make it more predictive and interpretable. Future research will enable the development of viable treatments for neurodegenerative disorders by combining brain areas contributing to projection with observed anatomical traits. [ABSTRACT FROM AUTHOR]

Photoacoustic (PA) imaging can be used to monitor high-intensity focused ultrasound (HIFU) therapies because ablation changes the optical absorption spectrum of the tissue, and this change can be detected with PA imaging. Multi-wavelength photoacoustic (MWPA) imaging makes this change easier to detect by repeating PA imaging at multiple optical wavelengths and sampling the optical absorption spectrum more thoroughly. Real-time pixel-wise classification in MWPA imaging can assist clinicians in monitoring HIFU lesion formation and will be a crucial milestone towards full HIFU therapy automation based on artificial intelligence. In this paper, we present a deep-learning-based approach to segment HIFU lesions in MWPA images. Ex vivo bovine tissue is ablated with HIFU and imaged via MWPA imaging. The acquired MWPA images are then used to train and test a convolutional neural network (CNN) for lesion segmentation. Traditional machine learning algorithms are also trained and tested to compare with the CNN, and the results show that the performance of the CNN significantly exceeds traditional machine learning algorithms. Feature selection is conducted to reduce the number of wavelengths to facilitate real-time implementation while retaining good segmentation performance. This study demonstrates the feasibility and high performance of the deep-learning-based lesion segmentation method in MWPA imaging to monitor HIFU lesion formation and the potential to implement this method in real time. [ABSTRACT FROM AUTHOR]

Microarray gene expression-based detection and classification of medical conditions have been prominent in research studies over the past few decades. However, extracting relevant data from the high-volume microarray gene expression with inherent nonlinearity and inseparable noise components raises significant challenges during data classification and disease detection. The dataset used for the research is the Lung Harvard 2 Dataset (LH2) which consists of 150 Adenocarcinoma subjects and 31 Mesothelioma subjects. The paper proposes a two-level strategy involving feature extraction and selection methods before the classification step. The feature extraction step utilizes Short Term Fourier Transform (STFT), and the feature selection step employs Particle Swarm Optimization (PSO) and Harmonic Search (HS) metaheuristic methods. The classifiers employed are Nonlinear Regression, Gaussian Mixture Model, Softmax Discriminant, Naive Bayes, SVM (Linear), SVM (Polynomial), and SVM (RBF). The two-level extracted relevant features are compared with raw data classification results, including Convolutional Neural Network (CNN) methodology. Among the methods, STFT with PSO feature selection and SVM (RBF) classifier produced the highest accuracy of 94.47%. [ABSTRACT FROM AUTHOR]

Dental X-ray images are important and useful for dentists to diagnose dental diseases. Utilizing deep learning in dental X-ray images can help dentists quickly and accurately identify common dental diseases such as periodontitis and dental caries. This paper applies image processing and deep learning technologies to dental X-ray images to propose a simultaneous recognition method for periodontitis and dental caries. The single-tooth X-ray image is detected by the YOLOv7 object detection technique and cropped from the periapical X-ray image. Then, it is processed through contrast-limited adaptive histogram equalization to enhance the local contrast, and bilateral filtering to eliminate noise while preserving the edge. The deep learning architecture for classification comprises a pre-trained EfficientNet-B0 and fully connected layers that output two labels by the sigmoid activation function for the classification task. The average precision of tooth detection using YOLOv7 is 97.1%. For the recognition of periodontitis, the area under the curve (AUC) of the receiver operating characteristic (ROC) curve is 98.67%, and the AUC of the precision-recall (PR) curve is 98.38%. For the recognition of dental caries, the AUC of the ROC curve is 98.31%, and the AUC of the PR curve is 97.55%. Different from the conventional deep learning-based methods for a single disease such as periodontitis or dental caries, the proposed approach can provide the recognition of both periodontitis and dental caries simultaneously. This recognition method presents good performance in the identification of periodontitis and dental caries, thus facilitating dental diagnosis. [ABSTRACT FROM AUTHOR]

Arrhythmias are defined as irregularities in the heartbeat rhythm, which may infrequently occur in a human's life. These arrhythmias may cause potentially fatal complications, which may lead to an immediate risk of life. Thus, the detection and classification of arrhythmias is a pertinent issue for cardiac diagnosis. (1) Background: To capture these sporadic events, an electrocardiogram (ECG), a register containing the heart's electrical function, is considered the gold standard. However, since ECG carries a vast amount of information, it becomes very complex and challenging to extract the relevant information from visual analysis. As a result, designing an efficient (automated) system to analyse the enormous quantity of data possessed by ECG is critical. (2) Method: This paper proposes a hybrid deep learning-based approach to automate the detection and classification process. This paper makes two-fold contributions. First, 1D ECG signals are translated into 2D Scalogram images to automate the noise filtering and feature extraction. Then, based on experimental evidence, by combining two learning models, namely 2D convolutional neural network (CNN) and the Long Short-Term Memory (LSTM) network, a hybrid model called 2D-CNN-LSTM is proposed. (3) Result: To evaluate the efficacy of the proposed 2D-CNN-LSTM approach, we conducted a rigorous experimental study using the widely adopted MIT–BIH arrhythmia database. The obtained results show that the proposed approach provides ≈98.7%, 99%, and 99% accuracy for Cardiac Arrhythmias (ARR), Congestive Heart Failure (CHF), and Normal Sinus Rhythm (NSR), respectively. Moreover, it provides an average sensitivity of the proposed model of 98.33% and a specificity value of 98.35%, for all three arrhythmias. (4) Conclusions: For the classification of arrhythmias, a robust approach has been introduced where 2 D scalogram images of ECG signals are trained over the CNN-LSTM model. The results obtained are better as compared to the other existing techniques and will greatly reduce the amount of intervention required by doctors. For future work, the proposed method can be applied over some live ECG signals and Bi-LSTM can be applied instead of LSTM. [ABSTRACT FROM AUTHOR]

Artificial neural networks (ANNs) ability to learn, correct errors, and transform a large amount of raw data into beneficial medical decisions for treatment and care has increased in popularity for enhanced patient safety and quality of care. Therefore, this paper reviews the critical role of ANNs in providing valuable insights for patients' healthcare decisions and efficient disease diagnosis. We study different types of ANNs in the existing literature that advance ANNs' adaptation for complex applications. Specifically, we investigate ANNs' advances for predicting viral, cancer, skin, and COVID-19 diseases. Furthermore, we propose a deep convolutional neural network (CNN) model called ConXNet, based on chest radiography images, to improve the detection accuracy of COVID-19 disease. ConXNet is trained and tested using a chest radiography image dataset obtained from Kaggle, achieving more than 97% accuracy and 98% precision, which is better than other existing state-of-the-art models, such as DeTraC, U-Net, COVID MTNet, and COVID-Net, having 93.1%, 94.10%, 84.76%, and 90% accuracy and 94%, 95%, 85%, and 92% precision, respectively. The results show that the ConXNet model performed significantly well for a relatively large dataset compared with the aforementioned models. Moreover, the ConXNet model reduces the time complexity by using dropout layers and batch normalization techniques. Finally, we highlight future research directions and challenges, such as the complexity of the algorithms, insufficient available data, privacy and security, and integration of biosensing with ANNs. These research directions require considerable attention for improving the scope of ANNs for medical diagnostic and treatment applications. [ABSTRACT FROM AUTHOR]

The dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) technique has taken on a significant and increasing role in diagnostic procedures and treatments for patients who suffer from chronic kidney disease. Careful segmentation of kidneys from DCE-MRI scans is an essential early step towards the evaluation of kidney function. Recently, deep convolutional neural networks have increased in popularity in medical image segmentation. To this end, in this paper, we propose a new and fully automated two-phase approach that integrates convolutional neural networks and level set methods to delimit kidneys in DCE-MRI scans. We first develop two convolutional neural networks that rely on the U-Net structure (UNT) to predict a kidney probability map for DCE-MRI scans. Then, to leverage the segmentation performance, the pixel-wise kidney probability map predicted from the deep model is exploited with the shape prior information in a level set method to guide the contour evolution towards the target kidney. Real DCE-MRI datasets of 45 subjects are used for training, validating, and testing the proposed approach. The valuation results demonstrate the high performance of the two-phase approach, achieving a Dice similarity coefficient of 0.95 ± 0.02 and intersection over union of 0.91 ± 0.03, and 1.54 ± 1.6 considering a 95% Hausdorff distance. Our intensive experiments confirm the potential and effectiveness of that approach over both UNT models and numerous recent level set-based methods. [ABSTRACT FROM AUTHOR]

Three-dimensional (3D) image analyses are frequently applied to perform classification tasks. Herein, 3D-based machine learning systems are generally used/generated by examining two designs: a 3D-based deep learning model or a 3D-based task-specific framework. However, except for a new approach named 3t2FTS, a promising feature transform operating from 3D to two-dimensional (2D) space has not been efficiently investigated for classification applications in 3D magnetic resonance imaging (3D MRI). In other words, a state-of-the-art feature transform strategy is not available that achieves high accuracy and provides the adaptation of 2D-based deep learning models for 3D MRI-based classification. With this aim, this paper presents a new version of the 3t2FTS approach (3t2FTS-v2) to apply a transfer learning model for tumor categorization of 3D MRI data. For performance evaluation, the BraTS 2017/2018 dataset is handled that involves high-grade glioma (HGG) and low-grade glioma (LGG) samples in four different sequences/phases. 3t2FTS-v2 is proposed to effectively transform the features from 3D to 2D space by using two textural features: first-order statistics (FOS) and gray level run length matrix (GLRLM). In 3t2FTS-v2, normalization analyses are assessed to be different from 3t2FTS to accurately transform the space information apart from the usage of GLRLM features. The ResNet50 architecture is preferred to fulfill the HGG/LGG classification due to its remarkable performance in tumor grading. As a result, for the classification of 3D data, the proposed model achieves a 99.64% accuracy by guiding the literature about the importance of 3t2FTS-v2 that can be utilized not only for tumor grading but also for whole brain tissue-based disease classification. [ABSTRACT FROM AUTHOR]

Most of the existing multi-lead electrocardiogram (ECG) detection methods are based on all 12 leads, which undoubtedly results in a large amount of calculation and is not suitable for the application in portable ECG detection systems. Moreover, the influence of different lead and heartbeat segment lengths on the detection is not clear. In this paper, a novel Genetic Algorithm-based ECG Leads and Segment Length Optimization (GA-LSLO) framework is proposed, aiming to automatically select the appropriate leads and input ECG length to achieve optimized cardiovascular disease detection. GA-LSLO extracts the features of each lead under different heartbeat segment lengths through the convolutional neural network and uses the genetic algorithm to automatically select the optimal combination of ECG leads and segment length. In addition, the lead attention module (LAM) is proposed to weight the features of the selected leads, which improves the accuracy of cardiac disease detection. The algorithm is validated on the ECG data from the Huangpu Branch of Shanghai Ninth People's Hospital (defined as the SH database) and the open-source Physikalisch-Technische Bundesanstalt diagnostic ECG database (PTB database). The accuracy for detection of arrhythmia and myocardial infarction under the inter-patient paradigm is 99.65% (95% confidence interval: 99.20–99.76%) and 97.62% (95% confidence interval: 96.80–98.16%), respectively. In addition, ECG detection devices are designed using Raspberry Pi, which verifies the convenience of hardware implementation of the algorithm. In conclusion, the proposed method achieves good cardiovascular disease detection performance. It selects the ECG leads and heartbeat segment length with the lowest algorithm complexity while ensuring classification accuracy, which is suitable for portable ECG detection devices. [ABSTRACT FROM AUTHOR]

Electroencephalogram (EEG) signals immensely suffer from several physiological artifacts, including electrooculogram (EOG), electromyogram (EMG), and electrocardiogram (ECG) artifacts, which must be removed to ensure EEG's usability. This paper proposes a novel one-dimensional convolutional neural network (1D-CNN), i.e., MultiResUNet3+, to denoise physiological artifacts from corrupted EEG. A publicly available dataset containing clean EEG, EOG, and EMG segments is used to generate semi-synthetic noisy EEG to train, validate and test the proposed MultiResUNet3+, along with four other 1D-CNN models (FPN, UNet, MCGUNet, LinkNet). Adopting a five-fold cross-validation technique, all five models' performance is measured by estimating temporal and spectral percentage reduction in artifacts, temporal and spectral relative root mean squared error, and average power ratio of each of the five EEG bands to whole spectra. The proposed MultiResUNet3+ achieved the highest temporal and spectral percentage reduction of 94.82% and 92.84%, respectively, in EOG artifacts removal from EOG-contaminated EEG. Moreover, compared to the other four 1D-segmentation models, the proposed MultiResUNet3+ eliminated 83.21% of the spectral artifacts from the EMG-corrupted EEG, which is also the highest. In most situations, our proposed model performed better than the other four 1D-CNN models, evident by the computed performance evaluation metrics. [ABSTRACT FROM AUTHOR]

The success of deep machine learning (DML) models in gaming and robotics has increased its trial in clinical and public healthcare solutions. In applying DML to healthcare problems, a special challenge of inadequate electrical energy and computing resources exists in regional and developing areas of the world. In this paper, we evaluate and report the computational and predictive performance design trade-offs for four candidate deep learning models that can be deployed for rapid malaria case finding. The goal is to maximise malaria detection accuracy while reducing computing resource and energy consumption. Based on our experimental results using a blood smear malaria test data set, the quantised versions of Basic Convolutional Neural Network (B-CNN) and MobileNetV2 have better malaria detection performance (up to 99% recall), lower memory usage (2MB 8-bit quantised model) and shorter inference time (33-95 microseconds on mobile phones) than VGG-19 fine-tuned and quantised models. Hence, we have implemented MobileNetV2 in our mobile application as it has even a lower memory requirement than B-CNN. This work will help to counter the negative effects of COVID-19 on the previous successes towards global malaria elimination. [ABSTRACT FROM AUTHOR]

Genitourinary syndrome of menopause (GSM) is a group of syndromes, including atrophy of the reproductive tract and urinary tract, and sexual dysfunction, caused by decreased levels of hormones, such as estrogen, in women during the transition to, or late stage of, menopause. GSM symptoms can gradually become severe with age and menopausal time, seriously affecting the safety, and physical and mental health, of patients. Optical coherence tomography (OCT) systems can obtain images similar to "optical slices" in a non-destructive manner. This paper presents a neural network, called RVM-GSM, to implement automatic classification tasks for different types of GSM-OCT images. The RVM-GSM module uses a convolutional neural network (CNN) and a vision transformer (ViT) to capture local and global features of the GSM-OCT images, respectively, and, then, fuses the two features in a multi-layer perception module to classify the image. In accordance with the practical needs of clinical work, lightweight post-processing is added to the final surface of the RVM-GSM module to compress the module. Experimental results showed that the accuracy rate of RVM-GSM in the GSM-OCT image classification task was 98.2%. This result is better than those of the CNN and Vit models, demonstrating the promise and potential of the application of RVM-GSM in the physical health and hygiene fields for women. [ABSTRACT FROM AUTHOR]

Recently, deep learning and the Internet of Things (IoT) have been widely used in the healthcare monitoring system for decision making. Disease prediction is one of the emerging applications in current practices. In the method described in this paper, lung cancer prediction is implemented using deep learning and IoT, which is a challenging task in computer-aided diagnosis (CAD). Because lung cancer is a dangerous medical disease that must be identified at a higher detection rate, disease-related information is obtained from IoT medical devices and transmitted to the server. The medical data are then processed and classified into two categories, benign and malignant, using a multi-layer CNN (ML-CNN) model. In addition, a particle swarm optimization method is used to improve the learning ability (loss and accuracy). This step uses medical data (CT scan and sensor information) based on the Internet of Medical Things (IoMT). For this purpose, sensor information and image information from IoMT devices and sensors are gathered, and then classification actions are taken. The performance of the proposed technique is compared with well-known existing methods, such as the Support Vector Machine (SVM), probabilistic neural network (PNN), and conventional CNN, in terms of accuracy, precision, sensitivity, specificity, F-score, and computation time. For this purpose, two lung datasets were tested to evaluate the performance: Lung Image Database Consortium (LIDC) and Linear Imaging and Self-Scanning Sensor (LISS) datasets. Compared to alternative methods, the trial outcomes showed that the suggested technique has the potential to help the radiologist make an accurate and efficient early lung cancer diagnosis. The performance of the proposed ML-CNN was analyzed using Python, where the accuracy (2.5–10.5%) was high when compared to the number of instances, precision (2.3–9.5%) was high when compared to the number of instances, sensitivity (2.4–12.5%) was high when compared to several instances, the F-score (2–30%) was high when compared to the number of cases, the error rate (0.7–11.5%) was low compared to the number of cases, and the computation time (170 ms to 400 ms) was low compared to how many cases were computed for the proposed work, including previous known methods. The proposed ML-CNN architecture shows that this technique outperforms previous works. [ABSTRACT FROM AUTHOR]

As an essential physiological indicator within the human body, noninvasive continuous blood pressure (BP) measurement is critical in the prevention and treatment of cardiovascular disease. However, traditional methods of blood pressure prediction using a single-wavelength Photoplethysmographic (PPG) have bottlenecks in further improving BP prediction accuracy, which limits their development in clinical application and dissemination. To this end, this study proposed a method to fuse a four-wavelength PPG and a BP prediction model based on the attention mechanism of a convolutional neural network and bidirectional long- and short-term memory (ACNN-BiLSTM). The effectiveness of a multi-wavelength PPG fusion method for blood pressure prediction was evaluated by processing PPG signals from 162 volunteers. The study compared the performance of the PPG signals with different individual wavelengths and using a multi-wavelength PPG fusion method in blood pressure prediction, assessed using mean absolute error (MAE), root mean squared error (RMSE) and AAMI-related criteria. The experimental results showed that the ACNN-BiLSTM model achieved a better MAE ± RMSE for a systolic BP and diastolic BP of 1.67 ± 5.28 and 1.15 ± 2.53 mmHg, respectively, when using the multi-wavelength PPG fusion method. As a result, the ACNN-BiLSTM blood pressure model based on multi-wavelength PPG fusion could be considered a promising method for noninvasive continuous BP measurement. [ABSTRACT FROM AUTHOR]

Ductal carcinoma in situ (DCIS) and breast cancer are common female breast diseases and pose a serious health threat to women. Early diagnosis of breast cancer and DCIS can help to develop targeted treatment plans in time. In this paper, we investigated the feasibility of using Raman spectroscopy combined with convolutional neural network (CNN) to discriminate between healthy volunteers, breast cancer and DCIS patients. Raman spectra were collected from the sera of 241 healthy volunteers, 463 breast cancer and 100 DCIS patients, and a total of 804 spectra were recorded. The pre-processed Raman spectra were used as the input of CNN to establish a model to classify the three different spectra. After using cross-validation to optimize its hyperparameters, the model's final classification performance was assessed using an unknown test set. For comparison with other machine learning algorithms, we additionally built models using support vector machine (SVM), random forest (RF) and k-nearest neighbor (KNN) methods. The final accuracies for CNN, SVM, RF and KNN were 98.76%, 94.63%, 80.99% and 78.93%, respectively. The values for area under curve (AUC) were 0.999, 0.994, 0.931 and 0.900, respectively. Therefore, our study results demonstrate that CNN outperforms three traditional algorithms in terms of classification performance for Raman spectral data and can be a useful auxiliary diagnostic tool of breast cancer and DCIS. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have been widely applied in the fields of medical tasks because they can achieve high accuracy in many fields using a large number of parameters and operations. However, many applications designed for auxiliary checks or help need to be deployed into portable devices, where the huge number of operations and parameters of a standard CNN can become an obstruction. MobileNet adopts a depthwise separable convolution to replace the standard convolution, which can greatly reduce the number of operations and parameters while maintaining a relatively high accuracy. Such highly structured models are very suitable for FPGA implementation in order to further reduce resource requirements and improve efficiency. Many other implementations focus on performance more than on resource requirements because MobileNets has already reduced both parameters and operations and obtained significant results. However, because many small devices only have limited resources they cannot run MobileNet-like efficient networks in a normal way, and there are still many auxiliary medical applications that require a high-performance network running in real-time to meet the requirements. Hence, we need to figure out a specific accelerator structure to further reduce the memory and other resource requirements while running MobileNet-like efficient networks. In this paper, a MobileNet accelerator is proposed to minimize the on-chip memory capacity and the amount of data that is transferred between on-chip and off-chip memory. We propose two configurable computing modules: Pointwise Convolution Accelerator and Depthwise Convolution Accelerator, to parallelize the network and reduce the memory requirement with a specific dataflow model. At the same time, a new cache usage method is also proposed to further reduce the use of the on-chip memory. We implemented the accelerator on Xilinx XC7Z020, deployed MobileNetV2 on it, and achieved 70.94 FPS with 524.25 KB on-chip memory usage under 150 MHz. [ABSTRACT FROM AUTHOR]

Apical Lesions, one of the most common oral diseases, can be effectively detected in daily dental examinations by a periapical radiograph (PA). In the current popular endodontic treatment, most dentists spend a lot of time manually marking the lesion area. In order to reduce the burden on dentists, this paper proposes a convolutional neural network (CNN)-based regional analysis model for spical lesions for periapical radiographs. In this study, the database was provided by dentists with more than three years of practical experience, meeting the criteria for clinical practical application. The contributions of this work are (1) an advanced adaptive threshold preprocessing technique for image segmentation, which can achieve an accuracy rate of more than 96%; (2) a better and more intuitive apical lesions symptom enhancement technique; and (3) a model for apical lesions detection with an accuracy as high as 96.21%. Compared with existing state-of-the-art technology, the proposed model has improved the accuracy by more than 5%. The proposed model has successfully improved the automatic diagnosis of apical lesions. With the help of automation, dentists can focus more on technical and medical diagnoses, such as treatment, tooth cleaning, or medical communication. This proposal has been certified by the Institutional Review Board (IRB) with the certification number 202002030B0. [ABSTRACT FROM AUTHOR]

Respiratory ailments are a very serious health issue and can be life-threatening, especially for patients with COVID. Respiration rate (RR) is a very important vital health indicator for patients. Any abnormality in this metric indicates a deterioration in health. Hence, continuous monitoring of RR can act as an early indicator. Despite that, RR monitoring equipment is generally provided only to intensive care unit (ICU) patients. Recent studies have established the feasibility of using photoplethysmogram (PPG) signals to estimate RR. This paper proposes a deep-learning-based end-to-end solution for estimating RR directly from the PPG signal. The system was evaluated on two popular public datasets: VORTAL and BIDMC. A lightweight model, ConvMixer, outperformed all of the other deep neural networks. The model provided a root mean squared error (RMSE), mean absolute error (MAE), and correlation coefficient (R) of 1.75 breaths per minute (bpm), 1.27 bpm, and 0.92, respectively, for VORTAL, while these metrics were 1.20 bpm, 0.77 bpm, and 0.92, respectively, for BIDMC. The authors also showed how fine-tuning a small subset could increase the performance of the model in the case of an out-of-distribution dataset. In the fine-tuning experiments, the models produced an average R of 0.81. Hence, this lightweight model can be deployed to mobile devices for real-time monitoring of patients. [ABSTRACT FROM AUTHOR]

Atrial fibrillation (AF) is one of the most common cardiac arrhythmias, and it is an indication of high-risk factors for stroke, myocardial ischemia, and other malignant cardiovascular diseases. Most of the existing AF detection methods typically convert one-dimensional time-series electrocardiogram (ECG) signals into two-dimensional representations to train a deep and complex AF detection system, which results in heavy training computation and high implementation costs. In this paper, a multiscale signal encoding scheme is proposed to improve feature representation and detection performance without the need for using any transformation or handcrafted feature engineering techniques. The proposed scheme uses different kernel sizes to produce the encoded signal by using multiple streams that are passed into a one-dimensional sequence of blocks of a residual convolutional neural network (ResNet) to extract representative features from the input ECG signal. This also allows networks to grow in breadth rather than in depth, thus reducing the computing time by using the parallel processing capability of deep learning networks. We investigated the effects of the use of a different number of streams with different kernel sizes on the performance. Experiments were carried out for a performance evaluation using the publicly available PhysioNet CinC Challenge 2017 dataset. The proposed multiscale encoding scheme outperformed existing deep learning-based methods with an average F1 score of 98.54%, but with a lower network complexity. [ABSTRACT FROM AUTHOR]

Given its essential role in body functions, liver cancer is the third most common cause of death from cancer, despite being the sixth most common type of cancer worldwide. Following advancements in medicine and image processing, medical image segmentation methods are receiving a great deal of attention. As a novelty, the paper proposes an intelligent decision system for segmenting liver and hepatic tumors by integrating four efficient neural networks (ResNet152, ResNeXt101, DenseNet201, and InceptionV3). Images from computed tomography for training, validation, and testing were taken from the public LiTS17 database and preprocessed to better highlight liver tissue and tumors. Global segmentation is done by separately training individual classifiers and the global system of merging individual decisions. For the aforementioned application, classification neural networks have been modified for semantic segmentation. After segmentation based on the neural network system, the images were postprocessed to eliminate artifacts. The segmentation results obtained by the system were better, from the point of view of the Dice coefficient, than those obtained by the individual networks, and comparable with those reported in recent works. [ABSTRACT FROM AUTHOR]

In recent years, many studies have proposed automatic detection and localization techniques for myocardial infarction (MI) using the 12-lead electrocardiogram (ECG). Most of them applied preprocessing to the ECG signals, e.g., noise removal, trend removal, beat segmentation, and feature selection, followed by model construction and classification based on machine-learning algorithms. The selection and implementation of preprocessing methods require specialized knowledge and experience to handle ECG data. In this paper, we propose an end-to-end convolutional neural network model that detects and localizes MI without such complicated multistep preprocessing. The proposed model executes comprehensive learning for the waveform features of unpreprocessed raw ECG images captured from 12-lead ECG signals. We evaluated the classification performance of the proposed model in two experimental settings: ten-fold cross-validation where ECG images were split randomly, and two-fold cross-validation where ECG images were split into one patient and the other patients. The experimental results demonstrate that the proposed model obtained MI detection accuracies of 99.82% and 93.93% and MI localization accuracies of 99.28% and 69.27% in the first and second settings, respectively. The performance of the proposed method is higher than or comparable to that of existing state-of-the-art methods. Thus, the proposed model is expected to be an effective MI diagnosis tool that can be used in intensive care units and as wearable technology. [ABSTRACT FROM AUTHOR]

Kidney cancer has several types, with renal cell carcinoma (RCC) being the most prevalent and severe type, accounting for more than 85% of adult patients. The manual analysis of whole slide images (WSI) of renal tissues is the primary tool for RCC diagnosis and prognosis. However, the manual identification of RCC is time-consuming and prone to inter-subject variability. In this paper, we aim to distinguish between benign tissue and malignant RCC tumors and identify the tumor subtypes to support medical therapy management. We propose a novel multiscale weakly-supervised deep learning approach for RCC subtyping. Our system starts by applying the RGB-histogram specification stain normalization on the whole slide images to eliminate the effect of the color variations on the system performance. Then, we follow the multiple instance learning approach by dividing the input data into multiple overlapping patches to maintain the tissue connectivity. Finally, we train three multiscale convolutional neural networks (CNNs) and apply decision fusion to their predicted results to obtain the final classification decision. Our dataset comprises four classes of renal tissues: non-RCC renal parenchyma, non-RCC fat tissues, clear cell RCC (ccRCC), and clear cell papillary RCC (ccpRCC). The developed system demonstrates a high classification accuracy and sensitivity on the RCC biopsy samples at the slide level. Following a leave-one-subject-out cross-validation approach, the developed RCC subtype classification system achieves an overall classification accuracy of 93.0% ± 4.9%, a sensitivity of 91.3% ± 10.7%, and a high classification specificity of 95.6% ± 5.2%, in distinguishing ccRCC from ccpRCC or non-RCC tissues. Furthermore, our method outperformed the state-of-the-art Resnet-50 model. [ABSTRACT FROM AUTHOR]

Breast cancer is a gigantic burden on humanity, causing the loss of enormous numbers of lives and amounts of money. It is the world's leading type of cancer among women and a leading cause of mortality and morbidity. The histopathological examination of breast tissue biopsies is the gold standard for diagnosis. In this paper, a computer-aided diagnosis (CAD) system based on deep learning is developed to ease the pathologist's mission. For this target, five pre-trained convolutional neural network (CNN) models are analyzed and tested—Xception, DenseNet201, InceptionResNetV2, VGG19, and ResNet152—with the help of data augmentation techniques, and a new approach is introduced for transfer learning. These models are trained and tested with histopathological images obtained from the BreakHis dataset. Multiple experiments are performed to analyze the performance of these models through carrying out magnification-dependent and magnification-independent binary and eight-class classifications. The Xception model has shown promising performance through achieving the highest classification accuracies for all the experiments. It has achieved a range of classification accuracies from 93.32% to 98.99% for magnification-independent experiments and from 90.22% to 100% for magnification-dependent experiments. [ABSTRACT FROM AUTHOR]

In ophthalmology, the registration problem consists of finding a geometric transformation that aligns a pair of images, supporting eye-care specialists who need to record and compare images of the same patient. Considering the registration methods for handling eye fundus images, the literature offers only a limited number of proposals based on deep learning (DL), whose implementations use the supervised learning paradigm to train a model. Additionally, ensuring high-quality registrations while still being flexible enough to tackle a broad range of fundus images is another drawback faced by most existing methods in the literature. Therefore, in this paper, we address the above-mentioned issues by introducing a new DL-based framework for eye fundus registration. Our methodology combines a U-shaped fully convolutional neural network with a spatial transformation learning scheme, where a reference-free similarity metric allows the registration without assuming any pre-annotated or artificially created data. Once trained, the model is able to accurately align pairs of images captured under several conditions, which include the presence of anatomical differences and low-quality photographs. Compared to other registration methods, our approach achieves better registration outcomes by just passing as input the desired pair of fundus images. [ABSTRACT FROM AUTHOR]

Brain signals can be captured via electroencephalogram (EEG) and be used in various brain–computer interface (BCI) applications. Classifying motor imagery (MI) using EEG signals is one of the important applications that can help a stroke patient to rehabilitate or perform certain tasks. Dealing with EEG-MI signals is challenging because the signals are weak, may contain artefacts, are dependent on the patient's mood and posture, and have low signal-to-noise ratio. This paper proposes a multi-branch convolutional neural network model called the Multi-Branch EEGNet with Convolutional Block Attention Module (MBEEGCBAM) using attention mechanism and fusion techniques to classify EEG-MI signals. The attention mechanism is applied both channel-wise and spatial-wise. The proposed model is a lightweight model that has fewer parameters and higher accuracy compared to other state-of-the-art models. The accuracy of the proposed model is 82.85% and 95.45% using the BCI-IV2a motor imagery dataset and the high gamma dataset, respectively. Additionally, when using the fusion approach (FMBEEGCBAM), it achieves 83.68% and 95.74% accuracy, respectively. [ABSTRACT FROM AUTHOR]

Laboratory medicine plays a fundamental role in the detection, diagnosis and management of COVID-19 infection. Recent observations of the morphology of cells circulating in blood found the presence of particular reactive lymphocytes (COVID-19 RL) in some of the infected patients and demonstrated that it was an indicator of a better prognosis of the disease. Visual morphological analysis is time consuming, requires smear review by expert clinical pathologists, and is prone to subjectivity. This paper presents a convolutional neural network system designed for automatic recognition of COVID-19 RL. It is based on the Xception71 structure and is trained using images of blood cells from real infected patients. An experimental study is carried out with a group of 92 individuals. The input for the system is a set of images selected by the clinical pathologist from the blood smear of a patient. The output is the prediction whether the patient belongs to the group associated with better prognosis of the disease. A threshold is obtained for the classification system to predict that the smear belongs to this group. With this threshold, the experimental test shows excellent performance metrics: 98.3% sensitivity and precision, 97.1% specificity, and 97.8% accuracy. The system does not require costly calculations and can potentially be integrated into clinical practice to assist clinical pathologists in a more objective smear review for early prognosis. [ABSTRACT FROM AUTHOR]

Cancer is the second leading cause of death globally, and breast cancer (BC) is the second most reported cancer. Although the incidence rate is reducing in developed countries, the reverse is the case in low- and middle-income countries. Early detection has been found to contain cancer growth, prevent metastasis, ease treatment, and reduce mortality by 25%. The digital mammogram is one of the most common, cheapest, and most effective BC screening techniques capable of early detection of up to 90% BC incidence. However, the mammogram is one of the most difficult medical images to analyze. In this paper, we present a method of training a deep learning model for BC diagnosis. We developed a discriminative fine-tuning method which dynamically assigns different learning rates to each layer of the deep CNN. In addition, the model was trained using mixed-precision training to ease the computational demand of training deep learning models. Lastly, we present data augmentation methods for mammograms. The discriminative fine-tuning algorithm enables rapid convergence of the model loss; hence, the models were trained to attain their best performance within 50 epochs. Comparing the results, DenseNet achieved the highest accuracy of 0.998, while AlexNet obtained 0.988. [ABSTRACT FROM AUTHOR]

This special issue of I Bioengineering i , entitled: "AI in MRI: Frontiers and Applications" focuses on the application of AI in magnetic resonance imaging (MRI), an area that has recently seen a surge of activity. Artificial intelligence (AI), machine learning, magnetic resonance imaging (MRI), deep learning, image reconstruction, segmentation, medical imaging, acceleration Keywords: artificial intelligence (AI); machine learning; magnetic resonance imaging (MRI); deep learning; image reconstruction; segmentation; medical imaging; acceleration EN artificial intelligence (AI) machine learning magnetic resonance imaging (MRI) deep learning image reconstruction segmentation medical imaging acceleration 492 9 05/02/23 20230401 NES 230401 Over the last decade, artificial intelligence (AI) has made an enormous impact on a wide range of fields, including science, engineering, informatics, finance, and transportation. [Extracted from the article]

The registration of preoperative and follow-up brain MRI, which is crucial in illustrating patients' responses to treatments and providing guidance for postoperative therapy, presents significant challenges. These challenges stem from the considerable deformation of brain tissue and the areas of non-correspondence due to surgical intervention and postoperative changes. We propose a stepwise corrected attention registration network grounded in convolutional neural networks (CNNs). This methodology leverages preoperative and follow-up MRI scans as fixed images and moving images, respectively, and employs a multi-level registration strategy that establishes a precise and holistic correspondence between images, from coarse to fine. Furthermore, our model introduces a corrected attention module into the multi-level registration network that can generate an attention map at the local level through the deformation fields of the upper-level registration network and pathological areas of preoperative images segmented by a mature algorithm in BraTS, serving to strengthen the registration accuracy of non-correspondence areas. A comparison between our scheme and the leading approach identified in the MICCAI's BraTS-Reg challenge indicates a 7.5% enhancement in the target registration error (TRE) metric and improved visualization of non-correspondence areas. These results illustrate the better performance of our stepwise corrected attention registration network in not only enhancing the registration accuracy but also achieving a more logical representation of non-correspondence areas. Thus, this work contributes significantly to the optimization of the registration of brain MRI between preoperative and follow-up scans. [ABSTRACT FROM AUTHOR]

The task of localizing distinct anatomical structures in medical image data is an essential prerequisite for several medical applications, such as treatment planning in orthodontics, bone-age estimation, or initialization of segmentation methods in automated image analysis tools. Currently, Anatomical Landmark Localization (ALL) is mainly solved by deep-learning methods, which cannot guarantee robust ALL predictions; there may always be outlier predictions that are far from their ground truth locations due to out-of-distribution inputs. However, these localization outliers are detrimental to the performance of subsequent medical applications that rely on ALL results. The current ALL literature relies heavily on implicit anatomical constraints built into the loss function and network architecture to reduce the risk of anatomically infeasible predictions. However, we argue that in medical imaging, where images are generally acquired in a controlled environment, we should use stronger explicit anatomical constraints to reduce the number of outliers as much as possible. Therefore, we propose the end-to-end trainable Global Anatomical Feasibility Filter and Analysis (GAFFA) method, which uses prior anatomical knowledge estimated from data to explicitly enforce anatomical constraints. GAFFA refines the initial localization results of a U-Net by approximately solving a Markov Random Field (MRF) with a single iteration of the sum-product algorithm in a differentiable manner. Our experiments demonstrate that GAFFA outperforms all other landmark refinement methods investigated in our framework. Moreover, we show that GAFFA is more robust to large outliers than state-of-the-art methods on the studied X-ray hand dataset. We further motivate this claim by visualizing the anatomical constraints used in GAFFA as spatial energy heatmaps, which allowed us to find an annotation error in the hand dataset not previously discussed in the literature. [ABSTRACT FROM AUTHOR]

Early diagnosis of paroxysmal atrial fibrillation (PAF) could prompt patients to receive timely interventions in clinical practice. Various PAF onset prediction algorithms might benefit from accurate heart rate variability (HRV) analysis and machine learning classification but are challenged by real-time monitoring scenarios. The aim of this study is to present an end-to-end deep learning-based PAFNet model that integrates a sliding window technique on raw R-R intervals of electrocardiogram (ECG) segments to achieve a real-time prediction of PAF onset. This integration enables the deep convolutional neural network (CNN) to be customized as a light-weight architecture that accommodates the size of sliding windows simply by altering the input layer, and specifically its effectiveness in making a new prediction with each new heartbeat. Catering to the potential influence of input sizes, three CNN models were trained using 50, 100, and 200 R-R intervals, respectively. For each model, the performance of the automated algorithms was evaluated for PAF prediction using a ten-fold cross-validation. As a results, a total of 56,381 PAFN-type and 56,900 N-type R-R interval segments were collected from publicly accessible ECG databases, and a promising prediction performance of the automated algorithm with 100 R-R intervals was achieved, with a sensitivity of 97.12%, a specificity of 97.77%, and an accuracy of 97.45%, respectively. Importantly, the automated algorithm with a sliding window step of 1 could process one sample in only 23.1 milliseconds and identify the onset of PAF at least 45 min in advance. The present results suggest that the sliding window technique on raw R-R interval sequences, along with deep learning-based algorithms, may offer the possibility of providing an accurate, real-time, end-to-end clinical tool for mass monitoring of PAF. [ABSTRACT FROM AUTHOR]

Anterior cruciate ligament (ACL) plays an important role in stabilising the knee joint, prevents excessive anterior translation of the tibia, and provides rotational stability. ACL injuries commonly occur as a result of rapid deceleration, sudden change in direction, or direct impact to the knee during sports activities. Although several deep learning techniques have recently been applied in the detection of ACL tears, challenges such as effective slice filtering and the nuanced relationship between varying tear grades still remain underexplored. This study used an advanced deep learning model that integrated a T-distribution-based slice attention filtering mechanism with a penalty weight loss function to improve the performance for detection of ACL tears. A T-distribution slice attention module was effectively utilised to develop a robust slice filtering system of the deep learning model. By incorporating class relationships and substituting the conventional cross-entropy loss with a penalty weight loss function, the classification accuracy of our model is markedly increased. The combination of slice filtering and penalty weight loss shows significant improvements in diagnostic performance across six different backbone networks. In particular, the VGG-Slice-Weight model provided an area score of 0.9590 under the receiver operating characteristic curve (AUC). The deep learning framework used in this study offers an effective diagnostic tool that supports better ACL injury detection in clinical diagnosis practice. [ABSTRACT FROM AUTHOR]

An apical lesion is caused by bacteria invading the tooth apex through caries. Periodontal disease is caused by plaque accumulation. Peri-endo combined lesions include both diseases and significantly affect dental prognosis. The lack of clear symptoms in the early stages of onset makes diagnosis challenging, and delayed treatment can lead to the spread of symptoms. Early infection detection is crucial for preventing complications. PAs used as the database were provided by Chang Gung Memorial Medical Center, Taoyuan, Taiwan, with permission from the Institutional Review Board (IRB): 02002030B0. The tooth apex image enhancement method is a new technology in PA detection. This image enhancement method is used with convolutional neural networks (CNN) to classify apical lesions, peri-endo combined lesions, and asymptomatic cases, and to compare with You Only Look Once-v8-Oriented Bounding Box (YOLOv8-OBB) disease detection results. The contributions lie in the utilization of database augmentation and adaptive histogram equalization on individual tooth images, achieving the highest comprehensive validation accuracy of 95.23% with the ConvNextv2 model. Furthermore, the CNN outperformed YOLOv8 in identifying apical lesions, achieving an F1-Score of 92.45%. For the classification of peri-endo combined lesions, CNN attained the highest F1-Score of 96.49%, whereas YOLOv8 scored 88.49%. [ABSTRACT FROM AUTHOR]

Genetic disorders affect over 6% of the global population and pose substantial obstacles to healthcare systems. Early identification of these rare facial genetic disorders is essential for managing related medical complexities and health issues. Many people consider the existing screening techniques inadequate, often leading to a diagnosis several years after birth. This study evaluated the efficacy of deep learning-based classifier models for accurately recognizing dysmorphic characteristics using facial photos. This study proposes a multi-class facial syndrome classification framework that encompasses a unique combination of diseases not previously examined together. The study focused on distinguishing between individuals with four specific genetic disorders (Down syndrome, Noonan syndrome, Turner syndrome, and Williams syndrome) and healthy controls. We investigated how well fine-tuning a few well-known convolutional neural network (CNN)-based pre-trained models—including VGG16, ResNet-50, ResNet152, and VGG-Face—worked for the multi-class facial syndrome classification task. We obtained the most encouraging results by adjusting the VGG-Face model. The proposed fine-tuned VGG-Face model not only demonstrated the best performance in this study, but it also performed better than other state-of-the-art pre-trained CNN models for the multi-class facial syndrome classification task. The fine-tuned model achieved both accuracy and an F1-Score of 90%, indicating significant progress in accurately detecting the specified genetic disorders. [ABSTRACT FROM AUTHOR]