Search

This study evaluates the efficacy of several Convolutional Neural Network (CNN) models for the classification of hearing loss in patients using preprocessed auditory brainstem response (ABR) image data. Specifically, we employed six CNN architectures—VGG16, VGG19, DenseNet121, DenseNet-201, AlexNet, and InceptionV3—to differentiate between patients with hearing loss and those with normal hearing. A dataset comprising 7990 preprocessed ABR images was utilized to assess the performance and accuracy of these models. Each model was systematically tested to determine its capability to accurately classify hearing loss. A comparative analysis of the models focused on metrics of accuracy and computational efficiency. The results indicated that the AlexNet model exhibited superior performance, achieving an accuracy of 95.93%. The findings from this research suggest that deep learning models, particularly AlexNet in this instance, hold significant potential for automating the diagnosis of hearing loss using ABR graph data. Future work will aim to refine these models to enhance their diagnostic accuracy and efficiency, fostering their practical application in clinical settings. [ABSTRACT FROM AUTHOR]

Introduction: The scapholunate interosseous ligament is pivotal for wrist stability, and its impairment can result in instability and joint degeneration. This study explores the application of real-time MRI for dynamic assessment of the scapholunate joint during wrist motion with the objective of determining its diagnostic value in efficacy in contrast to static imaging modalities. Materials and Methods: Ten healthy participants underwent real-time MRI scans during wrist ab/adduction and fist-clenching maneuvers. Measurements were obtained at proximal, medial, and distal landmarks on both dynamic and static images with statistical analyses conducted to evaluate the reliability of measurements at each landmark and the concordance between dynamic measurements and established static images. Additionally, inter- and intraobserver variabilities were evaluated. Results: Measurements of the medial landmarks demonstrated the closest agreement with static images and exhibited the least scatter. Distal landmark measurements showed a similar level of agreement but with increased scatter. Proximal landmark measurements displayed substantial deviation, which was accompanied by an even greater degree of scatter. Although no significant differences were observed between the ab/adduction and fist-clenching maneuvers, both inter- and intraobserver variabilities were significant across all measurements. Conclusions: This study highlights the potential of real-time MRI in the dynamic assessment of the scapholunate joint particularly at the medial landmark. Despite promising results, challenges such as measurement variability need to be addressed. Standardization and integration with advanced image processing methods could significantly enhance the accuracy and reliability of real-time MRI, paving the way for its clinical implementation in dynamic wrist imaging studies. [ABSTRACT FROM AUTHOR]

Stroke management employs a variety of diagnostic imaging modalities, image processing and analysis methods, and treatment procedures. This work categorizes methods for stroke imaging, image processing and analysis, and treatment, and provides their taxonomies illustrated by a state-of-the-art review. Imaging plays a critical role in stroke management, and the most frequently employed modalities are computed tomography (CT) and magnetic resonance (MR). CT includes unenhanced non-contrast CT as the first-line diagnosis, CT angiography, and CT perfusion. MR is the most complete method to examine stroke patients. MR angiography is useful to evaluate the severity of artery stenosis, vascular occlusion, and collateral flow. Diffusion-weighted imaging is the gold standard for evaluating ischemia. MR perfusion-weighted imaging assesses the penumbra. The stroke image processing methods are divided into non-atlas/template-based and atlas/template-based. The non-atlas/template-based methods are subdivided into intensity and contrast transformations, local segmentation-related, anatomy-guided, global density-guided, and artificial intelligence/deep learning-based. The atlas/template-based methods are subdivided into intensity templates and atlases with three atlas types: anatomy atlases, vascular atlases, and lesion-derived atlases. The treatment procedures for arterial and venous strokes include intravenous and intraarterial thrombolysis and mechanical thrombectomy. This work captures the state-of-the-art in stroke management summarized in the form of comprehensive and straightforward taxonomy diagrams. All three introduced taxonomies in diagnostic imaging, image processing and analysis, and treatment are widely illustrated and compared against other state-of-the-art classifications. [ABSTRACT FROM AUTHOR]

Merkel cell carcinoma (MCC) is recognized as one of the most malignant skin tumors. Its rarity might explain the limited exploration of digital color studies in this area. The objective of this study was to delineate color alterations in MCCs compared to benign lesions resembling MCC, such as cherry angiomas and hemangiomas, along with other non-melanoma skin cancer lesions like basal cell carcinoma (BCC) and squamous cell carcinoma (SCC), utilizing computer-aided digital color analysis. This was a retrospective study where clinical images of the color of the lesion and adjacent normal skin from 11 patients with primary MCC, 11 patients with cherry angiomas, 12 patients with hemangiomas, and 12 patients with BCC/SCC (totaling 46 patients) were analyzed using the RGB (red, green, and blue) and the CIE Lab color system. The Lab color system aided in estimating the Individual Typology Angle (ITA) change in the skin, and these results are documented in this study. It was demonstrated that the estimation of color components can assist in the differential diagnosis of these types of lesions because there were significant differences in color parameters between MCC and other categories of skin lesions such as hemangiomas, common skin carcinomas, and cherry hemangiomas. Significant differences in values were observed in the blue color of RGB (p = 0.003) and the b* parameter of Lab color (p < 0.0001) of MCC versus cherry angiomas. Similarly, the mean a* value of Merkel cell carcinoma (MCC) compared to basal cell carcinoma and squamous cell carcinoma showed a statistically significant difference (p < 0.0001). Larger prospective studies are warranted to further validate the clinical application of these findings. [ABSTRACT FROM AUTHOR]

Artificial Intelligence (AI) has revolutionized medical imaging procedures, specifically with regard to image segmentation, reconstruction, interpretation, and research. 3D Slicer, an open-source medical image analysis platform, has become a valuable tool in medical imaging education due to its integration of various AI applications. Through its open-source architecture, students can gain practical experience with diverse medical images and the latest AI technology, reinforcing their understanding of anatomy and imaging technology while fostering independent learning and clinical reasoning skills. The implementation of this platform improves instruction quality and nurtures skilled professionals who can meet the demands of clinical practice, research institutions, and technology innovation enterprises. AI algorithms' application in medical image processing have facilitated their translation from the lab to practical clinical applications and education. [ABSTRACT FROM AUTHOR]

To develop diagnostic imaging approaches, this paper emphasizes the transformational potential of merging geophysics with health sciences. Diagnostic imaging technology improvements have transformed the health sciences by enabling earlier and more precise disease identification, individualized therapy, and improved patient care. This review article examines the connection between geophysics and diagnostic imaging in the field of health sciences. Geophysics, which is typically used to explore Earth's subsurface, has provided new uses of its methodology in the medical field, providing innovative solutions to pressing medical problems. The article examines the different geophysical techniques like electrical imaging, seismic imaging, and geophysics and their corresponding imaging techniques used in health sciences like tomography, magnetic resonance imaging, ultrasound imaging, etc. The examination includes the description, similarities, differences, and challenges associated with these techniques and how modified geophysical techniques can be used in imaging methods in health sciences. Examining the progression of each method from geophysics to medical imaging and its contributions to illness diagnosis, treatment planning, and monitoring are highlighted. Also, the utilization of geophysical data analysis techniques like signal processing and inversion techniques in image processing in health sciences has been briefly explained, along with different mathematical and computational tools in geophysics and how they can be implemented for image processing in health sciences. The key findings include the development of machine learning and artificial intelligence in geophysics-driven medical imaging, demonstrating the revolutionary effects of data-driven methods on precision, speed, and predictive modeling. [ABSTRACT FROM AUTHOR]

The article discusses the advancements in the medical field through the use of artificial intelligence (AI), machine learning (ML), and other cutting-edge technologies. It highlights the potential of these technologies in various areas of medicine, including radiology, lung cancer, brain tumors, breast cancer, Alzheimer's disease, diabetic retinopathy, knee osteoarthritis, and cardiovascular disorders. The article emphasizes the importance of human expertise and oversight in the diagnostic process, as AI should not replace medical professionals. The research articles included in the special edition cover a range of topics and contribute to the growing body of knowledge in this field. [Extracted from the article]

One of the most frequently detected neoplasms in women in Italy is breast cancer, for which high-sensitivity diagnostic techniques are essential for early diagnosis in order to minimize mortality rates. As addressed in Part I of this work, we have seen how conditions such as high glandular density or limitations related to mammographic sensitivity have driven the optimization of technology and the use of increasingly advanced and specific diagnostic methodologies. While the first part focused on analyzing the use of a mammography machine from a physical and dosimetric perspective, in this paper, we will examine other techniques commonly used in breast imaging: contrast-enhanced mammography, digital breast tomosynthesis, radio imaging, and include some notes on image processing. We will also explore the differences between these various techniques to provide a comprehensive overview of breast lesion detection techniques. We will examine the strengths and weaknesses of different diagnostic modalities and observe how, with the implementation of improvements over time, increasingly effective diagnoses can be achieved. [ABSTRACT FROM AUTHOR]

Auditory brainstem response (ABR) is the response of the brain stem through the auditory nerve. The ABR test is a method of testing for loss of hearing through electrical signals. Basically, the test is conducted on patients such as the elderly, the disabled, and infants who have difficulty in communication. This test has the advantage of being able to determine the presence or absence of objective hearing loss by brain stem reactions only, without any communication. This paper proposes the image preprocessing process required to construct an efficient graph image data set for deep learning models using auditory brainstem response data. To improve the performance of the deep learning model, we standardized the ABR image data measured on various devices with different forms. In addition, we applied the VGG16 model, a CNN-based deep learning network model developed by a research team at the University of Oxford, using preprocessed ABR data to classify the presence or absence of hearing loss and analyzed the accuracy of the proposed method. This experimental test was performed using 10,000 preprocessed data, and the model was tested with various weights to verify classification learning. Based on the learning results, we believe it is possible to help set the criteria for preprocessing and the learning process in medical graph data, including ABR graph data. [ABSTRACT FROM AUTHOR]

Thorax disease is a life-threatening disease caused by bacterial infections that occur in the lungs. It could be deadly if not treated at the right time, so early diagnosis of thoracic diseases is vital. The suggested study can assist radiologists in more swiftly diagnosing thorax disorders and in the rapid airport screening of patients with a thorax disease, such as pneumonia. This paper focuses on automatically detecting and localizing thorax disease using chest X-ray images. It provides accurate detection and localization using DenseNet-121 which is foundation of our proposed framework, called Z-Net. The proposed framework utilizes the weighted cross-entropy loss function (W-CEL) that manages class imbalance issue in the ChestX-ray14 dataset, which helped in achieving the highest performance as compared to the previous models. The 112,120 images contained in the ChestX-ray14 dataset (60,412 images are normal, and the rest contain thorax diseases) were preprocessed and then trained for classification and localization. This work uses computer-aided diagnosis (CAD) system that supports development of highly accurate and precise computer-aided systems. We aim to develop a CAD system using a deep learning approach. Our quantitative results show high AUC scores in comparison with the latest research works. The proposed approach achieved the highest mean AUC score of 85.8%. This is the highest accuracy documented in the literature for any related model. [ABSTRACT FROM AUTHOR]

Human skin cancer is the most common and potentially life-threatening form of cancer. Melanoma skin cancer, in particular, exhibits a high mortality rate. Early detection is crucial for effective treatment. Traditionally, melanoma is detected through painful and time-consuming biopsies. This research introduces a computer-aided detection technique for early melanoma diagnosis-sis. In this study, we propose two methods for detecting skin cancer and focus specifically on melanoma cancerous cells using image data. The first method employs convolutional neural networks, including AlexNet, LeNet, and VGG-16 models, and we integrate the model with the highest accuracy into web and mobile applications. We also investigate the relationship between model depth and performance with varying dataset sizes. The second method uses support vector machines with a default RBF kernel, using feature parameters to categorize images as benign, malignant, or normal after image processing. The SVM classifier achieved an 86.6% classification accuracy, while the CNN maintained a 91% accuracy rate after 100 compute epochs. The CNN model is deployed as a web and mobile application with the assistance of Django and Android Studio. [ABSTRACT FROM AUTHOR]

Objectives: Hip MRI using standard multiplanar sequences requires long scan times. Accelerating MRI is accompanied by reduced image quality. This study aimed to compare standard two-dimensional (2D) turbo spin echo (TSE) sequences with accelerated 2D TSE sequences with deep learning (DL) reconstruction (TSEDL) for routine clinical hip MRI at 1.5 and 3 T in terms of feasibility, image quality, and diagnostic performance. Material and Methods: In this prospective, monocentric study, TSEDL was implemented clinically and evaluated in 14 prospectively enrolled patients undergoing a clinically indicated hip MRI at 1.5 and 3T between October 2020 and May 2021. Each patient underwent two examinations: For the first exam, we used standard sequences with generalized autocalibrating partial parallel acquisition reconstruction (TSES). For the second exam, we implemented prospectively undersampled TSE sequences with DL reconstruction (TSEDL). Two radiologists assessed the TSEDL and TSES regarding image quality, artifacts, noise, edge sharpness, diagnostic confidence, and delineation of anatomical structures using an ordinal five-point Likert scale (1 = non-diagnostic; 2 = poor; 3 = moderate; 4 = good; 5 = excellent). Both sequences were compared regarding the detection of common pathologies of the hip. Comparative analyses were conducted to assess the differences between TSEDL and TSES. Results: Compared with TSES, TSEDL was rated to be significantly superior in terms of image quality (p ≤ 0.020) with significantly reduced noise (p ≤ 0.001) and significantly improved edge sharpness (p = 0.003). No difference was found between TSES and TSEDL concerning the extent of artifacts, diagnostic confidence, or the delineation of anatomical structures (p > 0.05). Example acquisition time reductions for the TSE sequences of 52% at 3 Tesla and 70% at 1.5 Tesla were achieved. Conclusion: TSEDL of the hip is clinically feasible, showing excellent image quality and equivalent diagnostic performance compared with TSES, reducing the acquisition time significantly. [ABSTRACT FROM AUTHOR]

Contemporary personalized cancer diagnostic approaches encounter multiple challenges. The presence of cellular and molecular heterogeneity in patient samples introduces complexities to analysis protocols. Conventional analyses are manual, reliant on expert personnel, time-intensive, and financially burdensome. The copious data amassed for subsequent analysis strains the system, obstructing real-time diagnostics at the "point of care" and impeding prompt intervention. This study introduces PTOLEMI: Python-based Tensor Oncological Locator Examining Microfluidic Instruments. PTOLEMI stands out as a specialized system designed for high-throughput image analysis, particularly in the realm of microfluidic assays. Utilizing a blend of machine learning algorithms, PTOLEMI can process large datasets rapidly and with high accuracy, making it feasible for point-of-care diagnostics. Furthermore, its advanced analytics capabilities facilitate a more granular understanding of cellular dynamics, thereby allowing for more targeted and effective treatment options. Leveraging cutting-edge AI algorithms, PTOLEMI rapidly and accurately discriminates between cell viability and distinct cell types within biopsy samples. The diagnostic process becomes automated, swift, precise, and resource-efficient, rendering it well-suited for point-of-care requisites. By employing PTOLEMI alongside a microfluidic cell culture chip, physicians can attain personalized diagnostic and therapeutic insights. This paper elucidates the evolution of PTOLEMI and showcases its prowess in analyzing cancer patient samples within a microfluidic apparatus. While the integration of machine learning tools into biomedical domains is undoubtedly in progress, this study's innovation lies in the fusion of PTOLEMI with a microfluidic platform—an integrated, rapid, and independent framework for personalized drug screening-based clinical decision-making. [ABSTRACT FROM AUTHOR]

Multiple sclerosis (MS) is a chronic autoimmune disease of the central nervous system that prominently affects young adults due to its debilitating nature. The pathogenesis of the disease is focused on the inflammation and neurodegeneration processes. Inflammation is associated with relapses, while neurodegeneration emerges in the progressive stages of the disease. Magnetic resonance imaging (MRI) is commonly used for the diagnosis of MS, and guidelines such as the McDonald criteria are available. MRI is an essential tool to demonstrate the spatial distribution and changes over time in the disease. This study discusses the use of image processing techniques for the diagnosis of MS and specifically combines the MobileNetV2 network with exemplar-based learning, IMrMr feature selection, and K-Nearest Neighbors (KNN) classification methods. Experiments conducted on two different datasets (Dataset 1 and Dataset 2) demonstrate that these methods provide high accuracy in diagnosing MS. Dataset 1 comprises 128 patients with 706 MRI images, 131 MS patients with 667 MRI images, and 150 healthy control subjects with 1373 MRI images. Dataset 2 includes an MS group with 650 MRI images and a healthy control group with 676 MRI images. The results of the study include 10-fold cross-validation results performed on different image sections (Axial, Sagittal, and Hybrid) for Dataset 1. Accuracy rates of 99.76% for Axial, 99.48% for Sagittal, and 98.02% for Hybrid sections were achieved. Furthermore, 100% accuracy was achieved on Dataset 2. In conclusion, this study demonstrates the effective use of powerful image processing methods such as the MobileNetV2 network and exemplar-based learning for the diagnosis of MS. These findings suggest that these methods can be further developed in future research and offer significant potential for clinical applications in the diagnosis and monitoring of MS. [ABSTRACT FROM AUTHOR]

Our research focused on creating an advanced machine-learning algorithm that accurately detects anomalies in chest X-ray images to provide healthcare professionals with a reliable tool for diagnosing various lung conditions. To achieve this, we analysed a vast collection of X-ray images and utilised sophisticated visual analysis techniques; such as deep learning (DL) algorithms, object recognition, and categorisation models. To create our model, we used a large training dataset of chest X-rays, which provided valuable information for visualising and categorising abnormalities. We also utilised various data augmentation methods; such as scaling, rotation, and imitation; to increase the diversity of images used for training. We adopted the widely used You Only Look Once (YOLO) v8 algorithm, an object recognition paradigm that has demonstrated positive outcomes in computer vision applications, and modified it to classify X-ray images into distinct categories; such as respiratory infections, tuberculosis (TB), and lung nodules. It was particularly effective in identifying unique and crucial outcomes that may, otherwise, be difficult to detect using traditional diagnostic methods. Our findings demonstrate that healthcare practitioners can reliably use machine learning (ML) algorithms to diagnose various lung disorders with greater accuracy and efficiency. [ABSTRACT FROM AUTHOR]

Lumbar spine stenosis (LSS) is caused by low back pain that exerts pressure on the nerves in the spine. Detecting LSS is a significantly important yet difficult task. It is detected by analyzing the area of the anteroposterior diameter of the patient's lumbar spine. Currently, the versatility and accuracy of LSS segmentation algorithms are limited. The objective of this research is to use magnetic resonance imaging (MRI) to automatically categorize LSS. This study presents a convolutional neural network (CNN)-based method to detect LSS using MRI images. Radiological grading is performed on a publicly available dataset. Four regions of interest (ROIs) are determined to diagnose LSS with normal, mild, moderate, and severe gradings. The experiments are performed on 1545 axial-view MRI images. Furthermore, two datasets—multi-ROI and single-ROI—are created. For training and testing, an 80:20 ratio of randomly selected labeled datasets is used, with fivefold cross-validation. The results of the proposed model reveal a 97.01% accuracy for multi-ROI and 97.71% accuracy for single-ROI. The proposed computer-aided diagnosis approach can significantly improve diagnostic accuracy in everyday clinical workflows to assist medical experts in decision making. The proposed CNN-based MRI image segmentation approach shows its efficacy on a variety of datasets. Results are compared to existing state-of-the-art studies, indicating the superior performance of the proposed approach. [ABSTRACT FROM AUTHOR]

Background: Using artificial intelligence (AI) with the concept of a deep learning-based automated computer-aided diagnosis (CAD) system has shown improved performance for skin lesion classification. Although deep convolutional neural networks (DCNNs) have significantly improved many image classification tasks, it is still difficult to accurately classify skin lesions because of a lack of training data, inter-class similarity, intra-class variation, and the inability to concentrate on semantically significant lesion parts. Innovations: To address these issues, we proposed an automated deep learning and best feature selection framework for multiclass skin lesion classification in dermoscopy images. The proposed framework performs a preprocessing step at the initial step for contrast enhancement using a new technique that is based on dark channel haze and top–bottom filtering. Three pre-trained deep learning models are fine-tuned in the next step and trained using the transfer learning concept. In the fine-tuning process, we added and removed a few additional layers to lessen the parameters and later selected the hyperparameters using a genetic algorithm (GA) instead of manual assignment. The purpose of hyperparameter selection using GA is to improve the learning performance. After that, the deeper layer is selected for each network and deep features are extracted. The extracted deep features are fused using a novel serial correlation-based approach. This technique reduces the feature vector length to the serial-based approach, but there is little redundant information. We proposed an improved anti-Lion optimization algorithm for the best feature selection to address this issue. The selected features are finally classified using machine learning algorithms. Main Results: The experimental process was conducted using two publicly available datasets, ISIC2018 and ISIC2019. Employing these datasets, we obtained an accuracy of 96.1 and 99.9%, respectively. Comparison was also conducted with state-of-the-art techniques and shows the proposed framework improved accuracy. Conclusions: The proposed framework successfully enhances the contrast of the cancer region. Moreover, the selection of hyperparameters using the automated techniques improved the learning process of the proposed framework. The proposed fusion and improved version of the selection process maintains the best accuracy and shorten the computational time. [ABSTRACT FROM AUTHOR]

Objective: The objective of this study was to evaluate a deep learning (DL) reconstruction for turbo spin echo (TSE) sequences of the elbow regarding image quality and visualization of anatomy. Materials and Methods: Between October 2020 and June 2021, seventeen participants (eight patients, nine healthy subjects; mean age: 43 ± 16 (20–70) years, eight men) were prospectively included in this study. Each patient underwent two examinations: standard MRI, including TSE sequences reconstructed with a generalized autocalibrating partial parallel acquisition reconstruction (TSESTD), and prospectively undersampled TSE sequences reconstructed with a DL reconstruction (TSEDL). Two radiologists evaluated the images concerning image quality, noise, edge sharpness, artifacts, diagnostic confidence, and delineation of anatomical structures using a 5-point Likert scale, and rated the images concerning the detection of common pathologies. Results: Image quality was significantly improved in TSEDL (mean 4.35, IQR 4–5) compared to TSESTD (mean 3.76, IQR 3–4, p = 0.008). Moreover, TSEDL showed decreased noise (mean 4.29, IQR 3.5–5) compared to TSESTD (mean 3.35, IQR 3–4, p = 0.004). Ratings for delineation of anatomical structures, artifacts, edge sharpness, and diagnostic confidence did not differ significantly between TSEDL and TSESTD (p > 0.05). Inter-reader agreement was substantial to almost perfect (κ = 0.628–0.904). No difference was found concerning the detection of pathologies between the readers and between TSEDL and TSESTD. Using DL, the acquisition time could be reduced by more than 35% compared to TSESTD. Conclusion: TSEDL provided improved image quality and decreased noise while receiving equal ratings for edge sharpness, artifacts, delineation of anatomical structures, diagnostic confidence, and detection of pathologies compared to TSESTD. Providing more than a 35% reduction of acquisition time, TSEDL may be clinically relevant for elbow imaging due to increased patient comfort and higher patient throughput. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have been extensively utilized in medical image processing to automatically extract meaningful features and classify various medical conditions, enabling faster and more accurate diagnoses. In this paper, LeNet, a classic CNN architecture, has been successfully applied to breast cancer data analysis. It demonstrates its ability to extract discriminative features and classify malignant and benign tumors with high accuracy, thereby supporting early detection and diagnosis of breast cancer. LeNet with corrected Rectified Linear Unit (ReLU), a modification of the traditional ReLU activation function, has been found to improve the performance of LeNet in breast cancer data analysis tasks via addressing the "dying ReLU" problem and enhancing the discriminative power of the extracted features. This has led to more accurate, reliable breast cancer detection and diagnosis and improved patient outcomes. Batch normalization improves the performance and training stability of small and shallow CNN architecture like LeNet. It helps to mitigate the effects of internal covariate shift, which refers to the change in the distribution of network activations during training. This classifier will lessen the overfitting problem and reduce the running time. The designed classifier is evaluated against the benchmarking deep learning models, proving that this has produced a higher recognition rate. The accuracy of the breast image recognition rate is 89.91%. This model will achieve better performance in segmentation, feature extraction, classification, and breast cancer tumor detection. [ABSTRACT FROM AUTHOR]

In recent times, there has been a huge increase in the average number of cases of skin cancer per year, which sometimes become life threatening for humans. Early detection of various skin diseases through automated detection techniques plays a crucial role. However, the presence of numerous artefacts makes this task challenging. Dermoscopic images exhibit various variations, including hair artefacts, markers, and ill-defined boundaries. These artefacts make automatic analysis of skin lesion quite a difficult task. To address these issues, it is essential to have an accurate and efficient automated method which will delineate a skin lesion from the rest of the image. Unfortunately, due to the presence of several types of skin artefacts, there is no such thresholding method that can provide a sufficient segmentation result for every type of skin lesion. To overcome this limitation, an ensemble-based method is proposed that selects the optimal thresholding based on an objective function. A group of state-of-the-art different thresholding methods such as Otsu, Kapur, Harris hawk, and grey level are used. The proposed method obtained superior results (dice score = 0.89 with p-value ≤ 0.05) as compared to other state-of-the-art methods (Otsu = 0.79, Kapur = 0.80, Harris hawk = 0.60, grey level = 0.69, active contour model = 0.72). The experiments conducted in this study utilize the ISIC 2016 dataset, which is publicly available and specifically designed for skin-related research. Accurate segmentation will help in the early detection of many skin diseases. [ABSTRACT FROM AUTHOR]

Computed tomography (CT) scans, or radiographic images, were used to aid in the early diagnosis of patients and detect normal and abnormal lung function in the human chest. However, the diagnosis of lungs infected with coronavirus disease 2019 (COVID-19) was made more accurately from CT scan data than from a swab test. This study uses human chest radiography pictures to identify and categorize normal lungs, lung opacities, COVID-19-infected lungs, and viral pneumonia (often called pneumonia). In the past, several CAD systems using image processing, ML/DL, and other forms of machine learning have been developed. However, those CAD systems did not provide a general solution, required huge hyper-parameters, and were computationally inefficient to process huge datasets. Moreover, the DL models required high computational complexity, which requires a huge memory cost, and the complexity of the experimental materials' backgrounds, which makes it difficult to train an efficient model. To address these issues, we developed the Inception module, which was improved to recognize and detect four classes of Chest X-ray in this research by substituting the original convolutions with an architecture based on modified-Xception (m-Xception). In addition, the model incorporates depth-separable convolution layers within the convolution layer, interlinked by linear residuals. The model's training utilized a two-stage transfer learning process to produce an effective model. Finally, we used the XgBoost classifier to recognize multiple classes of chest X-rays. To evaluate the m-Xception model, the 1095 dataset was converted using a data augmentation technique into 48,000 X-ray images, including 12,000 normal, 12,000 pneumonia, 12,000 COVID-19 images, and 12,000 lung opacity images. To balance these classes, we used a data augmentation technique. Using public datasets with three distinct train-test divisions (80–20%, 70–30%, and 60–40%) to evaluate our work, we attained an average of 96.5% accuracy, 96% F1 score, 96% recall, and 96% precision. A comparative analysis demonstrates that the m-Xception method outperforms comparable existing methods. The results of the experiments indicate that the proposed approach is intended to assist radiologists in better diagnosing different lung diseases. [ABSTRACT FROM AUTHOR]

Many researchers have realized the intelligent medical diagnosis of diabetic retinopathy (DR) from fundus images by using deep learning methods, including supervised contrastive learning (SupCon). However, although SupCon brings label information into the calculation of contrastive learning, it does not distinguish between augmented positives and same-label positives. As a result, we propose the concept of Angular Margin and incorporate it into SupCon to address this issue. To demonstrate the effectiveness of our strategy, we tested it on two datasets for the detection and grading of DR. To align with previous work, Accuracy, Precision, Recall, F1, and AUC were selected as evaluation metrics. Moreover, we also chose alignment and uniformity to verify the effect of representation learning and UMAP (Uniform Manifold Approximation and Projection) to visualize fundus image embeddings. In summary, DR detection achieved state-of-the-art results across all metrics, with Accuracy = 98.91, Precision = 98.93, Recall = 98.90, F1 = 98.91, and AUC = 99.80. The grading also attained state-of-the-art results in terms of Accuracy and AUC, which were 85.61 and 93.97, respectively. The experimental results demonstrate that Angular Margin is an excellent intelligent medical diagnostic algorithm, performing well in both DR detection and grading tasks. [ABSTRACT FROM AUTHOR]

Osteosarcoma is a common type of bone tumor, particularly prevalent in children and adolescents between the ages of 5 and 25 who are experiencing growth spurts during puberty. Manual delineation of tumor regions in MRI images can be laborious and time-consuming, and results may be subjective and difficult to replicate. Therefore, a convolutional neural network (CNN) was developed to automatically segment osteosarcoma cancerous cells in three types of MRI images. The study consisted of five main stages. First, 3692 DICOM format MRI images were acquired from 46 patients, including T1-weighted, T2-weighted, and T1-weighted with injection of Gadolinium (T1W + Gd) images. Contrast stretching and median filter were applied to enhance image intensity and remove noise, and the pre-processed images were reconstructed into NIfTI format files for deep learning. The MRI images were then transformed to fit the CNN's requirements. A 3D U-Net architecture was proposed with optimized parameters to build an automatic segmentation model capable of segmenting osteosarcoma from the MRI images. The 3D U-Net segmentation model achieved excellent results, with mean dice similarity coefficients (DSC) of 83.75%, 85.45%, and 87.62% for T1W, T2W, and T1W + Gd images, respectively. However, the study found that the proposed method had some limitations, including poorly defined borders, missing lesion portions, and other confounding factors. In summary, an automatic segmentation method based on a CNN has been developed to address the challenge of manually segmenting osteosarcoma cancerous cells in MRI images. While the proposed method showed promise, the study revealed limitations that need to be addressed to improve its efficacy. [ABSTRACT FROM AUTHOR]

Diffusion-weighted images of the prostate can suffer from a "hazy" background in low signal-intensity areas. We hypothesize that enhanced image processing (EIP) using complex averaging reduces artifacts, noise, and distortion in conventionally acquired diffusion-weighted images and synthesized high b-value images, thus leading to higher image quality and better detection of potentially malignant lesions. Conventional DWI trace images with a b-value of 1000 s/mm2 (b1000), calculated images with a b-value of 2000 s/mm2 (cb2000), and ADC maps of 3T multiparametric prostate MRIs in 53 patients (age 68.8 ± 10 years) were retrospectively evaluated. Standard images were compared to images using EIP. In the standard images, 36 lesions were detected in the peripheral zone and 20 in the transition zone. In 13 patients, EIP led to the detection of 8 additional lesions and the upgrading of 6 lesions; 6 of these patients were diagnosed with prostate carcinoma Gleason 7 or 8. EIP improved qualitative ratings for overall image quality and lesion detectability. Artifacts were significantly reduced in the cb2000 images. Quantitative measurements for lesion detectability expressed as an SI ratio were significantly improved. EIP using complex averaging led to image quality improvements in acquired and synthesized DWI, potentially resulting in elevated diagnostic accuracy and management changes. [ABSTRACT FROM AUTHOR]

Diabetic retinopathy is one of the abnormalities of the retina in which a diabetic patient suffers from severe vision loss due to an affected retina. Proliferative diabetic retinopathy (PDR) is the final and most critical stage of diabetic retinopathy. Abnormal and fragile blood vessels start to grow on the surface of the retina at this stage. It causes retinal detachment, which may lead to complete blindness in severe cases. In this paper, a novel method is proposed for the detection and grading of neovascularization. The proposed system first performs pre-processing on input retinal images to enhance the vascular pattern, followed by blood vessel segmentation and optic disc localization. Then various features are tested on the candidate regions with different thresholds. In this way, positive and negative advanced diabetic retinopathy cases are separated. Optic disc coordinates are applied for the grading of neovascularization as NVD or NVE. The proposed algorithm improves the quality of automated diagnostic systems by eliminating normal blood vessels and exudates that might cause hindrances in accurate disease detection, thus resulting in more accurate detection of abnormal blood vessels. The evaluation of the proposed system has been carried out using performance parameters such as sensitivity, specificity, accuracy, and positive predictive value (PPV) on a publicly available standard retinal image database and one of the locally available databases. The proposed algorithm gives an accuracy of 98.5% and PPV of 99.8% on MESSIDOR and an accuracy of 96.5% and PPV of 100% on the local database. [ABSTRACT FROM AUTHOR]

Artificial intelligence has made substantial progress in medicine. Automated dental imaging interpretation is one of the most prolific areas of research using AI. X-ray and infrared imaging systems have enabled dental clinicians to identify dental diseases since the 1950s. However, the manual process of dental disease assessment is tedious and error-prone when diagnosed by inexperienced dentists. Thus, researchers have employed different advanced computer vision techniques, and machine- and deep-learning models for dental disease diagnoses using X-ray and near-infrared imagery. Despite the notable development of AI in dentistry, certain factors affect the performance of the proposed approaches, including limited data availability, imbalanced classes, and lack of transparency and interpretability. Hence, it is of utmost importance for the research community to formulate suitable approaches, considering the existing challenges and leveraging findings from the existing studies. Based on an extensive literature review, this survey provides a brief overview of X-ray and near-infrared imaging systems. Additionally, a comprehensive insight into challenges faced by researchers in the dental domain has been brought forth in this survey. The article further offers an amalgamative assessment of both performances and methods evaluated on public benchmarks and concludes with ethical considerations and future research avenues. [ABSTRACT FROM AUTHOR]

Advances in computer technology and image processing now allow us to obtain from angiographic images a large variety of information on coronary physiology without the use of a guide-wire as a diagnostic information equivalent to FFR and iFR but also information allowing for the performance of a real virtual percutaneous coronary intervention (PCI) and finally the ability to obtain information to optimize the results of PCI. With specific software, it is now possible to have a real upgrading of invasive coronary angiography. In this review, we present the different advances in this field and discuss the future perspectives offered by this technology. [ABSTRACT FROM AUTHOR]

Jaundice is caused by excess circulating bilirubin, known as hyperbilirubinemia. This symptom is sometimes caused by a critical hepatobiliary disorder, and is generally identified as yellowish sclera when bilirubin levels increase more than 3 mg/dL. It is difficult to identify jaundice accurately, especially via telemedicine. This study aimed to identify and quantify jaundice by trans-conjunctiva optical imaging. Patients with jaundice (total bilirubin ≥3 mg/dL) and normal control subjects (total bilirubin <3 mg/dL) were prospectively enrolled from June 2021 to July 2022. We took bilateral conjunctiva imaging with a built-in camera on a smartphone (1st generation iPhone SE) under normal white light conditions without any restrictions. We processed the images using an Algorithm Based on Human Brain (ABHB) (Zeta Bridge Corporation, Tokyo, Japan) and converted them into a hue degree of Hue Saturation Lightness (HSL) color space. A total of 26 patients with jaundice (9.57 ± 7.11 mg/dL) and 25 control subjects (0.77 ± 0.35 mg/dL) were enrolled in this study. The causes of jaundice among the 18 male and 8 female subjects (median age 61 yrs.) included hepatobiliary cancer (n = 10), chronic hepatitis or cirrhosis (n = 6), pancreatic cancer (n = 4), acute liver failure (n = 2), cholelithiasis or cholangitis (n = 2), acute pancreatitis (n = 1), and Gilbert's syndrome (n = 1). The maximum hue degree (MHD) optimal cutoff to identify jaundice was 40.8 (sensitivity 81% and specificity 80%), and the AUROC was 0.842. The MHD was moderately correlated to total serum bilirubin (TSB) levels (rS = 0.528, p < 0.001). TSB level (≥5 mg/dL) can be estimated by the formula 21.1603 − 0.7371 × 56.3 − MHD 2 . In conclusion, the ABHB-based MHD of conjunctiva imaging identified jaundice using an ordinary smartphone without any specific attachments and deep learning. This novel technology could be a helpful diagnostic tool in telemedicine or self-medication. [ABSTRACT FROM AUTHOR]

This paper introduces a new method for real-time high-density impulsive noise elimination applied to medical images. A double process aimed at the enhancement of local data composed of Nested Filtering followed by a Morphological Operation (NFMO) is proposed. The major problem with heavily noisy images is the lack of color information around corrupted pixels. We show that the classic replacement techniques all come up against this problem, resulting in average restoration quality. We only focus on the corrupt pixel replacement phase. For the detection itself, we use the Modified Laplacian Vector Median Filter (MLVMF). To perform pixel replacement, two-window nested filtering is suggested. All noise pixels in the neighborhood scanned by the first window are investigated using the second window. This investigation phase increases the amount of useful information within the first window. The remaining useful information that the second window failed to produce in the case of a very strong connex noise concentration is then estimated using a morphological operation of dilatation. To validate the proposed method, NFMO is first evaluated on the standard image Lena with a range of 10% to 90% impulsive noise. Using the Peak Signal-to-Noise Ratio metric (PSNR), the image denoising quality obtained is compared to the performance of a wide variety of existing approaches. Several noisy medical images are subjected to a second test. In this test, the computation time and image-restoring quality of NFMO are assessed using the PSNR and the Normalized Color Difference (NCD) criteria. Finally, an optimized design for a field-programmable gate array (FPGA) is suggested to implement the proposed method for real-time processing. The proposed solution performs excellent quality restoration for images with high-density impulsive noise. When the proposed NFMO is used on the standard Lena image with 90% impulsive noise, the PSNR reaches 29.99 dB. Under the same noise conditions, NFMO completely restores medical images in an average time of 23 milliseconds with an average PSNR of 31.62 dB and an average NCD of 0.10. [ABSTRACT FROM AUTHOR]

In this research, we demonstrate a Deep Convolutional Neural Network-based classification model for the detection of monkeypox. Monkeypox can be difficult to diagnose clinically in its early stages since it resembles both chickenpox and measles in symptoms. The early diagnosis of monkeypox helps doctors cure it more quickly. Therefore, pre-trained models are frequently used in the diagnosis of monkeypox, because the manual analysis of a large number of images is labor-intensive and prone to inaccuracy. Therefore, finding the monkeypox virus requires an automated process. The large layer count of convolutional neural network (CNN) architectures enables them to successfully conceptualize the features on their own, thereby contributing to better performance in image classification. The scientific community has recently articulated significant attention in employing artificial intelligence (AI) to diagnose monkeypox from digital skin images due primarily to AI's success in COVID-19 identification. The VGG16, VGG19, ResNet50, ResNet101, DenseNet201, and AlexNet models were used in our proposed method to classify patients with monkeypox symptoms with other diseases of a similar kind (chickenpox, measles, and normal). The majority of images in our research are collected from publicly available datasets. This study suggests an adaptive k-means clustering image segmentation technique that delivers precise segmentation results with straightforward operation. Our preliminary computational findings reveal that the proposed model could accurately detect patients with monkeypox. The best overall accuracy achieved by ResNet101 is 94.25%, with an AUC of 98.59%. Additionally, we describe the categorization of our model utilizing feature extraction using Local Interpretable Model-Agnostic Explanations (LIME), which provides a more in-depth understanding of particular properties that distinguish the monkeypox virus. [ABSTRACT FROM AUTHOR]

Melanoma, a kind of skin cancer that is very risky, is distinguished by uncontrolled cell multiplication. Melanoma detection is of the utmost significance in clinical practice because of the atypical border structure and the numerous types of tissue it can involve. The identification of melanoma is still a challenging process for color images, despite the fact that numerous approaches have been proposed in the research that has been done. In this research, we present a comprehensive system for the efficient and precise classification of skin lesions. The framework includes preprocessing, segmentation, feature extraction, and classification modules. Preprocessing with DullRazor eliminates skin-imaging hair artifacts. Next, Fully Connected Neural Network (FCNN) semantic segmentation extracts precise and obvious Regions of Interest (ROIs). We then extract relevant skin image features from ROIs using an enhanced Sobel Directional Pattern (SDP). For skin image analysis, Sobel Directional Pattern outperforms ABCD. Finally, a stacked Restricted Boltzmann Machine (RBM) classifies skin ROIs. Stacked RBMs accurately classify skin melanoma. The experiments have been conducted on five datasets: Pedro Hispano Hospital (PH2), International Skin Imaging Collaboration (ISIC 2016), ISIC 2017, Dermnet, and DermIS, and achieved an accuracy of 99.8%, 96.5%, 95.5%, 87.9%, and 97.6%, respectively. The results show that a stack of Restricted Boltzmann Machines is superior for categorizing skin cancer types using the proposed innovative SDP. [ABSTRACT FROM AUTHOR]

Experts have used ultrasound imaging to manually determine follicle count and perform measurements, especially in cases of polycystic ovary syndrome (PCOS). However, due to the laborious and error-prone process of manual diagnosis, researchers have explored and developed medical image processing techniques to help with diagnosing and monitoring PCOS. This study proposes a combination of Otsu's thresholding with the Chan–Vese method to segment and identify follicles in the ovary with reference to ultrasound images marked by a medical practitioner. Otsu's thresholding highlights the pixel intensities of the image and creates a binary mask for use with the Chan–Vese method to define the boundary of the follicles. The acquired results were compared between the classical Chan–Vese method and the proposed method. The performances of the methods were evaluated in terms of accuracy, Dice score, Jaccard index and sensitivity. In overall segmentation evaluation, the proposed method showed superior results compared to the classical Chan–Vese method. Among the calculated evaluation metrics, the sensitivity of the proposed method was superior, with an average of 0.74 ± 0.12. Meanwhile, the average sensitivity for the classical Chan–Vese method was 0.54 ± 0.14, which is 20.03% lower than the sensitivity of the proposed method. Moreover, the proposed method showed significantly improved Dice score (p = 0.011), Jaccard index (p = 0.008) and sensitivity (p = 0.0001). This study showed that the combination of Otsu's thresholding and the Chan–Vese method enhanced the segmentation of ultrasound images. [ABSTRACT FROM AUTHOR]

Automatic brain tumor detection in MR Images is one of the basic applications of machine vision in medical image processing, which, despite much research, still needs further development. Using multiple machine learning techniques as an ensemble system is one of the solutions that can be effective in achieving this goal. In this paper, a novel method for diagnosing brain tumors by combining data mining and machine learning techniques has been proposed. In the proposed method, each image is initially pre-processed to eliminate its background region and identify brain tissue. The Social Spider Optimization (SSO) algorithm is then utilized to segment the MRI Images. The MRI Images segmentation allows for a more precise identification of the tumor region in the image. In the next step, the distinctive features of the image are extracted using the SVD technique. In addition to removing redundant information, this strategy boosts the speed of the processing at the classification stage. Finally, a combination of the algorithms Naïve Bayes, Support vector machine and K-nearest neighbor is used to classify the extracted features and detect brain tumors. Each of the three algorithms performs feature classification individually, and the final output of the proposed model is created by integrating the three independent outputs and voting the results. The results indicate that the proposed method can diagnose brain tumors in the BRATS 2014 dataset with an average accuracy of 98.61%, sensitivity of 95.79% and specificity of 99.71%. Additionally, the proposed method could diagnose brain tumors in the BTD20 database with an average accuracy of 99.13%, sensitivity of 99% and specificity of 99.26%. These results show a significant improvement compared to previous efforts. The findings confirm that using the image segmentation technique, as well as the ensemble learning, is effective in improving the efficiency of the proposed method. [ABSTRACT FROM AUTHOR]

Malaria is a pressing medical issue in tropical and subtropical regions. Currently, the manual microscopic examination remains the gold standard malaria diagnosis method. Nevertheless, this procedure required highly skilled lab technicians to prepare and examine the slides. Therefore, a framework encompassing image processing and machine learning is proposed due to inconsistencies in manual inspection, counting, and staging. Here, a standardized segmentation framework utilizing thresholding and clustering is developed to segment parasites' stages of P. falciparum and P. vivax species. Moreover, a multi-stage classifier is designed for recognizing parasite species and staging in both species. Experimental results indicate the effectiveness of segmenting thick smear images based on Phansalkar thresholding garnered an accuracy of 99.86%. The employment of variance and new transferring process for the clustered members, enhanced k-means (EKM) clustering has successfully segmented all malaria stages with accuracy and an F1-score of 99.20% and 0.9033, respectively. In addition, the accuracies of parasite detection, species recognition, and staging obtained through a random forest (RF) accounted for 86.89%, 98.82%, and 90.78%, respectively, simultaneously. The proposed framework enables versatile malaria parasite detection and staging with an interactive result, paving the path for future improvements by utilizing the proposed framework on all others malaria species. [ABSTRACT FROM AUTHOR]

The ongoing coronavirus disease 2019 (COVID-19) pandemic has had a significant impact on patients and healthcare systems across the world. Distinguishing non-COVID-19 patients from COVID-19 patients at the lowest possible cost and in the earliest stages of the disease is a major issue. Additionally, the implementation of explainable deep learning decisions is another issue, especially in critical fields such as medicine. The study presents a method to train deep learning models and apply an uncertainty-based ensemble voting policy to achieve 99% accuracy in classifying COVID-19 chest X-rays from normal and pneumonia-related infections. We further present a training scheme that integrates the cyclic cosine annealing approach with cross-validation and uncertainty quantification that is measured using prediction interval coverage probability (PICP) as final ensemble voting weights. We also propose the Uncertain-CAM technique, which improves deep learning explainability and provides a more reliable COVID-19 classification system. We introduce a new image processing technique to measure the explainability based on ground-truth, and we compared it with the widely adopted Grad-CAM method. [ABSTRACT FROM AUTHOR]

Compressed sensing accelerates magnetic resonance imaging (MRI) acquisition by undersampling of the k-space. Yet, excessive undersampling impairs image quality when using conventional reconstruction techniques. Deep-learning-based reconstruction methods might allow for stronger undersampling and thus faster MRI scans without loss of crucial image quality. We compared imaging approaches using parallel imaging (SENSE), a combination of parallel imaging and compressed sensing (COMPRESSED SENSE, CS), and a combination of CS and a deep-learning-based reconstruction (CS AI) on raw k-space data acquired at different undersampling factors. 3D T2-weighted images of the lumbar spine were obtained from 20 volunteers, including a 3D sequence (standard SENSE), as provided by the manufacturer, as well as accelerated 3D sequences (undersampling factors 4.5, 8, and 11) reconstructed with CS and CS AI. Subjective rating was performed using a 5-point Likert scale to evaluate anatomical structures and overall image impression. Objective rating was performed using apparent signal-to-noise and contrast-to-noise ratio (aSNR and aCNR) as well as root mean square error (RMSE) and structural-similarity index (SSIM). The CS AI 4.5 sequence was subjectively rated better than the standard in several categories and deep-learning-based reconstructions were subjectively rated better than conventional reconstructions in several categories for acceleration factors 8 and 11. In the objective rating, only aSNR of the bone showed a significant tendency towards better results of the deep-learning-based reconstructions. We conclude that CS in combination with deep-learning-based image reconstruction allows for stronger undersampling of k-space data without loss of image quality, and thus has potential for further scan time reduction. [ABSTRACT FROM AUTHOR]

A corneal ulcers are one of the most common eye diseases. They come from various infections, such as bacteria, viruses, or parasites. They may lead to ocular morbidity and visual disability. Therefore, early detection can reduce the probability of reaching the visually impaired. One of the most common techniques exploited for corneal ulcer screening is slit-lamp images. This paper proposes two highly accurate automated systems to localize the corneal ulcer region. The designed approaches are image processing techniques with Hough transform and deep learning approaches. The two methods are validated and tested on the publicly available SUSTech-SYSU database. The accuracy is evaluated and compared between both systems. Both systems achieve an accuracy of more than 90%. However, the deep learning approach is more accurate than the traditional image processing techniques. It reaches 98.9% accuracy and Dice similarity 99.3%. However, the first method does not require parameters to optimize an explicit training model. The two approaches can perform well in the medical field. Moreover, the first model has more leverage than the deep learning model because the last one needs a large training dataset to build reliable software in clinics. Both proposed methods help physicians in corneal ulcer level assessment and improve treatment efficiency. [ABSTRACT FROM AUTHOR]

COVID-19 was first discovered in December 2019 in Wuhan. There have been reports of thousands of illnesses and hundreds of deaths in almost every region of the world. Medical images, when combined with cutting-edge technology such as artificial intelligence, have the potential to improve the efficiency of the public health system and deliver faster and more reliable findings in the detection of COVID-19. The process of developing the COVID-19 diagnostic system begins with image accusation and proceeds via preprocessing, feature extraction, and classification. According to literature review, several attempts to develop taxonomies for COVID-19 detection using image processing methods have been introduced. However, most of these adhere to a standard category that exclusively considers classification methods. Therefore, in this study a new taxonomy for the early stages of COVID-19 detection is proposed. It attempts to offer a full grasp of image processing in COVID-19 while considering all phases required prior to classification. The survey concludes with a discussion of outstanding concerns and future directions. [ABSTRACT FROM AUTHOR]

Background: Deep learning (DL) methods can noninvasively predict glioma subtypes; however, there is no set paradigm for the selection of network structures and input data, including the image combination method, image processing strategy, type of numeric data, and others. Purpose: To compare different combinations of DL frameworks (ResNet, ConvNext, and vision transformer (VIT)), image preprocessing strategies, magnetic resonance imaging (MRI) sequences, and numerical data for increasing the accuracy of DL models for differentiating glioma subtypes prior to surgery. Methods: Our dataset consisted of 211 patients with newly diagnosed gliomas who underwent preoperative MRI with standard and diffusion-weighted imaging methods. Different data combinations were used as input for the three different DL classifiers. Results: The accuracy of the image preprocessing strategies, including skull stripping, segment addition, and individual treatment of slices, was 5%, 10%, and 12.5% higher, respectively, than that of the other strategies. The accuracy increased by 7.5% and 10% following the addition of ADC and numeric data, respectively. ResNet34 exhibited the best performance, which was 5% and 17.5% higher than that of ConvNext tiny and VIT-base, respectively. Data Conclusions: The findings demonstrated that the addition of quantitatively numeric data, ADC images, and effective image preprocessing strategies improved model accuracy for datasets of similar size. The performance of ResNet was superior for small or medium datasets. [ABSTRACT FROM AUTHOR]

In medical image processing, accurate segmentation of lung tumors is very important. Computer-aided accurate segmentation can effectively assist doctors in surgery planning and treatment decisions. Although the accurate segmentation results of lung tumors can provide a reliable basis for clinical treatment, the key to obtaining accurate segmentation results is how to improve the segmentation performance of the algorithm. We propose an automatic segmentation method for lung tumors based on an improved region growing algorithm, which uses the prior information on lung tumors to achieve an automatic selection of the initial seed point. The proposed method includes a seed point expansion mechanism and an automatic threshold update mechanism and takes the combination of multiple segmentation results as the final segmentation result. In the lung image database consortium (LIDC-IDRI) dataset, we designed 10 experiments to test the proposed method and compare it with 4 popular segmentation methods. The experimental results show that the average dice coefficient obtained by the proposed method is 0.936 ± 0.027, and the average Jaccard distance is 0.114 ± 0.049. The average dice coefficient obtained by the proposed method is 0.107, 0.053, 0.040, and 0.156, higher than that of the other four methods, respectively. This study proves that the proposed method can automatically segment lung tumors in CT slices and has suitable segmentation performance. [ABSTRACT FROM AUTHOR]

Purpose: To assess the impact of virtual-monoenergetic-image (VMI) energies on the diagnosis of pulmonary embolism (PE) in photon-counting-detector computed-tomography (PCD-CT). Methods: Eighty patients (median age 60.4 years) with suspected PE were retrospectively included. Scans were performed on PCD-CT in the multi-energy mode at 120 kV. VMIs from 40–70 keV in 10 keV intervals were reconstructed. CT-attenuation was measured in the pulmonary trunk and the main branches of the pulmonary artery. Signal-to-noise (SNR) ratio was calculated. Two radiologists evaluated subjective-image-quality (noise, vessel-attenuation and sharpness; five-point-Likert-scale, non-diagnostic–excellent), the presence of hardening artefacts and presence/visibility of PE. Results: Signal was highest at the lowest evaluated VMI (40 keV; 1053.50 HU); image noise was lowest at the highest VMI (70 keV; 15.60 HU). Highest SNR was achieved at the lowest VMI (p < 0.05). Inter-reader-agreement for subjective analysis was fair to excellent (k = 0.373–1.000; p < 0.001). Scores for vessel-attenuation and sharpness were highest at 40 keV (both:5, range 4/3–5; k = 1.000); scores for image-noise were highest at 70 keV (4, range 3–5). The highest number of hardening artifacts were reported at 40 keV (n = 22; 28%). PE-visualization was rated best at 50 keV (4.7; range 4–5) and decreased with increasing VMI-energy (r = −0.558; p < 0.001). Conclusions: While SNR was best at 40 keV, subjective PE visibility was rated highest at 50 keV, potentially owing to the lower image noise and hardening artefacts. [ABSTRACT FROM AUTHOR]

Objectives: Assessing implant stability is integral to dental implant therapy. This study aimed to construct a multi-task cascade convolution neural network to evaluate implant stability using cone-beam computed tomography (CBCT). Methods: A dataset of 779 implant coronal section images was obtained from CBCT scans, and matching clinical information was used for the training and test datasets. We developed a multi-task cascade network based on CBCT to assess implant stability. We used the MobilenetV2-DeeplabV3+ semantic segmentation network, combined with an image processing algorithm in conjunction with prior knowledge, to generate the volume of interest (VOI) that was eventually used for the ResNet-50 classification of implant stability. The performance of the multitask cascade network was evaluated in a test set by comparing the implant stability quotient (ISQ), measured using an Osstell device. Results: The cascade network established in this study showed good prediction performance for implant stability classification. The binary, ternary, and quaternary ISQ classification test set accuracies were 96.13%, 95.33%, and 92.90%, with mean precisions of 96.20%, 95.33%, and 93.71%, respectively. In addition, this cascade network evaluated each implant's stability in only 3.76 s, indicating high efficiency. Conclusions: To our knowledge, this is the first study to present a CBCT-based deep learning approach CBCT to assess implant stability. The multi-task cascade network accomplishes a series of tasks related to implant denture segmentation, VOI extraction, and implant stability classification, and has good concordance with the ISQ. [ABSTRACT FROM AUTHOR]

Machine-learning (ML) and deep-learning (DL) algorithms are part of a group of modeling algorithms that grasp the hidden patterns in data based on a training process, enabling them to extract complex information from the input data. In the past decade, these algorithms have been increasingly used for image processing, specifically in the medical domain. Cardiothoracic imaging is one of the early adopters of ML/DL research, and the COVID-19 pandemic resulted in more research focus on the feasibility and applications of ML/DL in cardiothoracic imaging. In this scoping review, we systematically searched available peer-reviewed medical literature on cardiothoracic imaging and quantitatively extracted key data elements in order to get a big picture of how ML/DL have been used in the rapidly evolving cardiothoracic imaging field. During this report, we provide insights on different applications of ML/DL and some nuances pertaining to this specific field of research. Finally, we provide general suggestions on how researchers can make their research more than just a proof-of-concept and move toward clinical adoption. [ABSTRACT FROM AUTHOR]

To quickly and accurately identify the pathological features of the tongue, we developed an intelligent tongue diagnosis system that uses deep learning on a mobile terminal. We also propose an efficient and accurate tongue image processing algorithm framework to infer the category of the tongue. First, a software system integrating registration, login, account management, tongue image recognition, and doctor–patient dialogue was developed based on the Android platform. Then, the deep learning models, based on the official benchmark models, were trained by using the tongue image datasets. The tongue diagnosis algorithm framework includes the YOLOv5s6, U-Net, and MobileNetV3 networks, which are employed for tongue recognition, tongue region segmentation, and tongue feature classification (tooth marks, spots, and fissures), respectively. The experimental results demonstrate that the performance of the tongue diagnosis model was satisfying, and the accuracy of the final classification of tooth marks, spots, and fissures was 93.33%, 89.60%, and 97.67%, respectively. The construction of this system has a certain reference value for the objectification and intelligence of tongue diagnosis. [ABSTRACT FROM AUTHOR]

The objectives of our study were to (a) evaluate the feasibility of using 3D printed phantoms in magnetic resonance imaging (MR) in assessing the robustness and repeatability of radiomic parameters and (b) to compare the results obtained from the 3D printed phantoms to metrics obtained in biological phantoms. To this end, three different 3D phantoms were printed: a Hilbert cube (5 × 5 × 5 cm3) and two cubic quick response (QR) code phantoms (a large phantom (large QR) (5 × 5 × 4 cm3) and a small phantom (small QR) (4 × 4 × 3 cm3)). All 3D printed and biological phantoms (kiwis, tomatoes, and onions) were scanned thrice on clinical 1.5 T and 3 T MR with 1 mm and 2 mm isotropic resolution. Subsequent analyses included analyses of several radiomics indices (RI), their repeatability and reliability were calculated using the coefficient of variation (CV), the relative percentage difference (RPD), and the interclass coefficient (ICC) parameters. Additionally, the readability of QR codes obtained from the MR images was examined with several mobile phones and algorithms. The best repeatability (CV ≤ 10%) is reported for the acquisition protocols with the highest spatial resolution. In general, the repeatability and reliability of RI were better in data obtained at 1.5 T (CV = 1.9) than at 3 T (CV = 2.11). Furthermore, we report good agreements between results obtained for the 3D phantoms and biological phantoms. Finally, analyses of the read-out rate of the QR code revealed better texture analyses for images with a spatial resolution of 1 mm than 2 mm. In conclusion, 3D printing techniques offer a unique solution to create textures for analyzing the reliability of radiomic data from MR scans. [ABSTRACT FROM AUTHOR]

The basilar artery, which is the core of the posterior circulation, supplies blood to the brainstem and cerebellum. When basilar artery blood circulation is impaired, several symptoms can occur. In addition, the bending of the basilar artery causes stroke and infarction. Therefore, an image processing method for analyzing the bending degree of the basilar artery is introduced herein. To analyze the bending degree, the coordinates of the center points of the basilar artery are extracted using image processing techniques such as Canny edge detection, the contour technique, and the distance conversion technique. An image reconstructed using the three-dimensional scatter plot function in MATLAB and vector plots is used to calculate the vectors for each central point of the basilar artery. Meanwhile, the angle of each central point is calculated by selecting the first central point where the basilar artery begins, the central point with the greatest bending degree, and the central point at which the branching ends. The greater the bending degree of the basilar artery is, the larger the magnitude of the vector in the bending direction. The obtained results are verified by experts in the field, and the proposed algorithm demonstrates good performance. [ABSTRACT FROM AUTHOR]

In December 2019, the novel coronavirus disease 2019 (COVID-19) appeared. Being highly contagious and with no effective treatment available, the only solution was to detect and isolate infected patients to further break the chain of infection. The shortage of test kits and other drawbacks of lab tests motivated researchers to build an automated diagnosis system using chest X-rays and CT scanning. The reviewed works in this study use AI coupled with the radiological image processing of raw chest X-rays and CT images to train various CNN models. They use transfer learning and numerous types of binary and multi-class classifications. The models are trained and validated on several datasets, the attributes of which are also discussed. The obtained results of various algorithms are later compared using performance metrics such as accuracy, F1 score, and AUC. Major challenges faced in this research domain are the limited availability of COVID image data and the high accuracy of the prediction of the severity of patients using deep learning compared to well-known methods of COVID-19 detection such as PCR tests. These automated detection systems using CXR technology are reliable enough to help radiologists in the initial screening and in the immediate diagnosis of infected individuals. They are preferred because of their low cost, availability, and fast results. [ABSTRACT FROM AUTHOR]

CNN-based image processing has been actively applied to histopathological analysis to detect and classify cancerous tumors automatically. However, CNN-based classifiers generally predict a label with overconfidence, which becomes a serious problem in the medical domain. The objective of this study is to propose a new training method, called MixPatch, designed to improve a CNN-based classifier by specifically addressing the prediction uncertainty problem and examine its effectiveness in improving diagnosis performance in the context of histopathological image analysis. MixPatch generates and uses a new sub-training dataset, which consists of mixed-patches and their predefined ground-truth labels, for every single mini-batch. Mixed-patches are generated using a small size of clean patches confirmed by pathologists while their ground-truth labels are defined using a proportion-based soft labeling method. Our results obtained using a large histopathological image dataset shows that the proposed method performs better and alleviates overconfidence more effectively than any other method examined in the study. More specifically, our model showed 97.06% accuracy, an increase of 1.6% to 12.18%, while achieving 0.76% of expected calibration error, a decrease of 0.6% to 6.3%, over the other models. By specifically considering the mixed-region variation characteristics of histopathology images, MixPatch augments the extant mixed image methods for medical image analysis in which prediction uncertainty is a crucial issue. The proposed method provides a new way to systematically alleviate the overconfidence problem of CNN-based classifiers and improve their prediction accuracy, contributing toward more calibrated and reliable histopathology image analysis. [ABSTRACT FROM AUTHOR]

An automatic pathological diagnosis is a challenging task because histopathological images with different cellular heterogeneity representations are sometimes limited. To overcome this, we investigated how the holistic and local appearance features with limited information can be fused to enhance the analysis performance. We propose an unsupervised deep learning model for whole-slide image diagnosis, which uses stacked autoencoders simultaneously feeding multiple-image descriptors such as the histogram of oriented gradients and local binary patterns along with the original image to fuse the heterogeneous features. The pre-trained latent vectors are extracted from each autoencoder, and these fused feature representations are utilized for classification. We observed that training with additional descriptors helps the model to overcome the limitations of multiple variants and the intricate cellular structure of histopathology data by various experiments. Our model outperforms existing state-of-the-art approaches by achieving the highest accuracies of 87.2 for ICIAR2018, 94.6 for Dartmouth, and other significant metrics for public benchmark datasets. Our model does not rely on a specific set of pre-trained features based on classifiers to achieve high performance. Unsupervised spaces are learned from the number of independent multiple descriptors and can be used with different variants of classifiers to classify cancer diseases from whole-slide images. Furthermore, we found that the proposed model classifies the types of breast and lung cancer similar to the viewpoint of pathologists by visualization. We also designed our whole-slide image processing toolbox to extract and process the patches from whole-slide images. [ABSTRACT FROM AUTHOR]

One of the most applied imaging methods in medicine is endoscopy. A highly specialized image modality has been developed since the first modern endoscope, the "Lichtleiter" of Bozzini was introduced in the early 19th century. Multiple medical disciplines use endoscopy for diagnostics or to visualize and support therapeutic procedures. Therefore, the shapes, functionalities, handling concepts, and the integrated and surrounding technology of endoscopic systems were adapted to meet these dedicated medical application requirements. This survey gives an overview of modern endoscopic technology's state of the art. Therefore, the portfolio of several manufacturers with commercially available products on the market was screened and summarized. Additionally, some trends for upcoming developments were collected. [ABSTRACT FROM AUTHOR]