Classification Of Lesions Research Articles

Oncocytic Lesions of Salivary Glands: Morphological, Immunohistochemical, and Molecular Findings.

The fifth edition of the World Health Organization (WHO) classification introduces new diagnostic methods based on genetic alterations, providing insight into the molecular basis of lesions. As a result, the classification system has evolved, new entities have been introduced, and existing entities have been reclassified. Oncocytic lesions of salivary glands are a group of neoplastic conditions characterized bythe presence ofoncocytic cells. These lesions present a diagnostic challenge due to their overlapping histological features. Therefore, a comprehensive evaluation, including morphological, immunohistochemical, and molecular analysis, is crucial for accurate diagnosis and appropriate management. Accurate classification of salivary gland pathologies is essential for selecting the appropriate treatment methods and predicting outcomes. The introduction of new therapeutic approaches, such as targeted therapies for malignant salivary gland tumors, has improved patient outcomes. However, to effectively implement these therapies in clinical practice, a clear classification of lesions is necessary.

A new SVM solver applied to Skin Lesion Classification

A new SVM solver applied to Skin Lesion Classification

A scoping review of guidelines on caries management for children and young people to inform UK undergraduate core curriculum development

BackgroundCurrent evidence in cariology teaching is not consistently reflected in paediatric dentistry in the United Kingdom (UK). Many dental schools are not consistently teaching biological approaches to caries management, with outdated or complex methods being taught outwith the purview of general dental practitioners. This scoping review aimed to map current guidelines on the management of caries in children and young people. This is part of a work package to inform the consensus and development of a UK-wide caries management curriculum for paediatric dentistry.MethodsA search of electronic databases for peer reviewed literature was performed using Cochrane Library, MEDLINE via PubMed, TRIP Medical Database and Web of Science. Hand searching was undertaken for grey literature (citations of sources of evidence, websites of global organisations and Google Web Search™ (Google LLC, California, USA). Results from databases were screened independently, concurrently by two reviewers. Full texts were obtained, and reviewers met to discuss any disagreement for both database and hand searching.ResultsThis review identified 16 guidelines suitable for inclusion. After quality appraisal, eight were selected for synthesis and interpretation. Key themes included the shift towards selective caries removal and avoidance of complete caries removal unless in specific circumstances in anterior teeth. For “early lesions” in primary and permanent teeth with and without cavitation, several guidelines recommend biological management including site specific prevention and fissure sealants.ConclusionsThis review mapping current cariology guidelines for children and young people found gaps in the literature including classification of early carious lesions and management of early cavitated lesions. Areas identified for further exploration include integration of biological caries management into treatment planning, selective caries removal and whether pulpotomy is specialist-level treatment, requiring referral. These results will inform consensus recommendations in the UK, using Delphi methods.

Optimal fusion of features from decomposed ultrasound RF data with adaptive weighted ensemble classifier to improve breast lesion classification

Early diagnosis plays a crucial role in successful treatment of breast tumors and reduced mortality. In this study, considering the complementary advantages between features and combined with the improvement of classifiers, fusion of optimal complexity and texture features from decomposed ultrasound radio frequency (RF) data is proposed to improve breast lesion classification performance. In this method, three complexity features and four texture features were extracted from the ring regions of interest for breast lesions in all decomposed RF sub-images and their combinations. Selection techniques based on analysis of feature relevance, redundancy, and interaction (FRRI) were used to determine the optimal feature sets (FS–FRRI). Finally, three classifiers with the best performance (weighted k-nearest neighbor, bagged tree, Gaussian Naive Bayes (NB)) were selected based on FS-FRRI. The three classifiers were integrated using the bagging method, and each classifier was adaptively weighted according to the genetic algorithm during the integration to classify breast lesions. The proposed method was evaluated using the Open Access Series of Breast Ultrasonic Data, with 10-fold cross-validation. The experimental results demonstrated that optimal performance was obtained by the FS–FRRI-based adaptive weighted ensemble classifier, with an accuracy of 97%, a sensitivity of 99%, a specificity of 96%, and an area under the receiver operating curve value of 0.97. Fusion of optimal complexity and texture features from decomposed ultrasound RF data with an adaptive weighted ensemble classifier can help improve breast lesion classification performance, which has great potential to assist clinicians in accurate diagnosis of breast lesions.

Deep transfer CNNs models performance evaluation using unbalanced histopathological breast cancer dataset

Cancer is one of the top deadly diseases. Of this disease, around about 9.8 million death cause annually. It has been recorded by the American Cancer Society that every eight women die due to breast cancer in the USA. In this paper, we have identified eight different lesion categories: Benign Tumor: Adenosis-Adenoma, Fibro-Adenoma, Phyllodes-Tumor, Tubular-Adenoma, and Malignant Tumor; Ductal-Carcinoma, Lobular-Carcinoma, Mucinous-Carcinoma, Papillary-Carcinoma. The main contribution of this paper is to examine the performance of five pre-trained CNN models on an unbalanced cancer dataset for cancer prediction. The identification of different cancer tumors has been recognized by using transfer learning models namely ResNet50, ResNet101, ResNet152, VGG16, and VGG19. BreakHis dataset has four different magnifications (40x-100x-200x-400x), and used for experiments setup in this study. The total number of images for all magnification levels is 7909. The experimental results state that the pre-trained model Residual Net with different variations has worked well 91%~96% as compared to other pre-trained models. The ResNet101 architecture model has gained a multiclass identification higher than 95%. In this paper, the proposed methodology has different evaluation parameters such as accuracy, recall, and f1-score of all pre-trained models that will help to build optimal, and automated breast lesion multiclass identification.

Explainable deep inherent learning for multi-classes skin lesion classification

There is often a lack of explanation when artificial intelligence (AI) is used to diagnose skin lesions, which makes the physician unable to interpret and validate the output; thus, diagnostic systems become significantly less safe. In this paper, we proposed a deep inherent learning method to classify seven types of skin lesions. The proposed deep inherent learning was validated using different explanation techniques. Explainable AI (X-AI) was used to explain decision-making processes at the local and global levels. In addition, we provide visual information to help physicians trust the proposed method. The challenging dataset, HAM10000, was used to evaluate the proposed method. Medical practitioners can better understand the mechanisms of black-box AI models using our simple, stage-based X-AI framework. They can trust the proposed method because the rationale for its decisions is explained.

Feasibility of Near-Infrared Spectroscopy in the Classification of Pig Lung Lesions.

Respiratory diseases significantly affect intensive pig farming, causing production losses and increased antimicrobial use. Accurate classification of lung lesions is crucial for effective diagnostics and disease management. The integration of non-destructive and rapid techniques would be beneficial to enhance overall efficiency in addressing these challenges. This study investigates the potential of near-infrared (NIR) spectroscopy in classifying pig lung tissues. The NIR spectra (908-1676 nm) of 101 lungs from weaned pigs were analyzed using a portable instrument and subjected to multivariate analysis. Two distinct discriminant models were developed to differentiate normal (N), congested (C), and pathological (P) lung tissues, as well as catarrhal bronchopneumonia (CBP), fibrinous pleuropneumonia (FPP), and interstitial pneumonia (IP) patterns. Overall, the model tailored for discriminating among pathological lesions demonstrated superior classification performances. Major challenges arose in categorizing C lungs, which exhibited a misclassification rate of 30% with N and P tissues, and FPP samples, with 30% incorrectly recognized as CBP samples. Conversely, IP and CBP lungs were all identified with accuracy, precision, and sensitivity higher than 90%. In conclusion, this study provides a promising proof of concept for using NIR spectroscopy to recognize and categorize pig lungs with different pathological lesions, offering prospects for efficient diagnostic strategies.

Role of Multiparametric Magnetic Resonance Imaging and Targeted Biopsy in the Detection of Clinically Significant Prostate Cancer in Patients with Suspicious Digital Rectal Examination

Objectives: Few studies have examined the role of prostate MRI in patients with suspicious digital rectal examination (DRE) and/or PSA > 10 ng/mL. In a cohort of non-screened patients with suspicious DRE, we investigated the rate of avoidable prostate biopsies and potentially missed clinically significant prostate cancer (csPCa) with negative MRI, and the concordance between targeted biopsy (TBx) and systematic biopsy (SBx) in detecting csPCa with positive MRI. Methods: We retrospectively examined 199 biopsy-naïve patients with suspicious DRE who underwent prostate MRI before transperineal biopsy. Prostate Imaging—Reporting and Data System (PI-RADS) v2.1 ≥ 3 category of the index lesion defined a positive MRI. Combined TBx/SBx and SBx alone were performed for positive and negative MRI, respectively. An International Society of Urogenital Pathology Grade Group ≥ 2 defined csPCa. We calculated the csPCa detection rate of TBx, SBx, and combined TBx/SBx. The Cohen kappa statistic was used to measure the concordance between TBx and SBx. Results: Ninety-one (45.7%) csPCa cases were detected. MRI was positive in 153 (76.9%) patients. In the 46 patients with negative MRI, SBx detected 5 (10.9%) csPCa cases. Prostate biopsy could, thus, be avoided in 41/199 (20.6%) patients at the cost of missing 5/91 (5.5%) csPCa cases. The concordance between TBx and SBx in detecting csPCa with positive mpMRI was substantial (k = 0.70). Specifically, 6/86 (6.9%) csPCa cases were detected with TBx, and 17/86 (19.7%) with SBx alone. Concordance was almost perfect (k = 0.82) in patients with PSA > 10 ng/mL. Only 4/38 (10.5%) csPCa cases were missed by TBx, and only 1 (2.6%) csPCa case was identified by TBx alone. Conclusions: MRI in patients with suspicious DRE could avoid roughly 21% of unnecessary biopsies at the cost of missing approximately 6% of csPCa cases. Moreover, MRI and TBx complemented SBx in detecting csPCa in the subgroup with PSA > 10 ng/mL.

State-of-the-Art Hybrid Imaging of Neuroendocrine Neoplasms.

Neuroendocrine neoplasms (NENs) may be challenging to diagnose due to their small size and diverse anatomical locations. Hybrid imaging techniques, specifically positron emission tomography/computed tomography (PET/CT) and positron emission tomography/magnetic resonance imaging (PET/MRI), represent the current state-of-the-art for evaluating NENs. The preferred radiopharmaceuticals for NEN PET imaging are gallium-68 (68Ga) DOTA-peptides, which target somatostatin receptors (SSTR) overexpressed on NEN cells. Clinical applications of [68Ga]Ga-DOTA-peptides PET/CT include diagnosis, staging, prognosis assessment, treatment selection, and response evaluation. Fluorodeoxyglucose-18 (18F-FDG) PET/CT aids in detecting low-SSTR-expressing lesions and helps in patient stratification and treatment planning, particularly in grade 3 neuroendocrine tumors (NETs). New radiopharmaceuticals such as fluorine-labeled SSTR agonists and SSTR antagonists are emerging as alternatives to 68Ga-labeled peptides, offering improved detection rates and favorable biodistribution. The maturing of PET/MRI brings advantages to NEN imaging, including simultaneous acquisition of PET and MRI images, superior soft tissue contrast resolution, and motion correction capabilities. The PET/MRI with [68Ga]Ga-DOTA-peptides has demonstrated higher lesion detection rates and more accurate lesion classification compared to PET/CT. Overall, hybrid imaging offers valuable insights in the diagnosis, staging, and treatment planning of NENs. Further research is needed to refine response assessment criteria and standardize reporting guidelines.

A protocol for annotation of total body photography for machine learning to analyze skin phenotype and lesion classification.

Artificial Intelligence (AI) has proven effective in classifying skin cancers using dermoscopy images. In experimental settings, algorithms have outperformed expert dermatologists in classifying melanoma and keratinocyte cancers. However, clinical application is limited when algorithms are presented with 'untrained' or out-of-distribution lesion categories, often misclassifying benign lesions as malignant, or misclassifying malignant lesions as benign. Another limitation often raised is the lack of clinical context (e.g., medical history) used as input for the AI decision process. The increasing use of Total Body Photography (TBP) in clinical examinations presents new opportunities for AI to perform holistic analysis of the whole patient, rather than a single lesion. Currently there is a lack of existing literature or standards for image annotation of TBP, or on preserving patient privacy during the machine learning process. This protocol describes the methods for the acquisition of patient data, including TBP, medical history, and genetic risk factors, to create a comprehensive dataset for machine learning. 500 patients of various risk profiles will be recruited from two clinical sites (Australia and Spain), to undergo temporal total body imaging, complete surveys on sun behaviors and medical history, and provide a DNA sample. This patient-level metadata is applied to image datasets using DICOM labels. Anonymization and masking methods are applied to preserve patient privacy. A two-step annotation process is followed to label skin images for lesion detection and classification using deep learning models. Skin phenotype characteristics are extracted from images, including innate and facultative skin color, nevi distribution, and UV damage. Several algorithms will be developed relating to skin lesion detection, segmentation and classification, 3D mapping, change detection, and risk profiling. Simultaneously, explainable AI (XAI) methods will be incorporated to foster clinician and patient trust. Additionally, a publicly released dataset of anonymized annotated TBP images will be released for an international challenge to advance the development of new algorithms using this type of data. The anticipated results from this protocol are validated AI-based tools to provide holistic risk assessment for individual lesions, and risk stratification of patients to assist clinicians in monitoring for skin cancer.

Artificial intelligence-driven enhanced skin cancer diagnosis: leveraging convolutional neural networks with discrete wavelet transformation

BackgroundArtificial intelligence (AI) has shown great promise in the field of healthcare as a means of improving the diagnosis of skin cancer. The objective of this research is to enhance the precision and effectiveness of skin cancer identification by the incorporation of convolutional neural networks (CNNs) and discrete wavelet transformation (DWT). Making use of AI-driven techniques has the potential to completely transform the diagnosis process by providing quicker and more accurate evaluations of skin lesions. In an effort to improve dermatology and give physicians reliable resources for early and precise skin cancer diagnosis, this work explores the combination of CNNs with DWT.MethodsThe accurate and timely classification of skin cancer lesions plays a crucial role in early diagnosis and effective treatment. In this, we propose a novel approach for skin cancer classification using discrete wavelet transformation (DWT). The DWT is employed to extract relevant features from skin lesion images, which are then used to train a classification model. The effectiveness of the suggested approach is assessed through the examination of a dataset of skin lesion images with known classes (malignant or benign).ResultsThe outcomes of the experiment demonstrate that the suggested model successfully attained a classification result of sensitivity as 94% and specificity as 91% when compared with artificial neural network (ANN) and multilayer perceptron methods.ConclusionsThe HAM 10000 dataset is employed to explore and evaluate the effectiveness of the proposed model, leading to improved accuracy compared to the existing machine learning algorithms in utilization. The results demonstrate the effectiveness of the DWT-based approach in accurately classifying skin cancer lesions, thus aiding in early detection and diagnosis.

Neuroanatomical correlates of gross manual dexterity in children with unilateral spastic cerebral palsy.

Unilateral spastic Cerebral Palsy (UCP) results from congenital brain injury, and Magnetic Resonance Imaging (MRI) has a role in understanding the etiology and severity of brain insult. In UCP, functional impairment predominantly occurs in the upper limb (UL) of the more affected side, where manual ability and dexterity are typically reduced. Also, mirror movements (MMs), are often present in UCP, with a further possible negative functional impact. This study aims to investigate the relationships among neuroanatomical characteristics of brain injury at MRI, manual functional impairment and MMs, in children with UCP. Thirty-five children with UCP participated in the study (20, M = 15, F, mean age 9.2 ± 3.5 years). Brain lesions at MRI were categorized according to the Magnetic Resonance Classification System (MRICS) and by using a semi-quantitative MRI (sqMRI) scale. Gross manual performance was assessed through Manual Ability Classification System (MACS) and the Box and Block Test (BBT), and MMs by Woods and Teuber scale, for both hands. Non-parametric correlation analyses were run to determine the relationship between neuroanatomical and functional features. Regression models were run to explore the contribution of neuroanatomical features and MMs to UL function. Correlation analyses revealed moderate to strong associations between sqMRI scores contralateral to the more affected side and UL functional impairment on MACS and BBT, with more severe brain injuries significantly correlating with poorer function in the more affected hand. No association emerged between brain lesion severity scores and MMs. MRICS showed no association with MACS or BBT, while a significant correlation emerged between MRICS category and MMs in the more affected hand, with brain lesion category that are suggestive of presumed earlier injury being associated with more severe MMs. Finally, exploratory regression analyses showed that neuroanatomical characteristics of brain injury and MMs contributed to the variability of UL functional impairment. This study contributes to the understanding of the neuroanatomical and neurological correlates of some aspects of manual functional impairment in UCP by using a simple clinical brain MRI assessment.

AI Applications to Breast MRI: Today and Tomorrow.

In breast imaging, there is an unrelenting increase in the demand for breast imaging services, partly explained by continuous expanding imaging indications in breast diagnosis and treatment. As the human workforce providing these services is not growing at the same rate, the implementation of artificial intelligence (AI) in breast imaging has gained significant momentum to maximize workflow efficiency and increase productivity while concurrently improving diagnostic accuracy and patient outcomes. Thus far, the implementation of AI in breast imaging is at the most advanced stage with mammography and digital breast tomosynthesis techniques, followed by ultrasound, whereas the implementation of AI in breast magnetic resonance imaging (MRI) is not moving along as rapidly due to the complexity of MRI examinations and fewer available dataset. Nevertheless, there is persisting interest in AI-enhanced breast MRI applications, even as the use of and indications of breast MRI continue to expand. This review presents an overview of the basic concepts of AI imaging analysis and subsequently reviews the use cases for AI-enhanced MRI interpretation, that is, breast MRI triaging and lesion detection, lesion classification, prediction of treatment response, risk assessment, and image quality. Finally, it provides an outlook on the barriers and facilitators for the adoption of AI in breast MRI. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 6.

Prediction of longitudinal clinical outcomes after acute myocardial infarction using a dynamic machine learning algorithm.

Several regression-based models for predicting outcomes after acute myocardial infarction (AMI) have been developed. However, prediction models that encompass diverse patient-related factors over time are limited. This study aimed to develop a machine learning-based model to predict longitudinal outcomes after AMI. This study was based on a nationwide prospective registry of AMI in Korea (n = 13,104). Seventy-seven predictor candidates from prehospitalization to 1 year of follow-up were included, and six machine learning approaches were analyzed. Primary outcome was defined as 1-year all-cause death. Secondary outcomes included all-cause deaths, cardiovascular deaths, and major adverse cardiovascular event (MACE) at the 1-year and 3-year follow-ups. Random forest resulted best performance in predicting the primary outcome, exhibiting a 99.6% accuracy along with an area under the receiver-operating characteristic curve of 0.874. Top 10 predictors for the primary outcome included peak troponin-I (variable importance value = 0.048), in-hospital duration (0.047), total cholesterol (0.047), maintenance of antiplatelet at 1 year (0.045), coronary lesion classification (0.043), N-terminal pro-brain natriuretic peptide levels (0.039), body mass index (BMI) (0.037), door-to-balloon time (0.035), vascular approach (0.033), and use of glycoprotein IIb/IIIa inhibitor (0.032). Notably, BMI was identified as one of the most important predictors of major outcomes after AMI. BMI revealed distinct effects on each outcome, highlighting a U-shaped influence on 1-year and 3-year MACE and 3-year all-cause death. Diverse time-dependent variables from prehospitalization to the postdischarge period influenced the major outcomes after AMI. Understanding the complexity and dynamic associations of risk factors may facilitate clinical interventions in patients with AMI.

Clinical guidelines for prevention, diagnostics, treatment and recovery from acute radiation injuries: classification and basic pathology

The provision of state guarantees to citizens with medical care is achieved by compliance with clinical recommendations by medical organizations. However, acute diseases (conditions) caused by excess radiation were excluded from the relevant pathologies for the development of appropriate clinical recommendations. The current events increase the relevance of acute radiation pathology for the healthcare system and determine the high risk of such cases among the personnel of radiation-hazardous facilities and population. The necessity of developing national clinical guidelines for the prevention, diagnosis, treatment, and rehabilitation of acute radiation injury victims is substantiated. Based on an analytical review of the databases of NEB, PubMed, and Medline for 1970 to 2023 on the problem of prevention, diagnosis, treatment, and rehabilitation of individuals exposed to excess radiation and analysis of the regulatory framework governing the process of creating clinical recommendations in the Russian Federation on the provision of medical care to victims of acute radiation injuries, the main terms and their definitions relevant to acute radiation pathology were formulated, which must be unified when developing clinical recommendations. The basic classification of acute radiation lesions is presented, systematizing the variety of possible clinical forms of diseases (conditions) and their etiopathogenetic variants based on the characteristics of the types of ionizing radiation sources and individual characteristics of the conditions of acute radiation exposure. Variants of working clinical classifications of acute radiation lesions based on the generalization of the experience in the country and the world on the systematization of acute radiation pathology were determined. In general, the expediency of developing a group of clinical recommendations for the prevention, diagnosis, treatment, and rehabilitation of acute radiation injuries, covering all the various current clinical forms of diseases caused by excess (uncontrolled, unregulated, emergency) exposure, is justified. The task of determining the current list of diseases (conditions) and groups of diseases (conditions) caused by excessive human exposure in the dose range that can lead to the development of acute radiation lesions is of practical importance both for departmental medicine and the country’s healthcare system.

A hybrid Grasshopper optimization algorithm for skin lesion segmentation and melanoma classification using deep learning

Skin cancer can be detected through visual examination and confirmed through dermoscopic analysis and various diagnostic tests. This is because visual observation enables early detection of unique skin images by artificial intelligence. Promising outcomes are shown by several Convolution Neural Network (CNN)–based skin lesion classification systems that employ tagged skin images. This study suggests a practical approach for identifying skin cancers using dermoscopy pictures, improving specialists' ability to distinguish benign from malignant tumors. The Swarm Intelligence (SI) approach used dermoscopy photographs to locate lesions on the skin areas Region of interest (ROI). The Grasshopper Optimization technique produced the best segmentation outcomes. The Speed-Up Robust Features (SURF) approach is applied to extract features based on these findings. Two groups were created using the ISIC-2017, ISIC-2018, and PH-2 databases to categorize skin tumors. With an estimated accuracy in classification of 98.52%, preciseness of 96.73%, and Matthews Correlation Coefficient (MCC) of 97.04%, the suggested classification and segmentation methodologies have been evaluated for classification efficacy, specificity, sensitivity, F-measure, preciseness, the MCC, the dice coefficient, and Jaccard's index. In every performance indicator, the method we suggest outperformed state-of-the-art methods.

Computer-aided diagnostic system with automated deep learning method based on the AutoGluon framework improved the diagnostic accuracy of early esophageal cancer.

There have been studies on the application of computer-aided diagnosis (CAD) in the endoscopic diagnosis of early esophageal cancer (EEC), but there is still a significant gap from clinical application. We developed an endoscopic CAD system for EEC based on the AutoGluon framework, aiming to explore the feasibility of automatic deep learning (DL) in clinical application. The endoscopic pictures of normal esophagus, esophagitis, and EEC were collected from The First Affiliated Hospital of Soochow University (September 2015 to December 2021) and the Norwegian HyperKvasir database. All images of non-cancerous esophageal lesions and EEC in this study were pathologically examined. There were three tasks: task A was normal vs. lesion classification under non-magnifying endoscopy (n=932 vs. 1,092); task B was non-cancer lesion vs. EEC classification under non-magnifying endoscopy (n=594 vs. 429); and task C was non-cancer lesion vs. EEC classification under magnifying endoscopy (n=505 vs. 824). In all classification tasks, we took 100 pictures as the verification set, and the rest comprised as the training set. The CAD system was established based on the AutoGluon framework. Diagnostic performance of the model was compared with that of endoscopists grouped according to years of experience (senior >15 years; junior <5 years). Model evaluation indicators included accuracy, recall rate, precision, F1 value, interpretation time, and the area under the receiver operating characteristic (ROC) curve (AUC). In tasks A and B, the accuracies of medium-performance CAD and high-performance CAD were lower than those of junior doctors and senior doctors. In task C, the medium-performance and high-performance CAD accuracies were close to those of junior doctors and senior doctors. The high-performance CAD model outperformed the junior doctors in both task A (0.850 vs. 0.830) and task C (0.840 vs. 0.830) in sensitivity comparison, but there was still a large gap between high-performance CAD models and doctors in sensitivity comparison. In task A, with the aid of CAD pre-interpretation, the accuracy of junior and senior physicians were significantly improved (from 0.880 to 0.915 and from 0.920 to 0.945, respectively); the time spent on film reading was significantly shortened (junior: from 11.3 to 8.7 s; senior: from 6.7 to 5.5 s). In task C, with the aid of CAD pre-interpretation, the accuracy of junior and senior physicians were significantly improved (from 0.850 to 0.865 and from 0.915 to 0.935, respectively); the reading time was significantly shortened (junior: from 9.5 to 7.7 s; senior: from 5.6 to 3.0 s). The CAD system based on the AutoGluon framework can assist doctors to improve the diagnostic accuracy and reading time of EEC under endoscopy. This study reveals that automatic DL methods are promising in clinical application.

Diagnostic effectiveness of deep learning-based MRI in predicting multiple sclerosis: A meta-analysis.

The brain and spinal cord, constituting the central nervous system (CNS), could be impacted by an inflammatory disease known as multiple sclerosis (MS). The convolutional neural networks (CNN), a machine learning method, can detect lesions early by learning patterns on brain magnetic resonance image (MRI). We performed this study to investigate the diagnostic performance of CNN based MRI in the identification, classification, and segmentation of MS lesions. PubMed, Web of Science, Embase, the Cochrane Library, CINAHL, and Google Scholar were used to retrieve papers reporting the use of CNN based MRI in MS diagnosis. The accuracy, the specificity, the sensitivity, and the Dice Similarity Coefficient (DSC) were evaluated in this study. In total, 2174 studies were identified and only 15 articles met the inclusion criteria. The 2D-3D CNN presented a high accuracy (98.81, 95% CI: 98.50-99.13), sensitivity (98.76, 95% CI: 98.42-99.10), and specificity (98.67, 95% CI: 98.22-99.12) in the identification of MS lesions. Regarding classification, the overall accuracy rate was significantly high (91.38, 95% CI: 83.23-99.54). A DSC rate of 63.78 (95% CI: 58.29-69.27) showed that 2D-3D CNN-based MRI performed highly in the segmentation of MS lesions. Sensitivity analysis showed that the results are consistent, indicating that this study is robust. This metanalysis revealed that 2D-3D CNN based MRI is an automated system that has high diagnostic performance and can promptly and effectively predict the disease.

Image dermoscopy skin lesion classification using deep learning method: systematic literature review

Classifying skin lesions poses a significant challenge due to the distinctive characteristics and diverse shapes they can exhibit, particularly in identifying early-stage melanoma. To address the shortcomings of the prior method, a neural network-driven strategy was introduced to differentiate between two types of skin lesions based on dermoscopic images. This new approach comprises four key stages: i) initial image processing, ii) skin lesion segmentation, iii) feature extraction, and iv) classification using deep neural networks (DNNs). Computers can also provide more accurate diagnosis results. In the review process, the articles are analyzed and summarized to contribute to developing methods or application development in skin lesion diagnosis. The stages include defining the relevant theory, input data, methods used (architecture and modules), training process, and model evaluation. This review also explores information based on trends and users, emphasizing the skin lesion segmentation process, skin lesion classification process, and minimal datasets as recommendations for future research.

Detection and Classification of Hysteroscopic Images Using Deep Learning.

Although hysteroscopy with endometrial biopsy is the gold standard in the diagnosis of endometrial pathology, the gynecologist experience is crucial for a correct diagnosis. Deep learning (DL), as an artificial intelligence method, might help to overcome this limitation. Unfortunately, only preliminary findings are available, with the absence of studies evaluating the performance of DL models in identifying intrauterine lesions and the possible aid related to the inclusion of clinical factors in the model. To develop a DL model as an automated tool for detecting and classifying endometrial pathologies from hysteroscopic images. A monocentric observational retrospective cohort study was performed by reviewing clinical records, electronic databases, and stored videos of hysteroscopies from consecutive patients with pathologically confirmed intrauterine lesions at our Center from January 2021 to May 2021. Retrieved hysteroscopic images were used to build a DL model for the classification and identification of intracavitary uterine lesions with or without the aid of clinical factors. Study outcomes were DL model diagnostic metrics in the classification and identification of intracavitary uterine lesions with and without the aid of clinical factors. We reviewed 1500 images from 266 patients: 186 patients had benign focal lesions, 25 benign diffuse lesions, and 55 preneoplastic/neoplastic lesions. For both the classification and identification tasks, the best performance was achieved with the aid of clinical factors, with an overall precision of 80.11%, recall of 80.11%, specificity of 90.06%, F1 score of 80.11%, and accuracy of 86.74 for the classification task, and overall detection of 85.82%, precision of 93.12%, recall of 91.63%, and an F1 score of 92.37% for the identification task. Our DL model achieved a low diagnostic performance in the detection and classification of intracavitary uterine lesions from hysteroscopic images. Although the best diagnostic performance was obtained with the aid of clinical data, such an improvement was slight.