Search

Context: The Balance Error Scoring System (BESS) is a commonly used clinical tool to evaluate postural control that is traditionally performed through visual assessment and subjective evaluation of balance errors. The purpose of this study was to evaluate an automated computer-based scoring system using an instrumented pressure mat compared to the traditional human-based manual assessment. Design: A descriptive cross-sectional study design was used to evaluate the performance of the automated versus human BESS scoring methodology in healthy individuals. Methods: Fifty-one healthy active participants performed BESS trials following standard BESS procedures on an instrumented pressure mat (MobileMat, Tekscan Inc). Trained evaluators manually scored balance errors from frontal and sagittal plane video recordings for comparison to errors scored using center of force measurements and an automated scoring software (SportsAT, version 2.0.2, Tekscan Inc). A linear mixed model was used to determine measurement discrepancies across the 2 methods. Bland–Altman analyses were conducted to determine limit of agreement for the automated and manual scoring methods. Results: Significant differences between the automated and manual errors scored were observed across all conditions (P <.05), excluding bilateral firm stance. The greatest discrepancy between scoring methods was during the tandem foam stance, while the smallest discrepancy was during the tandem firm stance. Conclusion: The 2 methods of BESS scoring are different with wide limits of agreement. The benefits and risks of each approach to error scoring should be considered when selecting the most appropriate metric for clinical use or research studies. [ABSTRACT FROM AUTHOR]

Objective: The objective of the study was to assess whether computer- assisted periodontal diagnosis can improve the accuracy and homogeneity of classification results obtained by dental students using the 2017 classification of periodontal diseases. Method and materials: All final year predoctoral dental students from two dental schools were invited to participate in the study. Participants who volunteered for the study were randomly div ided into two groups for digital or manual diagnosis, and each participant classified 48 cases. A group of three experienced periodontists provided the reference or gold standard diagnosis. Results: Overall, 27 students completed the evaluation of all cases; 14 students comprised the digital application group and 13 the manual group. The accuracy of the classification results compared with the gold standard committee was 82% for the digital group compared to 50% of the manual group in terms of the extent of gingivitis; 71% vs 56% for the stage of periodontitis; 67% vs 62% for grade of periodontitis; 76% vs 63% for extent of periodontitis; and 43% vs 30% for overall diagnosis accuracy of periodontitis cases respectively. Conclusions: Computer-assisted classification using newly developed software, within the boundaries of this study, was shown to be a sensible support tool for dental practitioners to use when diagnosing periodontal disease. This digital tool can the clinicians' accuracy of diagnosis primarily in the extent and staging of periodontitis. [ABSTRACT FROM AUTHOR]

PURPOSE: The Medical Imaging and Data Resource Center (MIDRC) was created to facilitate medical imaging machine learning (ML) research for tasks including early detection, diagnosis, prognosis, and assessment of treatment response related to the coronavirus disease 2019 pandemic and beyond. The purpose of this work was to create a publicly available metrology resource to assist researchers in evaluating the performance of their medical image analysis ML algorithms. APPROACH: An interactive decision tree, called MIDRC-MetricTree, has been developed, organized by the type of task that the ML algorithm was trained to perform. The criteria for this decision tree were that (1) users can select information such as the type of task, the nature of the reference standard, and the type of the algorithm output and (2) based on the user input, recommendations are provided regarding appropriate performance evaluation approaches and metrics, including literature references and, when possible, links to publicly available software/code as well as short tutorial videos. RESULTS: Five types of tasks were identified for the decision tree: (a) classification, (b) detection/localization, (c) segmentation, (d) time-to-event (TTE) analysis, and (e) estimation. As an example, the classification branch of the decision tree includes two-class (binary) and multiclass classification tasks and provides suggestions for methods, metrics, software/code recommendations, and literature references for situations where the algorithm produces either binary or non-binary (e.g., continuous) output and for reference standards with negligible or non-negligible variability and unreliability. CONCLUSIONS: The publicly available decision tree is a resource to assist researchers in conducting task-specific performance evaluations, including classification, detection/localization, segmentation, TTE, and estimation tasks.

Ocular diseases can have debilitating consequences on visual acuity if left untreated, necessitating early and accurate diagnosis to improve patients' quality of life. Although the contemporary clinical prognosis involving fundus screening is a cost-effective method for detecting ocular abnormalities, however, it is time-intensive due to limited resources and expert ophthalmologists. While computer-aided detection, including traditional machine learning and deep learning, has been employed for enhanced prognosis from fundus images, conventional deep learning models often face challenges due to limited global modeling ability, inducing bias and suboptimal performance on unbalanced datasets. Presently, most studies on ocular disease detection focus on cataract detection or diabetic retinopathy severity prediction, leaving a myriad of vision-impairing conditions unexplored. Minimal research has been conducted utilizing deep models for identifying diverse ocular abnormalities from fundus images, with limited success. The study leveraged the capabilities of four Swin Transformer models (Swin-T, Swin-S, Swin-B, and Swin-L) for detecting various significant ocular diseases (including Cataracts, Hypertensive Retinopathy, Diabetic Retinopathy, Myopia, and Age-Related Macular Degeneration) from fundus images of the ODIR dataset. Swin Transformer models, confining self-attention to local windows while enabling cross-window interactions, demonstrated superior performance and computational efficiency. Upon assessment across three specific ODIR test sets, utilizing metrics such as AUC, F1-score, Kappa score, and a composite metric representing an average of these three (referred to as the final score), all Swin models exhibited superior performance metric scores than those documented in contemporary studies. The Swin-L model, in particular, achieved final scores of 0.8501, 0.8211, and 0.8616 on the Off-site, On-site, and Balanced ODIR test sets, respectively. An external validation on a Retina dataset further substantiated the generalizability of Swin models, with the models reporting final scores of 0.9058 (Swin-T), 0.92907 (Swin-S), 0.95917 (Swin-B), and 0.97042 (Swin-L). The results, corroborated by statistical analysis, underline the consistent and stable performance of Swin models across varied datasets, emphasizing their potential as reliable tools for multi-ocular disease detection from fundus images, thereby aiding in the early diagnosis and intervention of ocular abnormalities. [ABSTRACT FROM AUTHOR]

The selection of the most efficient features for glaucoma identification is the subject of our investigation because this disease is rapidly increasing worldwide. This disease causes lifelong blindness due to damage to the eye's optical nerve. Ophthalmologists have traditionally used tonometry, pachymetry, and other methods to measure intraocular pressure in order to diagnose patients. Yet each of these judgments takes time, requires high professional experience, and can be open to human error (inter-observer variability). Therefore, scholars are currently engaged in the domain of medical imaging, specifically focusing on the analysis of retinal images for the purpose of predicting glaucoma. This research also has the same objective and aims to address the aforementioned challenges. This empirical study proposes an artificial intelligence-based computer-assisted diagnosis (CAD) system which is built to overcome these difficulties by providing the best features for machine learning techniques for categorizing subject retinal pictures as "healthy" or "sick". This study presents a new set of reduced hybrid features that were selected from an initial set of 36 features extracted from fundus images of benchmark datasets that belonged to different classes to categorize patient fundus images into two categories: "healthy" or "infected." The nature inspired computing-based Emperor Penguin Optimization (EPO) algorithm and the Bacterial Foraging Optimization (BFO) algorithm are utilized to implement feature selection (FS) process. Additionally, a novel hybrid algorithm combining these two techniques is also proposed. Seven machine learning (ML) classifiers are engaged to compute eight statistically based performance metrics along with execution time computation, and a comparison of those metrics is also provided in a detailed fashion. The recommended method exhibits a fortunate performance with the highest specificity of 0.9940, sensitivity of 0.9347, and maximum accuracy of 96.55%. Expert medical practitioners who are overworked may receive assistance from the proposed system in making the optimal decisions to preserve human vision. [ABSTRACT FROM AUTHOR]

Many people are affected by lung cancer and it kills a lot of people worldwide. Often times, lung cancer does not have symptoms in the early stage. Abnormal growths called pulmonary nodules may be found in the lungs. Some of the pulmonary nodules may be cancerous. So, identifying pulmonary nodules will help detect lung cancer at an early stage. V-3DResNets based on variants of residual network is proposed to improve the generalization capability of the pulmonary nodule detection system. A U-shaped encoder-decoder is used to effectively extract the features. Residual networks help to reduce the vanishing gradient problem in deep neural networks. A Slice Grouped Non Local (SGNL) module studies the relation among entities across Computed Tomography (CT) slices. The content-aware mechanism of the squeeze and excitation block assigns different weights to the channels and improves the performance of the nodule detection system. The proposed work is analyzed using the PN9 dataset that includes 8,798 CT Scans with nine types of pulmonary nodules which attained a Competition Performance metric (CPM) of 65.51%. [ABSTRACT FROM AUTHOR]

When contemplating the improvement of overall performance in machine learning (ML) models, a critical strategy for optimizing data preparation is feature selection (FS). There has been a significant rise in the popularity of metaheuristic FS algorithms in recent times. This can be attributed to their proficiency in accurately identifying and selecting the most relevant features for ML tasks. This study presents three feature selection strategies that utilize metaheuristic algorithms. The methodologies mentioned include the Gravitational Search Optimization Algorithm (GSA), Emperor Penguin Optimization (EPO), and a hybrid approach of GSA and EPO referred to as hGSAEPO. Previous research has explored the use of baseline algorithms for feature selection in various ML tasks. However, there is a lack of investigation regarding their application specifically in breast cancer(BC) classification. A combination of these two has been utilized for the first occasion. The purpose of selecting BC as the study of investigation is due to the reason that this illness is recognized as the second most prevalent cause of mortality in the female population. If the condition is detected in its initial phases, it can be remedied and can assist individuals in evading superfluous medical processes. The procedure of selecting relevant features holds significant importance in the purpose of predicting ailments like BC. The current research presents an innovative methodology that employs three soft-computing algorithms, EPO, GSA, and their proposed hybrid hGSAEPO to efficiently identify significant features while concurrently decreasing the occurrence of irrelevant ones, simplifying overall complexity and enhancing the accuracy. The utilization of these soft computing methodologies and six ML classifiers presents a viable framework for prognostic research through the classification of data instances on Wisconsin Diagnostic Breast Cancer (WDBC). The experimental findings of eight experiments conducted suggest that the suggested approach exhibits exceptional performance in the context of binary classification for BC by computing astounding results like precision of 0.9800, sensitivity of 0.9700, specificity of 0.9887, F1-score of 0.9539, area under the curve(AUC) surpassing 0.998, with an accuracy of 98.31%. We achieved our objectives by presenting a dependable clinical prediction system for healthcare professionals for efficient diagnosis. [ABSTRACT FROM AUTHOR]

Visual observation and dermoscopic analysis are the most common methods of diagnosing skin cancer. In advanced stages, melanomas spread faster and are less responsive to treatment. Because different lesions in the skin appear similar to one another and sometimes errors in identification occur, the accuracy of diagnosis will decrease significantly when the amount of received images is large. However, the proposed methods for estimating skin lesions and their separation from melanoma have uncertainties and are not generalizable. This paper proposes an optimal decision tree (DT)-based approach, including fuzzy-ID3-pValue and Bayes learning algorithms, which overcomes these challenges. When classifying images, DTs employ a multi-stage procedure to partition the feature space, which enhances their ease of use, precision, and speed. Inference engines are used in fuzzy logic to derive logical deductions about knowledge, which facilitates learning DT and Bayesian learning. Taking advantage of the DT dependency structure, we present a novel fuzzy DT for extracting precise and collaborative fuzzy rules. Furthermore, to emphasize the cohesive nature of the laws, a weighted method is employed. Besides, the inference engine system is constructed through deductive and inductive inference engines. The proposed method is verified using the ISIC-2019 dataset as well as the PH2 images, both of which contain dermoscopic images of multiple lesions. The proposed method provides efficient results with 96% and 88% accuracy for ISIC-2019 and PH2 data, respectively. [ABSTRACT FROM AUTHOR]

Breast carcinoma or breast cancer is the most common type of cancer in women. It is very dangerous, and early detection is important for proper diagnosis and reduction of mortality rate. Cancer starts in a benign state, and if there is no proper treatment, it becomes malignant. Computer-aided diagnosis (CAD) techniques can be used for early detection of cancers. These techniques can significantly and effectively help in the diagnosis of cancer. Deep learning is the most popular technique used for accurate data analysis. It is also a powerful tool for categorizing histopathological images of breast cancer and analyzing breast cell shapes and densities. This paper proposes a hybrid EfficientNet with an SVM to categorize breast mass density with consideration of tumor types. (i.e., malignant or benign). In this hybrid, EfficientNet, the mammography images are applied to EfficientNet, and then the classification is carried out using a Support Vector Machine (SVM). The proposed model achieved accuracy of 94.48%, precision of 94.79%, specificity of 99.21%, Precision of 94.79%, FPR of 0.79%, score of 94.45%, MCC of 93.78%, and Kappa of 74.76%. The model outperformed state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

Microaneurysms (MAs) are small, circular, red lesions typically observed in the initial stage of Diabetic Retinopathy (DR). DR is a degenerative eye condition resulting from diabetes mellitus that can lead to vision loss if not detected and treated early. Since MAs are one of the first visible signs of DR, detecting them can lead to early diagnosis and treatment of DR and potentially prevent severe vision loss. In this survey, we conduct a thorough review and analyze the published literature on automated detection and segmentation of MAs, with the aim of bolstering ophthalmologists capabilities in the early screening and management of DR. Section 2 provides an overview of publicly available datasets that include image-level and pixel-level annotations of MAs. Benchmarking plays a vital role in the precise assessment of the efficacy of early DR detection systems. Section 3 presents common metrics used to benchmark the performance of MA recognition technologies. We categorize MA recognition methodologies into two principal groups: those based on image processing and those leveraging deep learning techniques. Sections 4 and 5 meticulously enumerate the cutting-edge techniques for MA detection and segmentation. Our discussion also delves into recent advancements and explores prospective future directions in this field. In conclusion, the evolution of machine learning and computer vision has enabled automated MA recognition methods to exhibit considerable potential, marking a significant stride forward in the fight against DR-related vision loss. [ABSTRACT FROM AUTHOR]

Pneumonia is a serious inflammatory disease that causes lung ulcers, and it is one of the leading reasons for pediatric death in the world. Chest X-rays are perhaps the most commonly utilized modalities to recognize pneumonia. Generally, the illness could be analyzed by a specialist radiologist. But for some reason, the diagnosis may be subjective. Thus, the physicians must be guided by computer-aided diagnosis frameworks in this challenging task. In this study, we propose a combined deep learning architecture to identify pneumonia in chest radiography images. We first, use Adaptive Median Filter for images enhancement, then we employ a regularized Convolutional Neural Network for features extraction, and then we use Long Short Term Memory as a classifier. Finally, the attention mechanism is used to direct the network attention to relevant features. The suggested approach was tested on two publicly available pneumonia X-ray datasets provided by Kermany and the Radiological Society of North America. On the Kermany and RSNA datasets, the suggested technique attained accuracy rates of 99.91% and 88.86%, respectively. In the last stage of our experiments, we employed a Grad-CAM-based color visualization technique to precisely interpret the detection of pneumonia in radiological images. The results outperformed those of state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Problem: Leishmaniasis is a disease caused by protozoan parasites of the genus Leishmania and has a high prevalence and impact on global health. Currently, the available drugs for its treatment have drawbacks, such as high toxicity, resistance of the parasite, and high cost. Therefore, the search for new, more effective, and safe drugs is a priority. The effectiveness of an anti-leishmanial drug is analyzed through in vitro studies in which a technician manually counts the intracellular form of the parasite (amastigote) within macrophages, which is slow, laborious, and prone to errors. Objective(s): To develop a computational system that facilitates the detection and counting of amastigotes in microscopy images obtained from in vitro studies using image processing techniques. Methodology: Segmentation of objects in the microscope image that might be Leishmania amastigotes was performed using the multilevel Otsu method on the saturation component of the hue, saturation, and intensity color model. In addition, morphological operations and the watershed transform combined with the weighted external distance transform were used to separate clustered objects. Then positive (amastigote) objects were detected (and consequently counted) using a classifier algorithm, the selection of which as well as the definition of the features to be used were also part of this research. MATLAB was used for the development of the system. Results and discussion: The results were evaluated in terms of sensitivity, precision, and the F-measure and suggested a favorable effectiveness of the proposed method. Conclusions: This system can help researchers by allowing large volumes of images of amastigotes to be counted using an automatic image analysis technique. [ABSTRACT FROM AUTHOR]

Lung cancer (LC) is a life-threatening and dangerous disease all over the world. However, earlier diagnoses and treatment can save lives. Earlier diagnoses of malevolent cells in the lungs responsible for oxygenating the human body and expelling carbon dioxide due to significant procedures are critical. Even though a computed tomography (CT) scan is the best imaging approach in the healthcare sector, it is challenging for physicians to identify and interpret the tumour from CT scans. LC diagnosis in CT scan using artificial intelligence (AI) can help radiologists in earlier diagnoses, enhance performance, and decrease false negatives. Deep learning (DL) for detecting lymph node contribution on histopathological slides has become popular due to its great significance in patient diagnoses and treatment. This study introduces a computer-aided diagnosis for LC by utilizing the Waterwheel Plant Algorithm with DL (CADLC-WWPADL) approach. The primary aim of the CADLC-WWPADL approach is to classify and identify the existence of LC on CT scans. The CADLC-WWPADL method uses a lightweight MobileNet model for feature extraction. Besides, the CADLC-WWPADL method employs WWPA for the hyperparameter tuning process. Furthermore, the symmetrical autoencoder (SAE) model is utilized for classification. An investigational evaluation is performed to demonstrate the significant detection outputs of the CADLC-WWPADL technique. An extensive comparative study reported that the CADLC-WWPADL technique effectively performs with other models with a maximum accuracy of 99.05% under the benchmark CT image dataset. [ABSTRACT FROM AUTHOR]

Recently, multi-modal vision-language foundation models have gained significant attention in the medical field. While these models offer great opportunities, they still face crucial challenges, such as the requirement for fine-grained knowledge understanding in computer-aided diagnosis and the capability of utilizing very limited or even no task-specific labeled data in real-world clinical applications. In this study, we present MaCo, a masked contrastive chest X-ray foundation model that tackles these challenges. MaCo explores masked contrastive learning to simultaneously achieve fine-grained image understanding and zero-shot learning for a variety of medical imaging tasks. It designs a correlation weighting mechanism to adjust the correlation between masked chest X-ray image patches and their corresponding reports, thereby enhancing the model's representation learning capabilities. To evaluate the performance of MaCo, we conducted extensive experiments using 6 well-known open-source X-ray datasets. The experimental results demonstrate the superiority of MaCo over 10 state-of-the-art approaches across tasks such as classification, segmentation, detection, and phrase grounding. These findings highlight the significant potential of MaCo in advancing a wide range of medical image analysis tasks. Multi-modal foundation models are increasingly important in medical applications. Here, authors show a masked contrastive chest X-ray model that achieves fine-grained image understanding and zero-shot capabilities, outperforming existing methods [ABSTRACT FROM AUTHOR]

Computer Aided Detection (CAD) has been used to help readers find cancers in mammograms. Although these automated systems have been shown to help cancer detection when accurate, the presence of CAD also leads to an over-reliance effect where miss errors and false alarms increase when the CAD system fails. Previous research investigated CAD systems which overlayed salient exogenous cues onto the image to highlight suspicious areas. These salient cues capture attention which may exacerbate the over-reliance effect. Furthermore, overlaying CAD cues directly on the mammogram occludes sections of breast tissue which may disrupt global statistics useful for cancer detection. In this study we investigated whether an over-reliance effect occurred with a binary CAD system, which instead of overlaying a CAD cue onto the mammogram, reported a message alongside the mammogram indicating the possible presence of a cancer. We manipulated the certainty of the message and whether it was presented only to indicate the presence of a cancer, or whether a message was displayed on every mammogram to state whether a cancer was present or absent. The results showed that although an over-reliance effect still occurred with binary CAD systems miss errors were reduced when the CAD message was more definitive and only presented to alert readers of a possible cancer. [ABSTRACT FROM AUTHOR]

Purpose: Susceptibility map weighted imaging (SMWI), based on quantitative susceptibility mapping (QSM), allows accurate nigrosome-1 (N1) evaluation and has been used to develop Parkinson’s disease (PD) deep learning (DL) classification algorithms. Neuromelanin-sensitive (NMS) MRI could improve automated quantitative N1 analysis by revealing neuromelanin content. This study aimed to compare classification performance of four approaches to PD diagnosis: (1) N1 quantitative “QSM-NMS” composite marker, (2) DL model for N1 morphological abnormality using SMWI (“Heuron IPD”), (3) DL model for N1 volume using SMWI (“Heuron NI”), and (4) N1 SMWI neuroradiological evaluation. Method: PD patients (n = 82; aged 65 ± 9 years; 68% male) and healthy-controls (n = 107; 66 ± 7 years; 48% male) underwent 3 T midbrain MRI with T2*-SWI multi-echo-GRE (for QSM and SMWI), and NMS-MRI. AUC was used to compare diagnostic performance. We tested for correlation of each imaging measure with clinical parameters (severity, duration and levodopa dosing) by Spearman-Rho or Kendall-Tao-Beta correlation. Results: Classification performance was excellent for the QSM-NMS composite marker (AUC = 0.94), N1 SMWI abnormality (AUC = 0.92), N1 SMWI volume (AUC = 0.90), and neuroradiologist (AUC = 0.98). Reasons for misclassification were right–left asymmetry, through-plane re-slicing, pulsation artefacts, and thin N1. In the two DL models, all 18/189 (9.5%) cases misclassified by Heuron IPD were controls with normal N1 volumes. We found significant correlation of the SN QSM-NMS composite measure with levodopa dosing (rho = −0.303, p = 0.006). Conclusion: Our data demonstrate excellent performance of a quantitative QSM-NMS marker and automated DL PD classification algorithms based on midbrain MRI, while suggesting potential further improvements. Clinical utility is supported but requires validation in earlier stage PD cohorts. [ABSTRACT FROM AUTHOR]

Purpose: The objective of this study was to determine the normative vestibulo- ocular reflex gain output values of the computerized rotational head impulse test (crHIT) with stationary visual targets (earth bound) in healthy participants in each decade age band of life: 10-19, 20-29, 30-39, 40-49, 50-59, 60-69, and 70+ years. Method: Seventy-seven community-dwelling participants (10-85 years of age) with normal lateral semicircular canal (SCC) functioning and no symptoms or history of vestibular dysfunction were recruited through convenience sampling and assessed with the crHIT using stationary targets. These participants were assessed using two standard protocols in a randomized order. Results: Results from 77 participants (Mage = 46 years; 43 women, 34 men) were analyzed. Pearson's correlation coefficient and simple linear regression indicated a statistically significant relationship between crHIT gain output and age (p >.05) for right gain, 1030°/s², and left gain, 1005°/s². Although a statistically significant relationship was found, the slope was minor, demonstrating that the clinical effect of age on crHIT gain output was insignificant. Furthermore, no statistically significant relationship exists between crHIT gain output and gender (p > .05). Age-dependent normative data were calculated using the 2.5th and 97.5th confidence interval (CI) percentile method. The responses of angular vestibulo-ocular reflex (aVOR) gain values for crHIT are expected to occur within the range for lower limit reference interval (RI) of 0.85-0.9 and upper limit RI of 1.11-1.18 for 1030°/s² and lower limit RI of 0.86-0.92 and upper limit RI of 1.13-1.16 for 1005°/s² .It can be expected that 90% CI of the population with normal lateral SCC function- ing will have aVOR gain values that fall within this range. Conclusion: Despite a statistically significant relationship that exists with aVOR gain output and age, the changes are minor, declining by 0.0088 units per 10 years, justifying the same normative data for all decade age bands. [ABSTRACT FROM AUTHOR]

The article discusses the importance of implementing transparency and auditing in machine learning (ML) systems used for clinical decision-making to ensure ethical and reliable use. Topics discussed include the necessity of transparency in ML system design, the role of mandatory auditing to assess system performance, and the need for enforceable regulations to complement ethical guidelines in healthcare AI tools.

To avoid irreversible vision loss, early detection and diagnosis of Diabetic Retinopathy (DR) severity is critical. The percentage of people undertaking eye examinations has risen in recent years, increasing the burden on Ophthalmologists. Various Artificial Intelligence (AI) screening systems have recently been deployed to improve the accuracy of DR diagnosis. However, owing to their black-box nature, most successful AI screening systems are still held back in reality for medical decision aid. The need for an Explainable Artificial Intelligence (XAI) screening system to help Ophthalmologists in DR diagnosis is inevitable. The proposed work is divided into three phases: (i) pre-processing, (ii) optic disk localization, and (iii) DR severity classification. On top of the deep learning model, the proposed work implements a Local Interpretable Model-agnostic Explanations (LIME) explainer to describe what features of the retinal image took part in justifying the predictions. The proposed framework outputs a pixel-value tensor, explaining the possible pixel values contributing to the model's prediction. MESSIDOR data collection is used for experimental analysis. When compared with other deep learning models, the proposed framework achieved a better accuracy of 98.04%, sensitivity of 99.69%, specificity of 96.37%, f1-score of 96.99% and error rate of 3.60%. Incorporating explainable deep learning models for diabetic retinopathy severity grading improves diagnostic accuracy and provides clinicians with clear insights, enabling trust and informed decision-making in DR diagnosis. This proposed technique enormously advances more effective and responsible healthcare procedures. [ABSTRACT FROM AUTHOR]

Brain tumor classification is a significant issue in computer aided diagnosis to make a convenient treatment. Deep learning techniques are surpassing traditional brain tumor classification methods in the medical image field with advanced hardware technology. In this article, a novel classification framework has been proposed that includes pre-trained fine-tuned EfficientNet B7. The framework focuses on a multi-class classification problem to distinguish among three common types of brain tumors, i.e., gliomas, meningiomas, and pituitary tumors. The proposed classification framework is trained and tested using six optimization algorithms SGD, RMSProp, Adagrad, Adam, Adadelta, and Nadam using two classifiers softmax and support vector machine (SVM). The best performance achieved by Nesterov-accelerated adaptive moment estimation (Nadam) optimizer using softmax classifier with test accuracy 99 % , average precision 99.3 % , average recall 97.3 % and average F1-score 98 % which outperformed other state-of-the-art architectures on Figshare MRI image data set. The proposed framework has also been evaluated, and performance has been compared using two more publicly available standard four-class brain tumor MRI data sets. [ABSTRACT FROM AUTHOR]

Medical image datasets are essential for training models used in computer-aided diagnosis, treatment planning, and medical research. However, some challenges are associated with these datasets, including variability in data distribution, data scarcity, and transfer learning issues when using models pre-trained from generic images. This work studies the effect of these challenges at the intra- and inter-domain level in few-shot learning scenarios with severe data imbalance. For this, we propose a methodology based on Siamese neural networks in which a series of techniques are integrated to mitigate the effects of data scarcity and distribution imbalance. Specifically, different initialization and data augmentation methods are analyzed, and four adaptations to Siamese networks of solutions to deal with imbalanced data are introduced, including data balancing and weighted loss, both separately and combined, and with a different balance of pairing ratios. Moreover, we also assess the inference process considering four classifiers, namely Histogram, kNN, SVM, and Random Forest. Evaluation is performed on three chest X-ray datasets with annotated cases of both positive and negative COVID-19 diagnoses. The accuracy of each technique proposed for the Siamese architecture is analyzed separately. The results are compared to those obtained using equivalent methods on a state-of-the-art CNN, achieving an average F1 improvement of up to 3.6%, and up to 5.6% of F1 for intra-domain cases. We conclude that the introduced techniques offer promising improvements over the baseline in almost all cases and that the technique selection may vary depending on the amount of data available and the level of imbalance. [ABSTRACT FROM AUTHOR]

As artificial intelligence (AI) assisted diagnosing systems become accessible and user-friendly, evaluating how first-year medical students perceive such systems holds substantial importance in medical education. This study aimed to assess medical students' perceptions of an AI-assisted diagnostic tool known as 'Glass AI.' Data was collected from first year medical students enrolled in a 1.5-week Cell Physiology pre-clerkship unit. Students voluntarily participated in an activity that involved implementation of Glass AI to solve a clinical case. A questionnaire was designed using 3 domains: 1) immediate experience with Glass AI, 2) potential for Glass AI utilization in medical education, and 3) student deliberations of AI-assisted diagnostic systems for future healthcare environments. 73/202 (36.10%) of students completed the survey. 96% of the participants noted that Glass AI increased confidence in the diagnosis, 43% thought Glass AI lacked sufficient explanation, and 68% expressed risk concerns for the physician workforce. Students expressed future positive outlooks involving AI-assisted diagnosing systems in healthcare, provided strict regulations, are set to protect patient privacy and safety, address legal liability, remove system biases, and improve quality of patient care. In conclusion, first year medical students are aware that AI will play a role in their careers as students and future physicians. [ABSTRACT FROM AUTHOR]

Objective: Accurately predicting knee osteoarthritis (KOA) is essential for early detection and personalized treatment. We aimed to develop and test a magnetic resonance imaging (MRI)‐based joint space (JS) radiomic model (RM) to predict radiographic KOA incidence through neural networks by integrating meniscus and femorotibial cartilage radiomic features. Methods: In the Osteoarthritis Initiative cohort, participants with knees without radiographic KOA at baseline but at high risk for radiographic KOA were included. Patients' knees developed radiographic KOA, whereas control knees did not over four years. We randomly split the participants into development and test cohorts (8:2) and extracted features from baseline three‐dimensional double‐echo steady‐state sequence MRI. Model performance was evaluated using an area under the receiver operating characteristic curve (AUC), sensitivity, and specificity in both cohorts. Nine resident surgeons performed the reader experiment without/with the JS‐RM aid. Results: Our study included 549 knees in the development cohort (275 knees of patients with KOA vs 274 knees of controls) and 137 knees in the test cohort (68 knees of patients with KOA vs 69 knees of controls). In the test cohort, JS‐RM had a favorable accuracy for predicting the radiographic KOA incidence with an AUC of 0.931 (95% confidence interval [CI] 0.876–0.963), a sensitivity of 84.4% (95% CI 83.9%–84.9%), and a specificity of 85.6% (95% CI 85.2%–86.0%). The mean specificity and sensitivity of resident surgeons through MRI reading in predicting radiographic KOA incidence were increased from 0.474 (95% CI 0.333–0.614) and 0.586 (95% CI 0.429–0.743) without the assistance of JS‐RM to 0.874 (95% CI 0.847–0.901) and 0.812 (95% CI 0.742–0.881) with JS‐RM assistance, respectively (P < 0.001). Conclusion: JS‐RM integrating the features of the meniscus and cartilage showed improved predictive values in radiographic KOA incidence. [ABSTRACT FROM AUTHOR]

Atrial fibrillation (AF) is a life-threatening cardiac condition caused by inadequate blood flow, resulting in abnormal ECG records, blood clotting, and cardioembolic strokes. In recent years, physicians have been particularly concerned with early detection and diagnosis to overcome cardiogenic stroke. AF can be easily identified at the initial stages due to the development in computer-aided diagnosis. The performance of this method is affected by noise and the variations in pattern of the ECG, which leads to false diagnosis. Current signal processing and shallow machine learning (ML) approaches are severely limited in their ability to detect this condition accurately. Deep neural networks have been shown to be extremely effective at learning nonlinear patterns in a wide variety of problems, which include computer vision tasks. Deep learning models are computationally costly, non-explainable, and require a large quantity of data to discover characteristics. In contrast, ML approaches are explainable and require good feature extraction. In this manuscript, ML based supervised classification method is developed based on feature ensembling. ECG signals are preprocessed (mean subtraction followed by Butterworth filtering and computation of RR intervals) and subjected to feature extraction (by entropy-, wavelets-, & statistical-features). The variations due to AF are effectively captured and selective features are ensembled to perform classification by SVM and KNN. This method is experimented on five different databases (such as: PAF prediction Challenge, Long-Term AF, Intracardiac, AF termination Challenge, and MIT-BIH atrial fibrillation) and the classification performance is found to be the highest compared to the state of art. To evaluate the effectiveness of the proposed technique, AF-specific characteristics are retrieved from the ECG signal in the presence of artificially added noise and the features are fed to classifiers for classification. Performance of the proposed method is compared with the deep learning based approaches. The graphical abstract of the proposed atrial fibrillation detection method is presented. The overall accuracy of the proposed method was found to be 91.88 % and 91.99 % for wavelets-SVM and ensemble wavelet-SVM, respectively. This model attained 100 % accuracy for entropy and statistical features with SVM and KNN, respectively. [ABSTRACT FROM AUTHOR]

Automatic pancreas detection and cropping with high precision from medical images is an important yet challenging problem for medical image analysis and Computer-Aided Diagnosis (CAD). Factors relating to the limited availability of image data and segmentation methodology hinder this task. High variability in the location of the pancreas,which occupies a very small area of the pancreatic Computed Tomography (CT) scans,and the anatomy of organs also add to the list of issues. These challenges necessitate an urgent need for the development of localization and auto-cropping methods of the region of interest (ROI). This paper presents the results obtained by the implementation of Region-based Convolutional Neural Network (RCNN)-Crop inspired by the Region Proposal Network (RPN) and Feature Pyramid Network (FPN) to localize the pancreas by building bounding boxes and auto-crop the ROI obtained from various other organs in the pancreatic CT scans and has a Mean Average Precision (mAP) of 28.10% for the dataset provided. [ABSTRACT FROM AUTHOR]

Ultrasound image examination has become the preferred choice for diagnosing metabolic dysfunction-associated steatotic liver disease (MASLD) due to its non-invasive nature. Computer-aided diagnosis (CAD) technology can assist doctors in avoiding deviations in the detection and classification of MASLD. We propose a hybrid model that integrates the pre-trained VGG16 network with an attention mechanism and a stacking ensemble learning model, which is capable of multi-scale feature aggregation based on the self-attention mechanism and multi-classification model fusion (Logistic regression, random forest, support vector machine) based on stacking ensemble learning. The proposed hybrid method achieves four classifications of normal, mild, moderate, and severe fatty liver based on ultrasound images. Our proposed hybrid model reaches an accuracy of 91.34% and exhibits superior robustness against interference, which is better than traditional neural network algorithms. Experimental results show that, compared with the pre-trained VGG16 model, adding the self-attention mechanism improves the accuracy by 3.02%. Using the stacking ensemble learning model as a classifier further increases the accuracy to 91.34%, exceeding any single classifier such as LR (89.86%) and SVM (90.34%) and RF (90.73%). The proposed hybrid method can effectively improve the efficiency and accuracy of MASLD ultrasound image detection. [ABSTRACT FROM AUTHOR]

Objectives: This study aims to develop computer-aided detection (CAD) for colorectal cancer (CRC) using abdominal CT based on a deep convolutional neural network. Methods: This retrospective study included consecutive patients with colorectal adenocarcinoma who underwent abdominal CT before CRC resection surgery (training set = 379, test set = 103). We customized the 3D U-Net of nnU-Net (CUNET) for CRC detection, which was trained with fivefold cross-validation using annotated CT images. CUNET was validated using datasets covering various clinical situations and institutions: an internal test set (n = 103), internal patients with CRC first determined by CT (n = 54) and asymptomatic CRC (n = 51), and an external validation set from two institutions (n = 60). During each validation, data from the healthy population were added (internal = 60; external = 130). CUNET was compared with other deep CNNs: residual U-Net and EfficientDet. The CAD performances were evaluated using per-CRC sensitivity (true positive/all CRCs), free-response receiver operating characteristic (FROC), and jackknife alternative FROC (JAFROC) curves. Results: CUNET showed a higher maximum per-CRC sensitivity than residual U-Net and EfficientDet (internal test set 91.3% vs. 61.2%, and 64.1%). The per-CRC sensitivity of CUNET at false-positive rates of 3.0 was as follows: internal CRC determined by CT, 89.3%; internal asymptomatic CRC, 87.3%; and external validation, 89.6%. CUNET detected 69.2% (9/13) of CRCs missed by radiologists and 89.7% (252/281) of CRCs from all validation sets. Conclusions: CUNET can detect CRC on abdominal CT in patients with various clinical situations and from external institutions. Key Points: • Customized 3D U-Net of nnU-Net (CUNET) can be applied to the opportunistic detection of colorectal cancer (CRC) in abdominal CT, helping radiologists detect unexpected CRC. • CUNET showed the best performance at false-positive rates ≥ 3.0, and 30.1% of false-positives were in the colorectum. CUNET detected 69.2% (9/13) of CRCs missed by radiologists and 87.3% (48/55) of asymptomatic CRCs. • CUNET detected CRCs in multiple validation sets composed of varying clinical situations and from different institutions, and CUNET detected 89.7% (252/281) of CRCs from all validation sets. [ABSTRACT FROM AUTHOR]

Rapid changes in artificial intelligence (AI) have already impacted the medical field. While the use of AI to assist medical diagnosis has been documented, AI is continually expanding within medical applications. AI applications in sonography and their effect on ultrasound examinations and sonographers are still indeterminate. Six papers were reviewed to investigate AI applications and effects within the sonography field. These papers provided results on a range of ultrasound applications including breast, obstetric, skin lesions, carotid, blood flow and cardiac ultrasound imaging when combined with AI. In this narrative review, the application of AI demonstrated that accuracy and speed of clinical diagnosis can be improved. These six aspects of ultrasound imaging combined with AI demonstrated the potential to assist the operator and clinicians with a diagnosis in various applications and settings. Additionally, AI can be beneficial to telehealth applications for rural and remote areas where healthcare access can be limited. These changes are opportunities to assist with medical care to provide benefits to patients, sonographers and clinicians as AI transitions to a positive integration within many aspects of clinical care. [ABSTRACT FROM AUTHOR]

Medical image registration is a crucial step in computer-assisted medical diagnosis, and has seen significant progress with the adoption of deep learning methods like convolutional neural networks (CNN). Creating a deep learning network for image registration is complex because humans can't easily prepare or supervise the training data unless it's very basic. This article presents an innovative approach to unsupervised deep learning-based multilevel image registration approach. We propose to develop a CNN to detect the geometric features, such as edges and thin structures, from images using a loss function derived from the Blake-Zisserman energy. This method enables the detection of discontinuities at different scales without relying on labeled data. Subsequently, we use this geometric information extracted from the input images, to define a second loss function and to perform our multimodal image registration process. Furthermore, we introduce a novel deep neural network architecture for multilevel image registration, offering enhanced precision and efficiency compared to traditional methods. Numerical simulations are employed to demonstrate the accuracy and relevance of our approach. We perform some numerical simulations to show the accuracy and the relevance of our approach for multimodal registration and its multilevel implementation. [ABSTRACT FROM AUTHOR]

The application of machine learning in the medical field has resulted in significant advancements in computer-aided pathological diagnosis. Multiple instance learning (MIL) has emerged as a promising approach for pathological image classification, particularly in scenarios where local annotations are lacking. However, current MIL models often overlook the importance of feature weights in the channel dimension and struggle with imbalanced positive and negative data. To address these limitations, an integration of a channel attention (CA) module and an augmented data (AUG) mechanism into the MIL model is proposed, resulting in improved performance. The CA module dynamically assigns weights to example features in the channel dimension, enhancing or suppressing features adaptively. Additionally, the AUG mechanism effectively balances the distribution of positive and negative data, significantly reducing false negatives. Through ablation experiments, the contributions of the CA module and AUG mechanism in enhancing the overall model performance are analyzed. Experimental validations on the CAMELYON16/17 public pathological image datasets demonstrate that the proposed model and method outperform existing approaches, with particular emphasis on reducing false negatives. Highlights: While multiple instance learning (MIL) models address scarce local annotations in pathological images, existing methods often neglect feature weights in the channel dimension and struggle with imbalanced data. This study introduces a novel approach by proposing a channel attention (CA) module and data augmentation mechanism for integration into the MIL model, significantly improving its performance. By conducting carefully designed ablation experiments, this study probes into the precise contributions of the introduced CA module and data augmentation mechanism towards enhancing the performance of the MIL model. Through validation on public datasets reveals that the proposed method excels over the latest methods by notably reducing false negatives, thereby enhancing sensitivity metrics. [ABSTRACT FROM AUTHOR]

The research on chemical process fault diagnosis has made significant progress, but there is still a big gap in its application to complex practical industrial processes. As for the fault diagnosis of batch crystallization processes, the recently‐proposed dynamic time warping–convolutional neural network (DTW‐CNN) model has achieved a great improvement in the fault diagnosis. However, its fault diagnosis rate (FDR) and timeliness of fault diagnosis are still low, and thus, it needs to improve further before being applied to the practical application. In this paper, a multiple pattern representation–convolutional neural network (MPR‐CNN) model is proposed and applied for the fault diagnosis of a semi‐batch crystallization process. The MPR‐CNN model enables the manual extraction of features with four pattern representation algorithms in the data pre‐processing stage, and generates a three‐dimensional matrix which is used as the training sample and input to the CNN for the formal feature extraction and weight learning. An excellent classification performance, with an average FDR of 97.5%, is achieved. This model is also applied for the fault diagnosis of process data within a shorter period of time after the occurrence of faults. The results indicate that the model could make timely fault diagnosis with a highly stable and accurate performance after the occurrence of a fault. [ABSTRACT FROM AUTHOR]

The article offers news briefs related to the dental nursing industry. Topics include Dental Defence Union's call for reform in clinical negligence costs, highlighting the unsustainable nature of current litigation expenses; the disproportionate legal costs in dental negligence claims, the impact on National Health Service resources, and proposals for fixed recoverable costs to address these issues.

Computer-aided diagnosis has been slow to develop in the field of oral ulcers. One of the major reasons for this is the lack of publicly available datasets. However, oral ulcers have cancerous lesions and their mortality rate is high. The ability to recognize oral ulcers at an early stage in a timely and effective manner is a very critical issue. In recent years, although there exists a small group of researchers working on these, the datasets are private. Therefore to address this challenge, in this paper a multi-tasking oral ulcer dataset (Autooral) containing two major tasks of lesion segmentation and classification is proposed and made publicly available. To the best of our knowledge, we are the first team to make publicly available an oral ulcer dataset with multi-tasking. In addition, we propose a novel modeling framework, HF-UNet, for segmenting oral ulcer lesion regions. Specifically, the proposed high-order focus interaction module (HFblock) performs acquisition of global properties and focus for acquisition of local properties through high-order attention. The proposed lesion localization module (LL-M) employs a novel hybrid sobel filter, which improves the recognition of ulcer edges. Experimental results on the proposed Autooral dataset show that our proposed HF-UNet segmentation of oral ulcers achieves a DSC value of about 0.80 and the inference memory occupies only 2029 MB. The proposed method guarantees a low running load while maintaining a high-performance segmentation capability. The proposed Autooral dataset and code are available from https://github.com/wurenkai/HF-UNet-and-Autooral-dataset. [ABSTRACT FROM AUTHOR]

Background: Alzheimer's disease (AD) is a progressive and irreversible neurodegenerative disorder that has become one of the major health concerns for the elderly. Computer-aided AD diagnosis can assist doctors in quickly and accurately determining patients' severity and affected regions. Methods: In this paper, we propose a method called MADNet for computer-aided AD diagnosis using multimodal datasets. The method selects ResNet-10 as the backbone network, with dual-branch parallel extraction of discriminative features for AD classification. It incorporates long-range dependenciesmodeling using attention scores in the decision-making layer and fuses the features based on their importance across modalities. To validate the effectiveness of our proposed multimodal classification method, we construct a multimodal dataset based on the publicly available ADNI dataset and a collected XWNI dataset, which includes examples of AD, Mild Cognitive Impairment (MCI), and Cognitively Normal (CN). Results: On this dataset, we conduct binary classification experiments of AD vs. CN and MCI vs. CN, and demonstrate that our proposed method outperforms other traditional single-modal deep learning models. Furthermore, this conclusion also confirms the necessity of using multimodal sMRI and DTI data for computer-aided AD diagnosis, as these twomodalities complement and convey information to each other. We visualize the feature maps extracted by MADNet using Grad-CAM, generating heatmaps that guide doctors' attention to important regions in patients' sMRI, which play a crucial role in the development of AD, establishing trust between human experts and machine learning models. Conclusion: We propose a simple yet effective multimodal deep convolutional neural network model MADNet that outperforms traditional deep learning methods that use a single-modality dataset for AD diagnosis. [ABSTRACT FROM AUTHOR]

Irrelevant salient distractors can trigger early quitting in visual search, causing observers to miss targets they might otherwise find. Here, we asked whether task-relevant salient cues can produce a similar early quitting effect on the subset of trials where those cues fail to highlight the target. We presented participants with a difficult visual search task and used two cueing conditions. In the high-predictive condition, a salient cue in the form of a red circle highlighted the target most of the time a target was present. In the low-predictive condition, the cue was far less accurate and did not reliably predict the target (i.e., the cue was often a false positive). These were contrasted against a control condition in which no cues were presented. In the high-predictive condition, we found clear evidence of early quitting on trials where the cue was a false positive, as evidenced by both increased miss errors and shorter response times on target absent trials. No such effects were observed with low-predictive cues. Together, these results suggest that salient cues which are false positives can trigger early quitting, though perhaps only when the cues have a high-predictive value. These results have implications for real-world searches, such as medical image screening, where salient cues (referred to as computer-aided detection or CAD) may be used to highlight potentially relevant areas of images but are sometimes inaccurate. Significance Statement: The present study examines how salient cues that sometimes highlight targets in visual search impact behavior. This is relevant for any type of visual search in which information from an initial reader is conveyed to a second human reader. The first reader may also be human, but in many cases artificial intelligence (AI) is used to make a first pass at identifying targets in a complex image. One example of this is in medical image screening, where computer-aided detection (CAD) signals are used to convey information from AI to a human observer. The negative effects that occur when these types of cues are false positives are not fully understood. In the present study, we find evidence to suggest that on the subset of trials in which cues are false positives, there are significant changes in strategy that cause participants to be more likely to miss targets that are present elsewhere. Moving forward, in any task in which information is conveyed from one searcher (human or not) to a second, human searcher, designers may want to consider alternative ways of highlighting information to avoid these early quitting effects. More research is needed to find out which alternative methods might be most effective. [ABSTRACT FROM AUTHOR]

This study aims to develop a super-resolution (SR) algorithm tailored specifically for enhancing the image quality and resolution of early cervical cancer (CC) magnetic resonance imaging (MRI) images. The proposed method is subjected to both qualitative and quantitative analyses, thoroughly investigating its performance across various upscaling factors and assessing its impact on medical image segmentation tasks. The innovative SR algorithm employed for reconstructing early CC MRI images integrates complex architectures and deep convolutional kernels. Training is conducted on matched pairs of input images through a multi-input model. The research findings highlight the significant advantages of the proposed SR method on two distinct datasets at different upscaling factors. Specifically, at a 2× upscaling factor, the sagittal test set outperforms the state-of-the-art methods in the PSNR index evaluation, second only to the hybrid attention transformer, while the axial test set outperforms the state-of-the-art methods in both PSNR and SSIM index evaluation. At a 4× upscaling factor, both the sagittal test set and the axial test set achieve the best results in the evaluation of PNSR and SSIM indicators. This method not only effectively enhances image quality, but also exhibits superior performance in medical segmentation tasks, thereby providing a more reliable foundation for clinical diagnosis and image analysis. [ABSTRACT FROM AUTHOR]

Medical image classification (IC) is a method for categorizing images according to the appropriate pathological stage. It is a crucial stage in computer-aided diagnosis (CAD) systems, which were created to help radiologists with reading and analyzing medical images as well as with the early detection of tumors and other disorders. The use of convolutional neural network (CNN) models in the medical industry has recently increased, and they achieve great results at IC, particularly in terms of high performance and robustness. The proposed method uses pre-trained models such as Dense Convolutional Network (DenseNet)-121 and Visual Geometry Group (VGG)-16 as feature extractor networks, bidirectional long short-term memory (BiLSTM) layers for temporal feature extraction, and the Support Vector Machine (SVM) and Random Forest (RF) algorithms to perform classification. For improved performance, the selected pre-trained CNN hyperparameters have been optimized using a modified grey wolf optimization method. The experimental analysis for the presented model on the Mammographic Image Analysis Society (MIAS) dataset shows that the VGG16 model is powerful for BC classification with overall accuracy, sensitivity, specificity, precision, and area under the ROC curve (AUC) of 99.86%, 99.9%, 99.7%, 97.1%, and 1.0, respectively, on the MIAS dataset and 99.4%, 99.03%, 99.2%, 97.4%, and 1.0, respectively, on the INbreast dataset. [ABSTRACT FROM AUTHOR]

The survival rate of lung cancer relies significantly on how far the disease has spread when it is detected, how it reacts to the treatment, the patient's overall health, and other factors. Therefore, the earlier the lung cancer diagnosis, the higher the survival rate. For radiologists, recognizing malignant lung nodules from computed tomography (CT) scans is a challenging and time-consuming process. As a result, computer-aided diagnosis (CAD) systems have been suggested to alleviate these burdens. Deep-learning approaches have demonstrated remarkable results in recent years, surpassing traditional methods in different fields. Researchers are currently experimenting with several deep-learning strategies to increase the effectiveness of CAD systems in lung cancer detection with CT. This work proposes a deep-learning framework for detecting and diagnosing lung cancer. The proposed framework used recent deep-learning techniques in all its layers. The autoencoder technique structure is tuned and used in the preprocessing stage to denoise and reconstruct the medical lung cancer dataset. Besides, it depends on the transfer learning pre-trained models to make multi-classification among different lung cancer cases such as benign, adenocarcinoma, and squamous cell carcinoma. The proposed model provides high performance while recognizing and differentiating between two types of datasets, including biopsy and CT scans. The Cancer Imaging Archive and Kaggle datasets are utilized to train and test the proposed model. The empirical results show that the proposed framework performs well according to various performance metrics. According to accuracy, precision, recall, F1-score, and AUC metrics, it achieves 99.60, 99.61, 99.62, 99.70, and 99.75%, respectively. Also, it depicts 0.0028, 0.0026, and 0.0507 in mean absolute error, mean squared error, and root mean square error metrics. Furthermore, it helps physicians effectively diagnose lung cancer in its early stages and allows specialists to improve the accuracy and consistency of workflow. [ABSTRACT FROM AUTHOR]

Ultrasound is a readily available, non-invasive and low-cost screening for the identification of endometriosis lesions, but its diagnostic specificity strongly depends on the experience of the operator. For this reason, computer-aided diagnosis tools based on Artificial Intelligence techniques can provide significant help to the clinical staff, both in terms of workload reduction and in increasing the overall accuracy of this type of examination and its outcome. However, although these techniques are spreading rapidly in a variety of domains, their application to endometriosis is still very limited. To fill this gap, we propose and evaluate a novel multi-scale ensemble approach for the automatic segmentation of endometriosis lesions from transvaginal ultrasounds. The peculiarity of the method lies in its high discrimination capability, obtained by combining, in a fusion fashion, multiple Convolutional Neural Networks trained on data at different granularity. The experimental validation carried out shows that: (i) the proposed method allows to significantly improve the performance of the individual neural networks, even in the presence of a limited training set; (ii) with a Dice coefficient of 82%, it represents a valid solution to increase the diagnostic efficacy of the ultrasound examination against such a pathology. [ABSTRACT FROM AUTHOR]

Objectives: Canine-induced root resorption (CIRR) is caused by impacted canines and CBCT images have shown to be more accurate in diagnosing CIRR than panoramic and periapical radiographs with the reported AUCs being 0.95, 0.49, and 0.57, respectively. The aim of this study was to use deep learning to automatically evaluate the diagnosis of CIRR in maxillary incisors using CBCT images. Methods: A total of 50 cone beam computed tomography (CBCT) images and 176 incisors were selected for the present study. The maxillary incisors were manually segmented and labeled from the CBCT images by two independent radiologists as either healthy or affected by root resorption induced by the impacted canines. We used five different strategies for training the model: (A) classification using 3D ResNet50 (Baseline), (B) classification of the segmented masks using the outcome of a 3D U-Net pretrained on the 3D MNIST, (C) training a 3D U-Net for the segmentation task and use its outputs for classification, (D) pretraining a 3D U-Net for the segmentation and transfer of the model, and (E) pretraining a 3D U-Net for the segmentation and fine-tuning the model with only the model encoder. The segmentation models were evaluated using the mean intersection over union (mIoU) and Dice coefficient (DSC). The classification models were evaluated in terms of classification accuracy, precision, recall, and F1 score. Results: The segmentation model achieved a mean intersection over union (mIoU) of 0.641 and a DSC of 0.901, indicating good performance in segmenting the tooth structures from the CBCT images. For the main classification task of detecting CIRR, Model C (classification of the segmented masks using 3D ResNet) and Model E (pretraining on segmentation followed by fine-tuning for classification) performed the best, both achieving 82% classification accuracy and 0.62 F1-scores on the test set. These results demonstrate the effectiveness of the proposed hierarchical, data-efficient deep learning approaches in improving the accuracy of automated CIRR diagnosis from limited CBCT data compared to the 3D ResNet baseline model. Conclusion: The proposed approaches are effective at improving the accuracy of classification tasks and are helpful when the diagnosis is based on the volume and boundaries of an object. While the study demonstrated promising results, future studies with larger sample size are required to validate the effectiveness of the proposed method in enhancing the medical image classification tasks. [ABSTRACT FROM AUTHOR]

Medical image registration is vital for disease diagnosis and treatment with its ability to merge diverse information of images, which may be captured under different times, angles, or modalities. Although several surveys have reviewed the development of medical image registration, they have not systematically summarized the existing medical image registration methods. To this end, a comprehensive review of these methods is provided from traditional and deep-learning-based perspectives, aiming to help audiences quickly understand the development of medical image registration. In particular, we review recent advances in retinal image registration, which has not attracted much attention. In addition, current challenges in retinal image registration are discussed and insights and prospects for future research provided. [ABSTRACT FROM AUTHOR]

Globally, eye disorders have been a major issue, especially in developing nations where resources for technology and financing are limited. Due to its tremendous feature learning ability, CNN has obtained remarkable progress in the area of fundus images. Through appropriate analysis and examination of fundus images, computer-aided diagnosis may yield information with a standard value for experts in clinical diagnosis or screening. However, the majority of earlier investigations have focused on the identification of a particular fundus disease, and the accurate fast classification of multiple fundus diseases remains a major challenge. Extremely numerous retinal fundus images must be analyzed to achieve a categorization that is reliable, fast, and precise. As a result, this research aims to propose a novel classification model for eye illnesses based on four major steps: (a) Pre-processing, (b) segmentation of blood vessels, (c) Extracting features and (d) Multi-classification of eye disease. In order to accurately classify the images, it is necessary to extract the essential informational characteristics from the segmented blood vessels. The categorization of eye diseases is carried out using a hybrid classifier that integrates the SqueezeNet and Long-Term Recurrent Convolutional Network (LRCN). We trained and validated our models using tenfold cross-validation tests on a database of fundus images including five categories: Normal, Retinitis Pigmentosa, Pathological Myopia, Maculopathy and Glaucoma. The efficacy of the presented approach is evaluated based on specificity, F1-score, recall, precision and accuracy of 98%, 97.8%, 97.6%, 98.4% and 98% respectively. [ABSTRACT FROM AUTHOR]

Pneumonia is an acute respiratory illness caused by viruses or bacteria. Early detection of pneumonia is important to ensure curative treatment and improve survival rates. Pneumonia detection on chest X-rays (CXR) is important for early diagnosis, effective treatment, monitoring patient progress, and managing public health concerns. It plays a vital role in ensuring that individuals with pneumonia receive the appropriate care they need while contributing to research and disease surveillance efforts. However, the examination of CXRs is a difficult process and is prone to subjective variabilities. The use of artificial intelligence (AI) and deep learning (DL) models can perform the detection and classification of pneumonia on CXR images. With this motivation, this study introduces a new Chaotic Sea Horse Optimization with Deep Learning Method for Pneumonia Detection and Classification (CSHODL-PDC) technique on CXR images. The main intention of the CSHODL-PDC algorithm lies in the automated detection and classification of pneumonia on CXR images. The CSHODL-PDC method initially designs a Gaussian filtering (GF) based noise eradication approach to eliminate the noise. In addition, the CSHODL-PDC technique employs the NASNetLarge model to produce a set of feature vectors. Moreover, an improved fuzzy deep neural network (FDNN) model is applied for the automated identification and classification of pneumonia. Finally, the CSHO algorithm selects the optimal hyperparameter values of the improved FDNN model, demonstrating the novelty of the work. A series of simulation analyses were performed on the CXR Pneumonia dataset from the Kaggle repository. The experimental values inferred the improved performance of the CSHODL-PDC method over recent models with a maximum accuracy of 99.22%, precision of 98.96%, and recall of 99.22%. Therefore, the proposed model can be employed for accurate and automated pneumonia detection. [ABSTRACT FROM AUTHOR]

Speech disorders are significant barriers to the balanced development of a child. Many children in Poland are affected by lisps (sigmatism)—the incorrect articulation of sibilants. Since speech therapy diagnostics is complex and multifaceted, developing computer-assisted methods is crucial. This paper presents the results of assessing the usefulness of hybrid feature vectors extracted based on multimodal (video and audio) data for the place of articulation assessment in sibilants /s/ and /ʂ/. We used acoustic features and, new in this field, visual parameters describing selected articulators' texture and shape. Analysis using statistical tests indicated the differences between various sibilant realizations in the context of the articulation pattern assessment using hybrid feature vectors. In sound /s/, 35 variables differentiated dental and interdental pronunciation, and 24 were visual (textural and shape). For sibilant /ʂ/, we found 49 statistically significant variables whose distributions differed between speaker groups (alveolar, dental, and postalveolar articulation), and the dominant feature type was noise-band acoustic. Our study suggests hybridizing the acoustic description with video processing provides richer diagnostic information. [ABSTRACT FROM AUTHOR]

At present, the early diagnosis of diabetic retinopathy (DR), a possible complication of diabetes due to elevated glucose concentrations in the blood, is usually performed by specialists using a manual inspection of high-resolution fundus images based on lesion screening, leading to problems such as high work-intensity and accessibility only in specialized health centers. To support the diagnosis of DR, we propose a deep learning-based (DL) DR lesion classification method through a knowledge distillation (KD) strategy. First, we use the pre-trained DL architecture, Inception-v3, as a teacher model to distill the dataset. Then, a student model, also using the Inception-v3 model, is trained on the distilled dataset to match the performance of the teacher model. In addition, a new combination of Kullback–Leibler (KL) divergence and categorical cross-entropy (CCE) loss is used to measure the difference between the teacher and student models. This combined metric encourages the student model to mimic the predictions of the teacher model. Finally, the trained student model is evaluated on a validation dataset to assess its performance and compare it with both the teacher model and another competitive DL model. Experiments are conducted on the two datasets, corresponding to an imbalanced and a balanced dataset. Two baseline models (Inception-v3 and YOLOv8) are evaluated for reference, obtaining a maximum training accuracy of 66.75% and 90.90%, respectively, and a maximum validation accuracy of 35.94% and 81.52%, both for the imbalanced dataset. On the other hand, the proposed DR classification model achieves an average training accuracy of 99.01% and an average validation accuracy of 97.30%, overcoming the baseline models and other state-of-the-art works. Experimental results show that the proposed model achieves competitive results in DR lesion detection and classification tasks, assisting in the early diagnosis of diabetic retinopathy. [ABSTRACT FROM AUTHOR]

Background: Ensuring accurate polyp detection during colonoscopy is essential for preventing colorectal cancer (CRC). Recent advances in deep learning-based computer-aided detection (CADe) systems have shown promise in enhancing endoscopists' performances. Effective CADe systems must achieve high polyp detection rates from the initial seconds of polyp appearance while maintaining low false positive (FP) detection rates throughout the procedure. Method: We integrated four open-access datasets into a unified platform containing over 340,000 images from various centers, including 380 annotated polyps, with distinct data splits for comprehensive model development and benchmarking. The REAL-Colon dataset, comprising 60 fullprocedure colonoscopy videos from six centers, is used as the fifth dataset of the platform to simulate clinical conditions for model evaluation on unseen center data. Performance assessment includes traditional object detection metrics and new metrics that better meet clinical needs. Specifically, by defining detection events as sequences of consecutive detections, we compute per-polyp recall at early detection stages and average per-patient FPs, enabling the generation of Free-Response Receiver Operating Characteristic (FROC) curves. Results: Using YOLOv7, we trained and tested several models across the proposed data splits, showcasing the robustness of our open-access platform for CADe system development and benchmarking. The introduction of new metrics allows for the optimization of CADe operational parameters based on clinically relevant criteria, such as per-patient FPs and early polyp detection. Our findings also reveal that omitting full-procedure videos leads to non-realistic assessments and that detecting small polyp bounding boxes poses the greatest challenge. Conclusion: This study demonstrates how newly available open-access data supports ongoing research progress in environments that closely mimic clinical settings. The introduced metrics and FROC curves illustrate CADe clinical efficacy and can aid in tuning CADe hyperparameters. [ABSTRACT FROM AUTHOR]