Search

BACKGROUND AND OBJECTIVES: Acute aortic dissection (AD) is a life-threatening condition in which early detection can significantly improve patient outcomes and survival. This study evaluates the clinical benefits of integrating a deep learning (DL)-based application for the automated detection and prioritization of AD on chest CT angiographies (CTAs) with a focus on the reduction in the scan-to-assessment time (STAT) and interpretation time (IT). MATERIALS AND METHODS: This retrospective Multi-Reader Multi-Case (MRMC) study compared AD detection with and without artificial intelligence (AI) assistance. The ground truth was established by two U.S. board-certified radiologists, while three additional expert radiologists served as readers. Each reader assessed the same CTAs in two phases: assessment unaided by AI assistance (pre-AI arm) and, after a 1-month washout period, assessment aided by device outputs (post-AI arm). STAT and IT metrics were compared between the two arms. RESULTS: This study included 285 CTAs (95 per reader, per arm) with a mean patient age of 58.5 years ±14.7 (SD), of which 52% were male and 37% had a prevalence of AD. AI assistance significantly reduced the STAT for detecting 33 true positive AD cases from 15.84 min (95% CI: 13.37-18.31 min) without AI to 5.07 min (95% CI: 4.23-5.91 min) with AI, representing a 68% reduction (p < 0.01). The IT also reduced significantly from 21.22 s (95% CI: 19.87-22.58 s) without AI to 14.17 s (95% CI: 13.39-14.95 s) with AI (p < 0.05). CONCLUSIONS: The integration of a DL-based algorithm for AD detection on chest CTAs significantly reduces both the STAT and IT. By prioritizing urgent cases, the AI-assisted approach outperforms the standard First-In, First-Out (FIFO) workflow.

Background/Objectives: Accurate detection and classification of blood cell types in microscopic images are crucial for diagnosing various hematological conditions. This study aims to develop and evaluate advanced architectures for automating blood cell detection and classification using the newly proposed YOLOv10 and YOLOv11 models, with a specific focus on identifying red blood cells (RBCs), white blood cells (WBCs), and platelets in microscopic images as a preliminary step of the complete blood count (CBC). Methods: The Blood Cell Count Detection (BCCD) dataset was enriched using data augmentation techniques to improve model robustness and diversity. Extensive experiments were performed, including complete weight initialization, advanced optimization strategies, and meticulous hyperparameter tuning for the YOLOv11 architecture. Results: The YOLOv11-l model achieved an overall mean Average Precision (mAP) of 93.8%, reflecting its robust accuracy across multiple blood cell types. Conclusions: The findings underscore the efficacy of the YOLOv11 architecture in automating blood cell classification with high precision, demonstrating its potential to enhance hematological analyses and support clinical diagnosis. [ABSTRACT FROM AUTHOR]

Mastering SQL programming skills is fundamental in computer science education, and Online Judging Systems (OJS) play a critical role in automatically assessing SQL codes, improving the accuracy and efficiency of evaluations. However, these systems are vulnerable to manipulation by students who can submit "cheating codes" that pass the tests without genuinely solving programming problems or demonstrating authentic SQL skills. This study analyzed over 5.8 million SQL codes validated by OJS and identified four types of cheating codes: Explicit Result Output, Quantitative Output Manipulation, Data-Observed Clause Manipulation, and DML-Driven Test Case Distortion. The initial experiment treated SQL codes as plain text using the Bag of Words vector model and processed them with six machine learning models to detect cheating. The results showed an average recall of 74.73% and precision of 97.10%, confirming the efficacy of automated detection. In the subsequent experiments, the first of these used 12 syntactic and semantic features of SQL codes, achieving a recall rate of 59.55% and precision of 87.26%. The final experiment added two more characteristic features of cheating codes to these models, significantly improving recall to 89.35% and precision to 95.25%. This highlights the importance of characteristic cheating features in identifying cheating codes. The study's findings deepen our understanding of cheating codes and contribute to enhancing online programming education and assessment quality. [ABSTRACT FROM AUTHOR]

Lung cancer is a leading cause of cancer-related deaths. Computer-aided detection (CAD) has emerged as a valuable tool to assist radiologists in the automated detection and segmentation of pulmonary nodules using Computed Tomography (CT) scans, indicating early stages of lung cancer. However, detecting small nodules remains challenging. This paper proposes novel techniques to address this challenge, achieving high sensitivity and low false-positive nodule identification using the RePoint-Net detection networks. Additionally, the 3DSqU2 Net, a novel nodule segmentation approach incorporating full-scale skip connections and deep supervision, is introduced. A 3DCNN model is employed for nodule candidate classification, generating final classification results by combining previous step outputs. Extensive training and testing on the LIDC/IDRI public lung CT database dataset validate the proposed model, demonstrating its superiority over human specialists with a remarkable 97.4% sensitivity in identifying nodule candidates. Moreover, CT texture analysis accurately differentiates between malignant and benign pulmonary nodules due to its ability to capture subtle tissue characteristic differences. This approach achieves a 95.8% sensitivity in nodule classification, promising non-invasive support for clinical decision-making in managing pulmonary nodules and improving patient outcomes. [ABSTRACT FROM AUTHOR]

Simple Summary: This study analyzed microbial contamination in mutton meat and during its slaughter process at four retail sites in Coimbatore, focusing on the total microbial load and prevalence of specific pathogens. Samples from mutton meat, cutting boards, hand swabs, knives, weighing balances, and water were collected. Mutton-washed water and mutton meat exhibited the highest microbial loads, particularly in terms of total plate count and coliforms. E. coli and Staphylococcus species were common, with automated identification revealing that most pathogens were of Staphylococcus origin. Salmonella was detected in 57% of the mutton samples using an automated identification system. Gas chromatography and mass spectrometry analysis of goat meat inoculated with pathogens identified distinct volatile and metabolite profiles, providing potential biomarkers for contamination. Multivariate statistical analysis further differentiated the volatile and metabolite profiles. These findings underscore the importance of cross-contamination during meat handling and suggest using volatile compounds for pathogen detection. Microbial contamination and the prevalence of foodborne pathogens in mutton meat and during its slaughtering process were investigated through microbial source tracking and automated pathogen identification techniques. Samples from mutton meat, cutting boards, hand swabs, knives, weighing balances, and water sources were collected from four different retail sites in Coimbatore. Total plate count (TPC), yeast and mold count (YMC), coliforms, E. coli, Pseudomonas aeruginosa, Salmonella, and Staphylococcus were examined across 91 samples. The highest microbial loads were found in the mutton-washed water, mutton meat, and cutting board samples. The automated pathogen identification system identified Staphylococcus species as the predominant contaminant and also revealed a 57% prevalence of Salmonella. Further analysis of goat meat inoculated with specific pathogens showed distinct volatile and metabolite profiles, identified using gas chromatography-mass spectrometry (GC-MS). Multivariate statistical analyses, including principal component analysis (PCA), orthogonal partial least squares discriminant analysis (OPLS-DA), and sparse partial least squares discriminant analysis (sPLS-DA), identified potential biomarkers for pathogen contamination. The results highlight the significance of cross-contamination in the slaughtering process and suggest the use of volatile compounds as potential biomarkers for pathogen detection. [ABSTRACT FROM AUTHOR]

Introduction: In recent years, artificial intelligence (AI) has emerged as a transformative tool for enhancing stroke diagnosis, aiding treatment decision making, and improving overall patient care. Leading AI-driven platforms such as RapidAI, Brainomix®, and Viz.ai have been developed to assist healthcare professionals in the swift and accurate assessment of stroke patients. Methods: Following the PRISMA guidelines, a comprehensive systematic review was conducted using PubMed, Embase, Web of Science, and Scopus. Characteristic descriptive measures were gathered as appropriate from all included studies, including the sensitivity, specificity, accuracy, and comparison of the available tools. Results: A total of 31 studies were included, of which 29 studies focused on detecting acute ischemic stroke (AIS) or large vessel occlusions (LVOs), and 2 studies focused on hemorrhagic strokes. The four main tools used were Viz.ai, RapidAI, Brainomix®, and deep learning modules. Conclusions: AI tools in the treatment of stroke have demonstrated usefulness for diagnosing different stroke types, providing high levels of accuracy and helping to make quicker and more precise clinical judgments. [ABSTRACT FROM AUTHOR]

Background: Neonatal seizures are diagnostically challenging and predominantly electrographic-only. Multichannel video continuous electroencephalography (cEEG) is the gold standard investigation, however, out-of-hours access to neurophysiology support can be limited. Automated seizure detection algorithms (SDAs) are designed to detect changes in EEG data, translated into user-friendly seizure probability trends. The aim of this study was to evaluate the diagnostic accuracy of the Persyst neonatal SDA in an intensive care setting. Methods: Single-centre retrospective service evaluation study in neonates undergoing cEEG during intensive care admission to Great Ormond Street Hospital (GOSH) between May 2019 and December 2022. Neonates with <44 weeks corrected gestational age, who had a cEEG recording duration >60 minutes, whilst inpatient in intensive care, were included in the study. One-hour cEEG clips were created for all cases (seizures detected) and controls (seizure-free) and analysed by the Persyst neonatal SDA. Expert neurophysiology reports of the cEEG recordings were used as the gold standard for diagnostic comparison. A receiver operating characteristic (ROC) curve was created using the highest seizure probability in each recording. Optimal seizure probability thresholds for sensitivity and specificity were identified. Results: Eligibility screening produced 49 cases, and 49 seizure-free controls. Seizure prevalence within those patients eligible for the study, was approximately 19% with 35% mortality. The most common case seizure aetiology was hypoxic ischaemic injury (35%) followed by inborn errors of metabolism (18%). The ROC area under the curve was 0.94 with optimal probability thresholds 0.4 and 0.6. Applying a threshold of 0.6, produced 80% sensitivity and 98% specificity. Conclusions: The Persyst neonatal SDA demonstrates high diagnostic accuracy in identifying neonatal seizures; comparable to the accuracy of the standard Persyst SDA in adult populations, other neonatal SDAs, and amplitude integrated EEG (aEEG). Overdiagnosis of seizures is a risk, particularly from cEEG recording artefact. To fully examine its clinical utility, further investigation of the Persyst neonatal SDA's accuracy is required, as well as confirming the optimal seizure probability thresholds in a larger patient cohort. [ABSTRACT FROM AUTHOR]

Purpose: The aim of this study was to systematically review the use of automated detection systems for identifying bone lesions based on CT and MRI, focusing on advancements in artificial intelligence (AI) applications. Materials and methods: A literature search was conducted on PubMed and MEDLINE. Data were extracted and grouped into three main categories, namely baseline study characteristics, model validation strategies, and the type of AI algorithms. Results: A total of 10 studies were selected and analyzed, including 2,768 patients overall with a median of 187 per study. These studies utilized various AI algorithms, predominantly deep learning models (6 studies) such as Convolutional Neural Networks. Among machine learning validation strategies, K-fold cross-validation was the mostly used (5 studies). Clinical validation was performed using data from the same institution (internal testing) in 8 studies and from both the same and different (external testing) institutions in 1 study, respectively. Conclusion: AI, particularly deep learning, holds significant promise in enhancing diagnostic accuracy and efficiency. However, the review highlights several limitations, such as the lack of standardized validation methods and the limited use of external datasets for testing. Future research should address these gaps to ensure the reliability and applicability of AI-based detection systems in clinical settings. [ABSTRACT FROM AUTHOR]

Abstract Background Post-weaning diarrhea (PWD) is a frequently occurring health and welfare issue in weaned piglets. Behavioral changes indicating impaired health may be detectable before the onset of signs and could be useful to detect the development of PWD early, enabling targeted and timely interventions. Current algorithms enable automated behavioral classification on the group level, while PWD may not affect all piglets in one pen and individual level analysis may be required. Therefore, this study aimed to assess whether changes in pen activity or individual piglet behavior can be early indicators of the occurrence of PWD. During 3 replicated rounds, 72 piglets (Sus scrofa domestica, Landrace x Large White) weaned at 27 days of age, were housed in 4 pens with 6 piglets each. Individual fecal color and consistency were scored (0–5; ≥ 3 considered as aberrant feces) six times during the first two weeks post-weaning using rectal swabs. Additionally, using a similar scoring scale, feces on the pen floor were assessed daily. Two methods were applied for behavioral scoring. Individual behaviors (eating, drinking, standing, walking; n = 48) were scored manually and instantaneously with a five-minute interval from videos of the first two rounds, while pen activity (eating, drinking, moving; n = 12) was analyzed automatically and continuously using a commercially available algorithm from videos of all three rounds. Results Piglets showing a relatively higher proportion of standing behavior one day before fecal scoring had increased odds of an aberrant fecal color score (odds ratio (OR): 4.8; 95% confidence interval (CI): 1.5–15.3). Furthermore, odds of aberrant colored feces increased in pens where piglets showed more moving activity two days before (OR: 6.14; 1.26

Background and Purpose: Paramagnetic rim lesions (PRLs) are an MRI biomarker of chronic inflammation in people with multiple sclerosis (MS). PRLs may aid in the diagnosis and prognosis of MS. However, manual identification of PRLs is time‐consuming and prone to poor interrater reliability. To address these challenges, the Automated Paramagnetic Rim Lesion (APRL) algorithm was developed to automate PRL detection. The primary objective of this study is to evaluate the accuracy of APRL for detecting PRLs in a multicenter setting. Methods: We applied APRL to a multicenter dataset, which included 3‐Tesla MRI acquired in 92 participants (43 with MS, 14 with clinically isolated syndrome [CIS]/radiologically isolated syndrome [RIS], 35 without RIS/CIS/MS). Subsequently, we assessed APRL's performance by comparing its results with manual PRL assessments carried out by a team of trained raters. Results: Among the 92 participants, expert raters identified 5637 white matter lesions and 148 PRLs. The automated segmentation method successfully captured 115 (78%) of the manually identified PRLs. Within these 115 identified lesions, APRL differentiated between manually identified PRLs and non‐PRLs with an area under the curve (AUC) of.73 (95% confidence interval [CI]: [.68,.78]). At the subject level, the count of APRL‐identified PRLs predicted MS diagnosis with an AUC of.69 (95% CI: [.57,.81]). Conclusion: Our study demonstrated APRL's capability to differentiate between PRLs and lesions without paramagnetic rims in a multicenter study. Automated identification of PRLs offers greater efficiency over manual identification and could facilitate large‐scale assessments of PRLs in clinical trials. [ABSTRACT FROM AUTHOR]

Florida manatees (Trichechus manatus latirostris) require frequent and extensive surveys to inform conservation efforts. Crewed aircraft surveys can be costly, dangerous, and logistically complex. Unoccupied aerial systems (UASs) can assist with these issues. While manual review of UAS imagery can be time- and laborintensive, automated detection of manatees in aerial survey footage can help. We present an object-based image analysis workflow for the automated detection and count of Florida manatees in Google Earth Engine, a free platform for research that allows for scripts and imagery sharing. Training and testing datasets were built from randomly extracted image frames from two stationary, unoccupied aerial system videos over thermal refugia. The workflow captured most manatees (93.98 to 95.62% recall; 4.38 to 6.03% false negative rate), but also counted many objects as manatees incorrectly (4.24 to 14.77% precision; 998.40 to 3,885.54% false positive over the detectable rate). Sun glint, mud plumes, and water close to shore were common causes of false positives. While the automated count was too high, the workflow lays markers over each detection, allowing for quick manual review for more accurate (semi-automated) counts. This study is an early step in automated detection tools for Florida manatees in a cloud-based platform. Future efforts could explore other platforms or may improve this workflow by including new classes for confounding objects. [ABSTRACT FROM AUTHOR]

• MELD algorithm has variable performance across novel pediatric/young adult datasets. • MELD algorithm has high sensitivity for FCDIIB. • MELD algorithm has high sensitivity for FCD Type II in neonatal/infantile patients. • MELD algorithm has clinical utility in simulated real world MRI-negative population. The purpose of this study was to evaluate the performance and generalizability of an automated, interpretable surface-based MRI classifier for the detection of focal cortical dysplasia. This was a retrospective cohort incorporating MRIs from the epilepsy surgery (FCD and MRI-negative) and neuroimaging (healthy controls) databases at Children's National Hospital (CNH), and a publicly-available FCD Type II dataset from Bonn, Germany. Clinical characteristics and outcomes were abstracted from patient records and/or existing databases. Subjects were included if they had 3T epilepsy-protocol MRI. Manually-segmented FCD masks were compared to the automated masks generated by the Multi-centre Epilepsy Lesion Detection (MELD) FCD detection algorithm. Sensitivity/specificity were calculated. From CNH, 39 FCD pharmacoresistant epilepsy (PRE) patients, 19 healthy controls, and 19 MRI-negative patients were included. From Bonn, 85 FCD Type II were included, of which 68 passed preprocessing. MELD had varying performance (sensitivity) in these datasets: CNH FCD-PRE (54 %); Bonn (68 %); MRI-negative (44 %). In multivariate regression, FCD Type IIB pathology predicted higher chance of MELD automated lesion detection. All four patients who underwent resection/ablation of MELD-identified clusters achieved Engel I outcome. We validate the performance of MELD automated, interpretable FCD classifier in a diverse pediatric cohort with FCD-PRE. We also demonstrate the classifier has relatively good performance in an independent FCD Type II cohort with pediatric-onset epilepsy, as well as simulated real-world value in a pediatric population with MRI-negative PRE. [ABSTRACT FROM AUTHOR]

• The first meta-analysis evaluating AI's diagnostic performance in detecting IED. • A minority of models validate their performance on external datasets. • Models validated with resampling methods outperformed those using external datasets. • Creating well-defined, multi-centric prospective labeled datasets is a priority. Interictal epileptiform discharges (IEDs) in electroencephalograms (EEGs) are an important biomarker for epilepsy. Currently, the gold standard for IED detection is the visual analysis performed by experts. However, this process is expert-biased, and time-consuming. Developing fast, accurate, and robust detection methods for IEDs based on EEG may facilitate epilepsy diagnosis. We aim to assess the performance of deep learning (DL) and classic machine learning (ML) algorithms in classifying EEG segments into IED and non-IED categories, as well as distinguishing whether the entire EEG contains IED or not. We systematically searched PubMed, Embase, and Web of Science following PRISMA guidelines. We excluded studies that only performed the detection of IEDs instead of binary segment classification. Risk of Bias was evaluated with Quality Assessment of Diagnostic Accuracy Studies (QUADAS-2). Meta-analysis with the overall area under the Summary Receiver Operating Characteristic (SROC), sensitivity, and specificity as effect measures, was performed with R software. A total of 23 studies, comprising 3,629 patients, were eligible for synthesis. Eighteen models performed discharge-level classification, and 6 whole-EEG classification. For the IED-level classification, 3 models were validated in an external dataset with more than 50 patients and achieved a sensitivity of 84.9 % (95 % CI: 82.3–87.2) and a specificity of 68.7 % (95 % CI: 7.9–98.2). Five studies reported model performance using both internal validation (cross-validation) and external datasets. The meta-analysis revealed higher performance for internal validation, with 90.4 % sensitivity and 99.6 % specificity, compared to external validation, which showed 78.1 % sensitivity and 80.1 % specificity. Meta-analysis showed higher performance for models validated with resampling methods compared to those using external datasets. Only a minority of models use more robust validation techniques, which often leads to overfitting. [ABSTRACT FROM AUTHOR]

Background: Post-weaning diarrhea (PWD) is a frequently occurring health and welfare issue in weaned piglets. Behavioral changes indicating impaired health may be detectable before the onset of signs and could be useful to detect the development of PWD early, enabling targeted and timely interventions. Current algorithms enable automated behavioral classification on the group level, while PWD may not affect all piglets in one pen and individual level analysis may be required. Therefore, this study aimed to assess whether changes in pen activity or individual piglet behavior can be early indicators of the occurrence of PWD. During 3 replicated rounds, 72 piglets (Sus scrofa domestica, Landrace x Large White) weaned at 27 days of age, were housed in 4 pens with 6 piglets each. Individual fecal color and consistency were scored (0–5; ≥ 3 considered as aberrant feces) six times during the first two weeks post-weaning using rectal swabs. Additionally, using a similar scoring scale, feces on the pen floor were assessed daily. Two methods were applied for behavioral scoring. Individual behaviors (eating, drinking, standing, walking; n = 48) were scored manually and instantaneously with a five-minute interval from videos of the first two rounds, while pen activity (eating, drinking, moving; n = 12) was analyzed automatically and continuously using a commercially available algorithm from videos of all three rounds. Results: Piglets showing a relatively higher proportion of standing behavior one day before fecal scoring had increased odds of an aberrant fecal color score (odds ratio (OR): 4.8; 95% confidence interval (CI): 1.5–15.3). Furthermore, odds of aberrant colored feces increased in pens where piglets showed more moving activity two days before (OR: 6.14; 1.26 < 95%CI < 29.84), which was also found for fecal consistency (OR: 4.77; 95%CI: 1.1–21.6). Conclusions: Our results indicate that increased standing in individual piglets and an increased moving activity on the pen level may be important behavioral indicators of PWD before the onset of diarrhea. Further development of current algorithms that can identify behavioral abnormalities in groups, from the pen to the individual level, may therefore be a promising avenue for improved and targeted health and welfare monitoring. [ABSTRACT FROM AUTHOR]

Pipeline networks are crucial components of modern infrastructure, and ensuring their reliable operation is essential for sustainable development. The percussion-based methods are considered promising for detecting pipeline faults due to their avoidance of constant-contact sensors and ease of implementation. However, the majority of existing percussion-based methods suffer from limitations such as the requirement for manual feature extraction, as well as subpar noise resilience and adaptability. This paper introduces a one-dimensional convolutional bidirectional long short-term memory network with wide first-layer kernels for the classification of percussion-induced acoustic signals, thus achieving automatic identification of pipeline leakage and water deposit conditions. This approach directly extracts features from audio signals using wide first-layer convolutional kernels, eliminating the need for manual feature extraction. Additionally, it employs bidirectional long short-term memory to effectively capture long-term signal dependencies from both past and future contexts. To validate the effectiveness of the method, two case studies were conducted on three groups of pipes. The results show that the proposed method demonstrates superior noise resistance and adaptability compared to other methods, and it also exhibits strong applicability to other percussion signal datasets. Additionally, the impact of different first convolutional kernel sizes on the noise resistance and adaptive performance of the model was investigated, which provides robust guidance for the effective processing of percussion-induced acoustic signals. [ABSTRACT FROM AUTHOR]

This study introduces an ensemble model designed for real-time monitoring of bedridden patients. The model was developed using a unique dataset, specifically acquired for this study, that captures six typical movements. The dataset was balanced using the Synthetic Minority Over-sampling Technique, resulting in a diverse distribution of movement types. Three models were evaluated: a Decision Tree Regressor, a Gradient Boosting Regressor, and a Bagging Regressor. The Decision Tree Regressor achieved an accuracy of 0.892 and an R2 score of 1.0 on the training dataset, and 0.939 on the test dataset. The Boosting Regressor achieved an accuracy of 0.908 and an R2 score of 0.99 on the training dataset, and 0.943 on the test dataset. The Bagging Regressor was selected due to its superior performance and trade-offs such as computational cost and scalability. It achieved an accuracy of 0.950, an R2 score of 0.996 for the training data, and an R2 score of 0.959 for the test data. This study also employs K-Fold cross-validation and learning curves to validate the robustness of the Bagging Regressor model. The proposed system addresses practical implementation challenges in real-time monitoring, such as data latency and false positives/negatives, and is designed for seamless integration with hospital IT infrastructure. This research demonstrates the potential of machine learning to enhance patient safety in healthcare settings. [ABSTRACT FROM AUTHOR]

Distributed Denial of Service (DDoS) attack is a severe type of attack. It affects the cloud in terms of loss of repudiation, service outage, financial loss, and data loss. Hence, the optimal feature selection and the hybrid learning-based classifier are developed for evading the normal function disruption in the cloud server. After pre-processing, the resultant data is subjected to the ensemble feature selection. The first feature is selected optimally by the Probability of Fitness-based Billiards-Inspired Optimization (PF-BIO) algorithm, the second feature selection is acquired through the Fisher discriminant, and the last feature selection is carried out by feature correlation with class. Consequently, the resultant of these feature selections is concatenated with the weight parameter to provide weighted fused features, where the weight is getting optimized by the PF-BIO algorithm. Finally, a newly developed hybrid-based learning model, where the Deep Belief Network with the Gated Recurrent Unit (DBN-GRU), in which the hyper parameters are tuned and optimized by the PF-BIO algorithm. Thus, the performance is compared with the existing approaches. Throughout the result analysis, the accuracy of the designed method is 97.05%. Hence, the proposed model proves the efficiency for the detection of DDoS attacks precisely. [ABSTRACT FROM AUTHOR]

Copyright of Scientific-Practical Journal of Medicine Vestnik KazNMU is the property of Asfendiyarov Kazakh National Medical University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The increasing availability and resolution of LiDAR data are revolutionizing landscape archaeology, enabling unprecedented large-scale studies. However, the time-intensive nature of manual analysis has posed significant challenges. This research tackles the complexities of large-scale archaeological site detection by integrating Artificial Intelligence (AI) with LiDAR data, focusing on hillforts across diverse European landscapes. A semi-automated workflow employing Convolutional Neural Networks (CNNs) was developed and tested across three regions – England, Hesse (Germany), and Molise (Italy) – covering a total area of 180,000 km2. The methodology utilized the Atlas of Hillforts of Britain and Ireland to train a CNN on LiDAR datasets and tested the model’s transferability to Germany and Italy. Techniques such as pseudo-labelling and fine-tuning addressed the “Model Drift” problem, improving region-specific performance. The AI classifier achieved F1 scores ranging from 34–38%, demonstrating its adaptability to diverse landscapes, including the Mediterranean terrain of Molise and Hesse’s densely forested regions. Case studies identified new potential hillforts in England and promising candidates in Hesse and Molise, underscoring the effectiveness of the approach. While automation significantly reduces manual workload, human verification remains critical for refining AI predictions and addressing false positives. This study also applies different expert validation workflows, emphasizing their efficiency and adaptability to regional differences. By combining automated detection with expert review, the research showcases the potential for scalable, AI-assisted archaeological discovery across diverse landscapes, providing a valuable tool for academic research and heritage management.

Lung cancer is a leading cause of cancer-related deaths. Computer-aided detection (CAD) has emerged as a valuable tool to assist radiologists in the automated detection and segmentation of pulmonary nodules using Computed Tomography (CT) scans, indicating early stages of lung cancer. However, detecting small nodules remains challenging. This paper proposes novel techniques to address this challenge, achieving high sensitivity and low false-positive nodule identification using the RePoint-Net detection networks. Additionally, the 3DSqU2 Net, a novel nodule segmentation approach incorporating full-scale skip connections and deep supervision, is introduced. A 3DCNN model is employed for nodule candidate classification, generating final classification results by combining previous step outputs. Extensive training and testing on the LIDC/IDRI public lung CT database dataset validate the proposed model, demonstrating its superiority over human specialists with a remarkable 97.4% sensitivity in identifying nodule candidates. Moreover, CT texture analysis accurately differentiates between malignant and benign pulmonary nodules due to its ability to capture subtle tissue characteristic differences. This approach achieves a 95.8% sensitivity in nodule classification, promising non-invasive support for clinical decision-making in managing pulmonary nodules and improving patient outcomes.

ObjectiveTo develop automated algorithms for the detection of posterior vitreous detachment (PVD) using OCT imaging.DesignEvaluation of a diagnostic test or technology.SubjectsOverall, 42 385 consecutive OCT images (865 volumetric OCT scans) obtained with Heidelberg Spectralis from 865 eyes from 464 patients at an academic retina clinic between October 2020 and December 2021 were retrospectively reviewed.MethodsWe developed a customized computer vision algorithm based on image filtering and edge detection to detect the posterior vitreous cortex for the determination of PVD status. A second deep learning (DL) image classification model based on convolutional neural networks and ResNet-50 architecture was also trained to identify PVD status from OCT images. The training dataset consisted of 674 OCT volume scans (33 026 OCT images), while the validation testing set consisted of 73 OCT volume scans (3577 OCT images). Overall, 118 OCT volume scans (5782 OCT images) were used as a separate external testing dataset.Main outcome measuresAccuracy, sensitivity, specificity, F1-scores, and area under the receiver operator characteristic curves (AUROCs) were measured to assess the performance of the automated algorithms.ResultsBoth the customized computer vision algorithm and DL model results were largely in agreement with the PVD status labeled by trained graders. The DL approach achieved an accuracy of 90.7% and an F1-score of 0.932 with a sensitivity of 100% and a specificity of 74.5% for PVD detection from an OCT volume scan. The AUROC was 89% at the image level and 96% at the volume level for the DL model. The customized computer vision algorithm attained an accuracy of 89.5% and an F1-score of 0.912 with a sensitivity of 91.9% and a specificity of 86.1% on the same task.ConclusionsBoth the computer vision algorithm and the DL model applied on OCT imaging enabled reliable detection of PVD status, demonstrating the potential for OCT-based automated PVD status classification to assist with vitreoretinal surgical planning.Financial disclosuresProprietary or commercial disclosure may be found after the references.

Abstract Background Learning to perform strabismus surgery is an essential aspect of ophthalmologists’ surgical training. Automated classification strategy for surgical steps can improve the effectiveness of training curricula and the efficient evaluation of residents’ performance. To this end, we aimed to develop and validate a deep learning (DL) model for automated detecting strabismus surgery steps in the videos. Methods In this study, we gathered 479 strabismus surgery videos from Shanghai Children’s Hospital, affiliated to Shanghai Jiao Tong University School of Medicine, spanning July 2017 to October 2021. The videos were manually cut into 3345 clips of the eight strabismus surgical steps based on the International Council of Ophthalmology’s Ophthalmology Surgical Competency Assessment Rubrics (ICO-OSCAR: strabismus). The videos dataset was randomly split by eye-level into a training (60%), validation (20%) and testing dataset (20%). We evaluated two hybrid DL algorithms: a Recurrent Neural Network (RNN) based and a Transformer-based model. The evaluation metrics included: accuracy, area under the receiver operating characteristic curve, precision, recall and F1-score. Results DL models identified the steps in video clips of strabismus surgery achieved macro-average AUC of 1.00 (95% CI 1.00–1.00) with Transformer-based model and 0.98 (95% CI 0.97-1.00) with RNN-based model, respectively. The Transformer-based model yielded a higher accuracy compared with RNN-based models (0.96 vs. 0.83, p

In the era of Internet informatization, a series of network attacks on Web applications have surfaced both domestically and internationally, thereby increasing the focus on network security. This paper presents the design and implementation of an automated tool based on improved web crawler technology, integrated with anti-crawler mechanisms and SQL injection vulnerability detection techniques, to tackle the challenges posed to network security. By comprehensively crawling website URLs and employing SQL injection vulnerability detection methods, the tool promptly identifies and facilitates the remediation of website vulnerabilities, thus preventing SQL injection attacks and protecting information security. The tool also employs a proxy IP rotation mechanism to enhance anti-crawling capabilities and improve crawling efficiency. Experimental results demonstrate the effectiveness of the tool in accurately crawling information and detecting SQL injection vulnerabilities, thereby ensuring the security of website information. [ABSTRACT FROM AUTHOR]

Current practices in traffic sign monitoring heavily rely on manual inspections, a method that is both time-consuming and prone to human error. This leads to inefficiencies in the management and maintenance of these critical roadside assets. The objective of this work is to overcome these limitations by proposing a method for automated change detection in traffic signs using low-density LiDAR data. The proposed solution integrates noise elimination, point cloud restructuring, and cross-scan KD-tree generation, followed by the application of unsupervised machine learning techniques for change identification. The effectiveness of this method was verified by testing across three different highways with varying point cloud resolutions. For robust testing, an algorithm was also designed to simulate a broad range of different damage scenarios in traffic signs of different types, sizes, and placements. Testing in different scenarios along almost 15 km of the road revealed impressive results with accuracy and F1 score metrics ranging from 92% to 100%. Moreover, the algorithm was also extremely efficient with an average runtime of just 115" per km of fully automated unattended processing. The change detection potential of the proposed algorithm extends beyond traffic signs, as it could be adapted for many highway elements, enhancing the efficiency of transportation asset management and highway maintenance programmes. The findings indicate that this approach not only fills a significant gap in the current traffic sign monitoring and asset management practice but also offers a promising, comprehensive solution towards automated, cost-effective, and precise monitoring and maintenance of traffic signs, thus addressing a major challenge in this area. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic has wreaked havoc on the whole world, taking over half a million lives and capsizing the world economy in unprecedented magnitudes. With the world scampering for a possible vaccine, early detection and containment are the only redress. Existing diagnostic technologies with high accuracy like RT-PCRs are expensive and sophisticated, requiring skilled individuals for specimen collection and screening, resulting in lower outreach. So, methods excluding direct human intervention are much sought after, and artificial intelligence-driven automated diagnosis, especially with radiography images, captured the researchers' interest. This survey marks a detailed inspection of the deep learning–based automated detection of COVID-19 works done to date, a comparison of the available datasets, methodical challenges like imbalanced datasets and others, along with probable solutions with different preprocessing methods, and scopes of future exploration in this arena. We also benchmarked the performance of 315 deep models in diagnosing COVID-19, normal, and pneumonia from X-ray images of a custom dataset created from four others. The dataset is publicly available at https://github.com/rgbnihal2/COVID-19-X-ray-Dataset. Our results show that DenseNet201 model with Quadratic SVM classifier performs the best (accuracy: 98.16%, sensitivity: 98.93%, specificity: 98.77%) and maintains high accuracies in other similar architectures as well. This proves that even though radiography images might not be conclusive for radiologists, but it is so for deep learning algorithms for detecting COVID-19. We hope this extensive review will provide a comprehensive guideline for researchers in this field. [ABSTRACT FROM AUTHOR]

Background: Learning to perform strabismus surgery is an essential aspect of ophthalmologists' surgical training. Automated classification strategy for surgical steps can improve the effectiveness of training curricula and the efficient evaluation of residents' performance. To this end, we aimed to develop and validate a deep learning (DL) model for automated detecting strabismus surgery steps in the videos. Methods: In this study, we gathered 479 strabismus surgery videos from Shanghai Children's Hospital, affiliated to Shanghai Jiao Tong University School of Medicine, spanning July 2017 to October 2021. The videos were manually cut into 3345 clips of the eight strabismus surgical steps based on the International Council of Ophthalmology's Ophthalmology Surgical Competency Assessment Rubrics (ICO-OSCAR: strabismus). The videos dataset was randomly split by eye-level into a training (60%), validation (20%) and testing dataset (20%). We evaluated two hybrid DL algorithms: a Recurrent Neural Network (RNN) based and a Transformer-based model. The evaluation metrics included: accuracy, area under the receiver operating characteristic curve, precision, recall and F1-score. Results: DL models identified the steps in video clips of strabismus surgery achieved macro-average AUC of 1.00 (95% CI 1.00–1.00) with Transformer-based model and 0.98 (95% CI 0.97-1.00) with RNN-based model, respectively. The Transformer-based model yielded a higher accuracy compared with RNN-based models (0.96 vs. 0.83, p < 0.001). In detecting different steps of strabismus surgery, the predictive ability of the Transformer-based model was better than that of the RNN. Precision ranged between 0.90 and 1 for the Transformer-based model and 0.75 to 0.94 for the RNN-based model. The f1-score ranged between 0.93 and 1 for the Transformer-based model and 0.78 to 0.92 for the RNN-based model. Conclusion: The DL models can automate identify video steps of strabismus surgery with high accuracy and Transformer-based algorithms show excellent performance when modeling spatiotemporal features of video frames. [ABSTRACT FROM AUTHOR]

ABSTRACT: The objective of this diagnostic accuracy study was to develop and validate an alert to identify calves at risk for a diarrhea bout using milk feeding behavior data (behavior) from automated milk feeders (AMF). We enrolled Holstein calves (n = 259) as a convenience sample size from 2 facilities that were health scored daily preweaning and offered either 10 or 15 L/d of milk replacer. For alert development, 132 calves were enrolled and the ability of milk intake, drinking speed, and rewarded visits collected from AMF to identify calves at risk for diarrhea was tested. Alerts that had high diagnostic accuracy in the alert development phase were validated using a holdout validation strategy of 127 different calves from the same facilities (all offered 15 L/d) for −3 to 1 d relative to diarrhea diagnosis. We enrolled calves that were either healthy or had a first diarrheal bout (loose feces ≥2 d or watery feces ≥1 d). Relative change and rolling dividends for each milk feeding behavior were calculated for each calf from the previous 2 d. Logistic regression models and receiver operator curves (ROC) were used to assess the diagnostic ability for relative change and rolling dividends behavior relative to alert d) to classify calves at risk for a diarrhea bout from −2 to 0 d relative to diagnosis. To maximize sensitivity (Se), alert thresholds were based on ROC optimal classification cutoff. Diagnostic accuracy was met when the alert had a moderate area under the ROC curve (≥0.70), high accuracy (Acc; ≥0.80), high Se (≥0.80), and very high precision (Pre; ≥0.85). For alert development, deviations in rolling dividend milk intake with drinking speed had the best performance (10 L/d: ROC area under the curve [AUC] = 0.79, threshold ≤0.70; 15 L/d: ROC AUC = 0.82, threshold ≤0.60). Our diagnostic criteria were only met in calves offered 15 L/d (10 L/d: Se 75%, Acc 72%, Pre 92%, specificity [Sp] 55% vs. 15 L/d: Se 91%, Acc 91%, Pre 89%, Sp 73%). For holdout validation, rolling dividend milk intake with drinking speed met diagnostic criteria for one facility (threshold ≤0.60, Se 86%, Acc 82%, Pre 94%, Sp 50%). However, no milk feeding behavior alerts met diagnostic criteria for the second facility due to poor Se (relative change milk intake −0.36 threshold, Se 71%, Acc 70%, and Pre 97%). We suggest that changes in milk feeding behavior may indicate diarrhea bouts in dairy calves. Future research should validate this alert in commercial settings; furthermore, software updates, support, and new analytics might be required for on-farm application to implement these types of alerts.

Cervical auscultation is a simple, noninvasive method for diagnosing dysphagia, although the reliability of the method largely depends on the subjectivity and experience of the evaluator. Recently developed methods for the automatic detection of swallowing sounds facilitate a rough automatic diagnosis of dysphagia, although a reliable method of detection specialized in the peculiar feature patterns of swallowing sounds in actual clinical conditions has not been established. We investigated a novel approach for automatically detecting swallowing sounds by a method wherein basic statistics and dynamic features were extracted based on acoustic features: Mel Frequency Cepstral Coefficients and Mel Frequency Magnitude Coefficients, and an ensemble learning model combining Support Vector Machine and Multi-Layer Perceptron were applied. The evaluation of the effectiveness of the proposed method, based on a swallowing-sounds database synchronized to a video fluorographic swallowing study compiled from 74 advanced-age patients with dysphagia, demonstrated an outstanding performance. It achieved an F1-micro average of approximately 0.92 and an accuracy of 95.20%. The method, proven effective in the current clinical recording database, suggests a significant advancement in the objectivity of cervical auscultation. However, validating its efficacy in other databases is crucial for confirming its broad applicability and potential impact. [ABSTRACT FROM AUTHOR]

Autonomous sensors provide opportunities to observe organisms across spatial and temporal scales that humans cannot directly observe. By processing large data streams from autonomous sensors with deep learning methods, researchers can make novel and important natural history discoveries. In this study, we combine automated acoustic monitoring with deep learning models to observe breeding-associated activity in the endangered Sierra Nevada yellow-legged frog (Rana sierrae), a behavior that current surveys do not measure. By deploying inexpensive hydrophones and developing a deep learning model to recognize breeding-associated vocalizations, we discover three undocumented R. sierrae vocalization types and find an unexpected temporal pattern of nocturnal breeding-associated vocal activity. This study exemplifies how the combination of autonomous sensor data and deep learning can shed new light on species' natural history, especially during times or in locations where human observation is limited or impossible. [ABSTRACT FROM AUTHOR]

Attention Deficit Hyperactivity Disorder (ADHD) is a frequent neurodevelopmental disorder in children that is commonly diagnosed subjectively. The objective detection of ADHD based on neuroimaging data has been a complex problem with low ranges of accuracy, possibly due to (among others) complex diagnostic processes, the high number of features considered and imperfect measurements in data collection. Hence, reliable neuroimaging biomarkers for detecting ADHD have been elusive. To address this problem we consider a recently proposed multi-model selection method called Sparse Wrapper AlGorithm (SWAG), which is a greedy algorithm that combines screening and wrapper approaches to create a set of low-dimensional models with good predictive power. While preserving the previous levels of accuracy, SWAG provides a measure of importance of brain regions for identifying ADHD. Our approach also provides a set of equallyperforming and simple models which highlight the main feature combinations to be analyzed and the interactions between them. Taking advantage of the network of models resulting from this approach, we confirm the relevance of the frontal and temporal lobes as well as highlight how the different regions interact to detect the presence of ADHD. In particular, these results are fairly consistent across different learning mechanisms employed within the SWAG (i.e. logistic regression, linear and radial-kernel support vector machines) thereby providing population-level insights, as well as delivering feature combinations that are smaller and often perform better than those that would be used if employing their original versions directly. [ABSTRACT FROM AUTHOR]

• Introducing three-dimension convolutional neural network can improve the performance of automated detection of focal cortical dysplasia. • Introducing positron emission tomography data aids in detecting lesions of focal cortical dysplasia. • Automated detection of focal cortical dysplasia with high sensitivity and few false-positive findings is feasible based on multi-modal data. Purpose: Focal cortical dysplasia (FCD) is a common etiology of drug-resistant focal epilepsy. Visual identification of FCD is usually time-consuming and depends on personal experience. Herein, we propose an automated type II FCD detection approach utilizing multi-modal data and 3D convolutional neural network (CNN). Methods: MRI and positron emission tomography (PET) data of 82 patients with FCD were collected, including 55 (67.1%) histopathologically, and 27 (32.9%) radiologically diagnosed patients. Three types of morphometric feature maps and three types of tissue maps were extracted from the T1-weighted images. These maps, T1, and PET images formed the inputs for CNN. Five-fold cross-validations were carried out on the training set containing 62 patients, and the model behaving best was chosen to detect FCD on the test set of 20 patients. Furthermore, ablation experiments were performed to estimate the value of PET data and CNN. Results: On the validation set, FCD was detected in 90.3% of the cases, with an average of 1.7 possible lesions per patient. The sensitivity on the test set was 90.0%, with 1.85 possible lesions per patient. Without the PET data, the sensitivity decreased to 80.0%, and the average lesion number increased to 2.05 on the test set. If an artificial neural network replaced the CNN, the sensitivity decreased to 85.0%, and the average lesion number increased to 4.65. Significance: Automated detection of FCD with high sensitivity and few false-positive findings is feasible based on multi-modal data. PET data and CNN could improve the performance of automated detection. [ABSTRACT FROM AUTHOR]

Recent developments in Unmanned Aircraft Vehicles (UAVs), thermal imaging, and Auto-machine learning (AutoML) have shown high potential for precise wildlife surveys but have rarely been studied for habitat assessment. Here, we propose a framework that leverages these advanced techniques to achieve cost-effective habitat quality assessment from the perspective of actual wildlife community usage. The framework exploits vision intelligence hidden in the UAV thermal images and AutoML methods to achieve cost-effective wildlife distribution mapping, and then derives wildlife use indicators to imply habitat quality variance. We conducted UAV-based thermal wildlife surveys at three wetlands in the Rainwater Basin, Nebraska. Experiments were set to examine the optimal protocols, including various flight designs (61 and 122 m), feature types, and AutoML. The results showed that UAV images collected at 61 m with a spatial resolution of 7.5 cm, combined with Faster R-CNN, returned the optimal wildlife mapping (more than 90% accuracy). Results also indicated that the vision intelligence exploited can effectively transfer the redundant AutoML adaptation cycles into a fully automatic process (with around 33 times efficiency improvement for data labeling), facilitating cost-effective AutoML adaptation. Eventually, the derived ecological indicators can explain the wildlife use status well, reflecting potential within- and between-habitat quality variance. [ABSTRACT FROM AUTHOR]

Prolonged diabetic retinopathy (DR), glaucoma, and age-related macular degeneration (AMD) may lead to vision loss. Hence, early detection and treatment are crucial to prevent irreversible vision loss. Fundus retinal images have been widely used to help detect these diseases. Manual screening is susceptible to human errors, tedious, and expensive. Hence, artificial intelligence (AI) techniques have been widely employed to overcome these constraints. This paper reviewed the work published on automated retinal health detection models using various machine learning (ML) and deep learning (DL) techniques. We reviewed 142 papers and 262 studies (124 on glaucoma, 60 on AMD, and 78 on DR) from January 2012 to June 2024 using Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. We found that Convolutional Neural Networks (CNN) and Support Vector Machines (SVM) models were widely used in DL and ML techniques, respectively. To the best of our knowledge, this is the first review developed for detecting AMD, DR, and glaucoma using AI techniques over the last decade. We have discussed the limitations of the present methods and also suggested future directions for accurately detecting eye diseases.

This study introduces an ensemble model designed for real-time monitoring of bedridden patients. The model was developed using a unique dataset, specifically acquired for this study, that captures six typical movements. The dataset was balanced using the Synthetic Minority Over-sampling Technique, resulting in a diverse distribution of movement types. Three models were evaluated: a Decision Tree Regressor, a Gradient Boosting Regressor, and a Bagging Regressor. The Decision Tree Regressor achieved an accuracy of 0.892 and an R2 score of 1.0 on the training dataset, and 0.939 on the test dataset. The Boosting Regressor achieved an accuracy of 0.908 and an R2 score of 0.99 on the training dataset, and 0.943 on the test dataset. The Bagging Regressor was selected due to its superior performance and trade-offs such as computational cost and scalability. It achieved an accuracy of 0.950, an R2 score of 0.996 for the training data, and an R2 score of 0.959 for the test data. This study also employs K-Fold cross-validation and learning curves to validate the robustness of the Bagging Regressor model. The proposed system addresses practical implementation challenges in real-time monitoring, such as data latency and false positives/negatives, and is designed for seamless integration with hospital IT infrastructure. This research demonstrates the potential of machine learning to enhance patient safety in healthcare settings.

Abstract Landscape‐scale bioacoustic projects have become a popular approach to biodiversity monitoring. Combining passive acoustic monitoring recordings and automated detection provides an effective means of monitoring sound‐producing species' occupancy and phenology and can lend insight into unobserved behaviours and patterns. The availability of low‐cost recording hardware has lowered barriers to large‐scale data collection, but technological barriers in data analysis remain a bottleneck for extracting biological insight from bioacoustic datasets. We provide a robust and open‐source Python toolkit for detecting and localizing biological sounds in acoustic data. OpenSoundscape provides access to automated acoustic detection, classification and localization methods through a simple and easy‐to‐use set of tools. Extensive documentation and tutorials provide step‐by‐step instructions and examples of end‐to‐end analysis of bioacoustic data. Here, we describe the functionality of this package and provide concise examples of bioacoustic analyses with OpenSoundscape. By providing an interface for bioacoustic data and methods, we hope this package will lead to increased adoption of bioacoustics methods and ultimately to enhanced insights for ecology and conservation.