Int J Comput Assist Radiol Surg. 2025 May 2. doi: 10.1007/s11548-025-03361-w. Online ahead of print.

ABSTRACT

PURPOSE: The study aims to develop an automatic method to align ultrasound images of the distal forearm for diagnosing pediatric fractures. This approach seeks to bypass the reliance on X-rays for fracture diagnosis, thereby minimizing radiation exposure and making the process less painful, as well as creating a more child-friendly diagnostic pathway.

METHODS: We present a fully automatic pipeline to align paired POCUS images. We first leverage a deep learning model to delineate bone boundaries, from which we obtain key anatomical landmarks. These landmarks are finally used to guide the optimization-based alignment process, for which we propose three optimization constraints: aligning specific points, ensuring parallel orientation of the bone segments, and matching the bone widths.

RESULTS: The method demonstrated high alignment accuracy compared to reference X-rays in terms of boundary distances. A morphology experiment including fracture classification and angulation measurement presents comparable performance when based on the merged ultrasound images and conventional X-rays, justifying the effectiveness of our method in these cases.

CONCLUSIONS: The study introduced an effective and fully automatic pipeline for aligning ultrasound images, showing potential to replace X-rays for diagnosing pediatric distal forearm fractures. Initial tests show that surgeons find many of our results sufficient for diagnosis. Future work will focus on increasing dataset size to improve diagnostic accuracy and reliability.

PMID:40314702 | DOI:10.1007/s11548-025-03361-w

J Chem Inf Model. 2025 May 2. doi: 10.1021/acs.jcim.5c00271. Online ahead of print.

ABSTRACT

Antimicrobial resistance (AMR) is a global threat, with Burkholderia species contributing significantly to difficult-to-treat infections. The Pen family of β-lactamases are produced by all Burkholderia spp., and their mutation or overproduction leads to the resistance of β-lactam antibiotics. Here we investigate the dynamic differences among four Pen β-lactamases (PenA, PenI, PenL and PenP) using machine learning driven enhanced sampling molecular dynamics simulations, Markov State Models (MSMs), convolutional variational autoencoder-based deep learning (CVAE) and the BindSiteS-CNN model. In spite of sharing the same catalytic mechanisms, these enzymes exhibit distinct dynamic features due to low sequence identity, resulting in different substrate profiles and catalytic turnover. The BindSiteS-CNN model further reveals local active site dynamics, offering insights into the Pen β-lactamase evolutionary adaptation. Our findings reported here identify critical mutations and propose new hot spots affecting Pen β-lactamase flexibility and function, which can be used to fight emerging resistance in these enzymes.

PMID:40314617 | DOI:10.1021/acs.jcim.5c00271

Radiol Imaging Cancer. 2025 May;7(3):e250141. doi: 10.1148/rycan.250141.

NO ABSTRACT

PMID:40314587 | DOI:10.1148/rycan.250141

Afr J Reprod Health. 2025 Apr 23;29(4):108-119. doi: 10.29063/ajrh2025/v29i4.10.

ABSTRACT

Due to physiological changes during the perimenopausal period, the morphology of cervical cells undergoes certain alterations. Accurate cell image segmentation and lesion identification are of great significance for the early detection of precancerous lesions. Traditional detection methods may have certain limitations, thereby creating an urgent need for the development of more effective models. This study aimed to develop a highly efficient and accurate cervical cell image segmentation and recognition model to enhance the detection of precancerous lesions in perimenopausal women. based on U-shaped Network(U-Net) and Residual Network (ResNet). The model integrates U-Net with Segmentation Network (SegNet) and incorporates the Squeeze-and-Excitation (SE) attention mechanism to create the 2Se/U-Net segmentation model. Additionally, ResNet is optimized with the local discriminant loss function (LD-loss) and deep residual learning (DRL) blocks to develop the LD/ResNet lesion recognition model. The performance of the models is evaluated using data from 103 cytology images of perimenopausal women, focusing on segmentation metrics like mean pixel accuracy (MPA) and mean intersection over union (mIoU), as well as lesion detection metrics such as accuracy (Acc), precision (Pre), recall (Re), and F1-score (F1). Results show that the 2Se/U-Net model achieves an MPA of 92.63% and mIoU of 96.93%, outperforming U-Net by 12.48% and 9.47%, respectively. The LD/ResNet model demonstrates over 97.09% accuracy in recognizing cervical cells and achieves high detection performance for precancerous lesions, with Acc, Pre, and Re at 98.95%, 99.36%, and 98.89%, respectively. The model shows great potential for enhancing cervical cancer screening in clinical settings.

PMID:40314307 | DOI:10.29063/ajrh2025/v29i4.10

Elife. 2025 May 2;13:RP98033. doi: 10.7554/eLife.98033.

ABSTRACT

Protein engineering is a pivotal aspect of synthetic biology, involving the modification of amino acids within existing protein sequences to achieve novel or enhanced functionalities and physical properties. Accurate prediction of protein variant effects requires a thorough understanding of protein sequence, structure, and function. Deep learning methods have demonstrated remarkable performance in guiding protein modification for improved functionality. However, existing approaches predominantly rely on protein sequences, which face challenges in efficiently encoding the geometric aspects of amino acids' local environment and often fall short in capturing crucial details related to protein folding stability, internal molecular interactions, and bio-functions. Furthermore, there lacks a fundamental evaluation for developed methods in predicting protein thermostability, although it is a key physical property that is frequently investigated in practice. To address these challenges, this article introduces a novel pre-training framework that integrates sequential and geometric encoders for protein primary and tertiary structures. This framework guides mutation directions toward desired traits by simulating natural selection on wild-type proteins and evaluates variant effects based on their fitness to perform specific functions. We assess the proposed approach using three benchmarks comprising over 300 deep mutational scanning assays. The prediction results showcase exceptional performance across extensive experiments compared to other zero-shot learning methods, all while maintaining a minimal cost in terms of trainable parameters. This study not only proposes an effective framework for more accurate and comprehensive predictions to facilitate efficient protein engineering, but also enhances the in silico assessment system for future deep learning models to better align with empirical requirements. The PyTorch implementation is available at https://github.com/ai4protein/ProtSSN.

PMID:40314227 | DOI:10.7554/eLife.98033

J Neural Eng. 2025 May 2;22(3). doi: 10.1088/1741-2552/adcfc8.

ABSTRACT

Objective.Major depressive disorder (MDD) is a widespread mental disorder that affects health. Many methods combining electroencephalography (EEG) with machine learning or deep learning have been proposed to objectively distinguish between MDD and healthy individuals. However, most current methods detect depression based on multichannel EEG signals, which constrains its application in daily life. The context in which EEG is obtained can vary in terms of study designs and EEG equipment settings, and the available depression EEG data is limited, which could also potentially lessen the efficacy of the model in differentiating between MDD and healthy subjects. To solve the above challenges, a depression detection model leveraging transfer learning with the single-channel EEG is advanced.Approach.We utilized a pretrained ResNet152V2 network to which a flattening layer and dense layer were appended. The method of feature extraction was applied, meaning that all layers within ResNet152V2 were frozen and only the parameters of the newly added layers were adjustable during training. Given the superiority of deep neural networks in image processing, the temporal sequences of EEG signals are first converted into images, transforming the problem of EEG signal categorization into an image classification task. Subsequently, a cross-subject experimental strategy was adopted for model training and performance evaluation.Main results.The model was capable of precisely (approaching 100% accuracy) identifying depression in other individuals by employing single-channel EEG samples obtained from a limited number of subjects. Furthermore, the model exhibited superior performance across four publicly available depression EEG datasets, thereby demonstrating good adaptability in response to variations in EEG caused by the context.Significance.This research not only highlights the impressive potential of deep transfer learning techniques in EEG signal analysis but also paves the way for innovative technical approaches to facilitate early diagnosis of associated mental disorders in the future.

PMID:40314182 | DOI:10.1088/1741-2552/adcfc8

Brief Bioinform. 2025 May 1;26(3):bbaf218. doi: 10.1093/bib/bbaf218.

NO ABSTRACT

PMID:40314061 | DOI:10.1093/bib/bbaf218

Front Neuroinform. 2025 Apr 17;19:1550432. doi: 10.3389/fninf.2025.1550432. eCollection 2025.

ABSTRACT

INTRODUCTION: Brain tumors are a leading cause of mortality worldwide, with early and accurate diagnosis being essential for effective treatment. Although Deep Learning (DL) models offer strong performance in tumor detection and segmentation using MRI, their black-box nature hinders clinical adoption due to a lack of interpretability.

METHODS: We present a hybrid AI framework that integrates a 3D U-Net Convolutional Neural Network for MRI-based tumor segmentation with radiomic feature extraction. Dimensionality reduction is performed using machine learning, and an Adaptive Neuro-Fuzzy Inference System (ANFIS) is employed to produce interpretable decision rules. Each experiment is constrained to a small set of high-impact radiomic features to enhance clarity and reduce complexity.

RESULTS: The framework was validated on the BraTS2020 dataset, achieving an average DICE Score of 82.94% for tumor core segmentation and 76.06% for edema segmentation. Classification tasks yielded accuracies of 95.43% for binary (healthy vs. tumor) and 92.14% for multi-class (healthy vs. tumor core vs. edema) problems. A concise set of 18 fuzzy rules was generated to provide clinically interpretable outputs.

DISCUSSION: Our approach balances high diagnostic accuracy with enhanced interpretability, addressing a critical barrier in applying DL models in clinical settings. Integrating of ANFIS and radiomics supports transparent decision-making, facilitating greater trust and applicability in real-world medical diagnostics assistance.

PMID:40313917 | PMC:PMC12043696 | DOI:10.3389/fninf.2025.1550432

Front Bioinform. 2025 Apr 17;5:1554010. doi: 10.3389/fbinf.2025.1554010. eCollection 2025.

ABSTRACT

Single-cell and spatial technologies have transformed our understanding of brain immunology, providing unprecedented insights into immune cell heterogeneity and spatial organisation within the central nervous system. These methods have uncovered complex cellular interactions, rare cell populations, and the dynamic immune landscape in neurological disorders. This review highlights recent advances in single-cell "omics" data analysis and discusses their applicability for brain immunology. Traditional statistical techniques, adapted for single-cell omics, have been crucial in categorizing cell types and identifying gene signatures, overcoming challenges posed by increasingly complex datasets. We explore how machine learning, particularly deep learning methods like autoencoders and graph neural networks, is addressing these challenges by enhancing dimensionality reduction, data integration, and feature extraction. Newly developed foundation models present exciting opportunities for uncovering gene expression programs and predicting genetic perturbations. Focusing on brain development, we demonstrate how single-cell analyses have resolved immune cell heterogeneity, identified temporal maturation trajectories, and uncovered potential therapeutic links to various pathologies, including brain malignancies and neurodegeneration. The integration of single-cell and spatial omics has elucidated the intricate cellular interplay within the developing brain. This mini-review is intended for wet lab biologists at all career stages, offering a concise overview of the evolving landscape of single-cell omics in the age of widely available artificial intelligence.

PMID:40313869 | PMC:PMC12043695 | DOI:10.3389/fbinf.2025.1554010

Front Comput Neurosci. 2025 Apr 16;19:1569828. doi: 10.3389/fncom.2025.1569828. eCollection 2025.

ABSTRACT

INTRODUCTION: Major Depressive Disorder (MDD) remains a critical mental health concern, necessitating accurate detection. Traditional approaches to diagnosing MDD often rely on manual Electroencephalography (EEG) analysis to identify potential disorders. However, the inherent complexity of EEG signals along with the human error in interpreting these readings requires the need for more reliable, automated methods of detection.

METHODS: This study utilizes EEG signals to classify MDD and healthy individuals through a combination of machine learning, deep learning, and split learning approaches. State of the art machine learning models i.e., Random Forest, Support Vector Machine, and Gradient Boosting are utilized, while deep learning models such as Transformers and Autoencoders are selected for their robust feature-extraction capabilities. Traditional methods for training machine learning and deep learning models raises data privacy concerns and require significant computational resources. To address these issues, the study applies a split learning framework. In this framework, an ensemble learning technique has been utilized that combines the best performing machine and deep learning models.

RESULTS: Results demonstrate a commendable classification performance with certain ensemble methods, and a Transformer-Random Forest combination achieved 99% accuracy. In addition, to address data-sharing constraints, a split learning framework is implemented across three clients, yielding high accuracy (over 95%) while preserving privacy. The best client recorded 96.23% accuracy, underscoring the robustness of combining Transformers with Random Forest under resource-constrained conditions.

DISCUSSION: These findings demonstrate that distributed deep learning pipelines can deliver precise MDD detection from EEG data without compromising data security. Proposed framework keeps data on local nodes and only exchanges intermediate representations. This approach meets institutional privacy requirements while providing robust classification outcomes.

PMID:40313734 | PMC:PMC12044669 | DOI:10.3389/fncom.2025.1569828

Front Pediatr. 2025 Apr 17;13:1514447. doi: 10.3389/fped.2025.1514447. eCollection 2025.

ABSTRACT

Artificial Intelligence is revolutionizing prenatal diagnostics by enhancing the accuracy and efficiency of procedures. This review explores AI and machine learning (ML) in the early detection, prediction, and assessment of neural tube defects (NTDs) through prenatal ultrasound imaging. Recent studies highlight the effectiveness of AI techniques, such as convolutional neural networks (CNNs) and support vector machines (SVMs), achieving detection accuracy rates of up to 95% across various datasets, including fetal ultrasound images, genetic data, and maternal health records. SVM models have demonstrated 71.50% accuracy on training datasets and 68.57% on testing datasets for NTD classification, while advanced deep learning (DL) methods report patient-level prediction accuracy of 94.5% and an area under the receiver operating characteristic curve (AUROC) of 99.3%. AI integration with genomic analysis has identified key biomarkers associated with NTDs, such as Growth Associated Protein 43 (GAP43) and Glial Fibrillary Acidic Protein (GFAP), with logistic regression models achieving 86.67% accuracy. Current AI-assisted ultrasound technologies have improved diagnostic accuracy, yielding sensitivity and specificity rates of 88.9% and 98.0%, respectively, compared to traditional methods with 81.5% sensitivity and 92.2% specificity. AI systems have also streamlined workflows, reducing median scan times from 19.7 min to 11.4 min, allowing sonographers to prioritize critical patient care. Advancements in DL algorithms, including Oct-U-Net and PAICS, have achieved recall and precision rates of 0.93 and 0.96, respectively, in identifying fetal abnormalities. Moreover, AI's evolving role in genetic research supports personalized NTD prevention strategies and enhances public awareness through AI-generated health messages. In conclusion, the integration of AI in prenatal diagnostics significantly improves the detection and assessment of NTDs, leading to greater accuracy and efficiency in ultrasound imaging. As AI continues to advance, it has the potential to further enhance personalized healthcare strategies and raise public awareness about NTDs, ultimately contributing to better maternal and fetal outcomes.

PMID:40313675 | PMC:PMC12043698 | DOI:10.3389/fped.2025.1514447

Proc IEEE Int Symp Biomed Imaging. 2024 May;2024. doi: 10.1109/ISBI56570.2024.10635349. Epub 2024 Aug 22.

ABSTRACT

Data limitation is a significant challenge in applying deep learning to medical images. Recently, the diffusion probabilistic model (DPM) has shown the potential to generate high-quality images by converting Gaussian random noise into realistic images. In this paper, we apply the DPM to augment the deep ultraviolet fluorescence (DUV) image dataset with an aim to improve breast cancer classification for intra-operative margin assessment. For classification, we divide the whole surface DUV image into small patches and extract convolutional features for each patch by utilizing the pre-trained ResNet. Then, we feed them into an XGBoost classifier for patch-level decisions and then fuse them with a regional importance map computed by Grad-CAM++ for whole surface-level prediction. Our experimental results show that augmenting the training dataset with the DPM significantly improves breast cancer detection performance in DUV images, increasing accuracy from 93% to 97%, compared to using Affine transformations and ProGAN.

PMID:40313564 | PMC:PMC12045284 | DOI:10.1109/ISBI56570.2024.10635349

Front Med (Lausanne). 2025 Apr 16;12:1555907. doi: 10.3389/fmed.2025.1555907. eCollection 2025.

ABSTRACT

BACKGROUND: Recent advances in machine learning are transforming medical image analysis, particularly in cancer detection and classification. Techniques such as deep learning, especially convolutional neural networks (CNNs) and vision transformers (ViTs), are now enabling the precise analysis of complex histopathological images, automating detection, and enhancing classification accuracy across various cancer types. This study focuses on osteosarcoma (OS), the most common bone cancer in children and adolescents, which affects the long bones of the arms and legs. Early and accurate detection of OS is essential for improving patient outcomes and reducing mortality. However, the increasing prevalence of cancer and the demand for personalized treatments create challenges in achieving precise diagnoses and customized therapies.

METHODS: We propose a novel hybrid model that combines convolutional neural networks (CNN) and vision transformers (ViT) to improve diagnostic accuracy for OS using hematoxylin and eosin (H&E) stained histopathological images. The CNN model extracts local features, while the ViT captures global patterns from histopathological images. These features are combined and classified using a Multi-Layer Perceptron (MLP) into four categories: non-tumor (NT), non-viable tumor (NVT), viable tumor (VT), and non-viable ratio (NVR).

RESULTS: Using the Cancer Imaging Archive (TCIA) dataset, the model achieved an accuracy of 99.08%, precision of 99.10%, recall of 99.28%, and an F1-score of 99.23%. This is the first successful four-class classification using this dataset, setting a new benchmark in OS research and offering promising potential for future diagnostic advancements.

PMID:40313555 | PMC:PMC12045028 | DOI:10.3389/fmed.2025.1555907

Natl Sci Rev. 2025 Jan 28;12(5):nwaf030. doi: 10.1093/nsr/nwaf030. eCollection 2025 May.

ABSTRACT

Unraveling complex cell-type-composition and gene-expression patterns at the cellular spatial resolution is crucial for understanding intricate cell functions in the brain. In this study, we developed Deep Neural Network-based Spatial Cell Typing (DSCT)-an innovative framework for spatial cell typing within spatial transcriptomic data sets. This approach utilizes a synergistic integration of an enhanced gene-selection strategy and a lightweight deep neural network for data training, offering a more rapid and accurate solution for the analysis of spatial transcriptomic data. Based on comprehensive analysis, DSCT achieved exceptional accuracy in cell-type identification across various brain regions, species and spatial transcriptomic platforms. It also performed well in mapping finer cell types, thereby showcasing its versatility and adaptability across diverse data sets. Strikingly, DSCT exhibited high efficiency and remarkable processing speed, with fewer computational resource demands. As such, this novel approach opens new avenues for exploring the spatial organization of cell types and gene-expression patterns, advancing our understanding of biological functions and pathologies within the nervous system.

PMID:40313458 | PMC:PMC12045154 | DOI:10.1093/nsr/nwaf030

Front Neurorobot. 2025 Apr 17;19:1582995. doi: 10.3389/fnbot.2025.1582995. eCollection 2025.

ABSTRACT

INTRODUCTION: Understanding human actions in complex environments is crucial for advancing applications in areas such as surveillance, robotics, and autonomous systems. Identifying actions from UAV-recorded videos becomes more challenging as the task presents unique challenges, including motion blur, dynamic background, lighting variations, and varying viewpoints. The presented work develops a deep learning system that recognizes multi-person behaviors from data gathered by UAVs. The proposed system provides higher recognition accuracy while maintaining robustness along with dynamic environmental adaptability through the integration of different features and neural network models. The study supports the wider development of neural network systems utilized in complicated contexts while creating intelligent UAV applications utilizing neural networks.

METHOD: The proposed study uses deep learning and feature extraction approaches to create a novel method to recognize various actions in UAV-recorded video. The proposed model improves identification capacities and system robustness by addressing motion dynamic problems and intricate environmental constraints, encouraging advancements in UAV-based neural network systems.

RESULTS: We proposed a deep learning-based framework with feature extraction approaches that may effectively increase the accuracy and robustness of multi-person action recognition in the challenging scenarios. Compared to the existing approaches, our system achieved 91.50% on MOD20 dataset and 89.71% on Okutama-Action. These results do, in fact, show how useful neural network-based methods are for managing the limitations of UAV-based application.

DISCUSSION: Results how that the proposed framework is indeed effective at multi-person action recognition under difficult UAV conditions.

PMID:40313416 | PMC:PMC12043872 | DOI:10.3389/fnbot.2025.1582995

Annu Rev Biomed Data Sci. 2025 May 1. doi: 10.1146/annurev-biodatasci-103123-094521. Online ahead of print.

ABSTRACT

Skin cancer is the most common cancer in the United States, with incidence rates continuing to rise both nationally and globally, posing significant health and economic burdens. These challenges are compounded by shortages in dermatological care and barriers to insurance access. To address these gaps, artificial intelligence (AI) and deep learning technologies offer promising solutions, enhancing skin cancer screening and diagnosis. AI has the potential to improve diagnostic accuracy and expand access to care, but significant challenges restrict its deployment. These challenges include clinical validation, algorithmic bias, regulatory oversight, and patient acceptance. Ethical concerns, such as disparities in access and fairness of AI algorithms, also require attention. In this review, we explore these limitations and outline future directions, including advancements in teledermatology and vision-language models (VLMs). Future research should focus on improving VLM reliability and interpretability and developing systems capable of integrating clinical context with dermatological images in a way that assists, rather than replaces, clinicians in making more accurate, timely diagnoses.

PMID:40312261 | DOI:10.1146/annurev-biodatasci-103123-094521

J Voice. 2025 Apr 30:S0892-1997(25)00158-4. doi: 10.1016/j.jvoice.2025.04.010. Online ahead of print.

ABSTRACT

Artificial Intelligence (AI) is transforming speech-language pathology (SLP) and dysphagia management, offering innovative solutions for assessment, diagnosis, and rehabilitation. This narrative review examines AI applications in these fields from 2014 to 2024, with particular focus on implementation challenges in Latin America. We analyze key AI technologies-including deep learning, machine learning algorithms, and natural language processing-that have demonstrated high accuracy in detecting voice disorders, analyzing swallowing function, and supporting personalized rehabilitation. The review identifies three primary domains of AI application: diagnostic tools with improved sensitivity for speech-language disorders, rehabilitation technologies that enable customized therapy, and telehealth platforms that expand access to specialized care in underserved regions. However, significant barriers persist, particularly in Latin America, where limited infrastructure, insufficient linguistic adaptation, and scarce regional datasets hamper widespread implementation. Our pilot study evaluating commercially available large language models for rehabilitation planning demonstrates their potential utility in generating structured therapy activities, especially in resource-constrained settings. While AI shows promise in enhancing clinical workflows and expanding service delivery, the evidence suggests that current applications remain predominantly focused on diagnosis rather than integrated rehabilitation. This review highlights the need for culturally and linguistically adapted AI models, expanded regional research collaborations, and regulatory frameworks that ensure ethical AI integration into SLP and dysphagia care, positioning these technologies as complementary tools that enhance rather than replace clinical expertise.

PMID:40312192 | DOI:10.1016/j.jvoice.2025.04.010

Lancet Digit Health. 2025 Apr 30:100868. doi: 10.1016/j.landig.2025.02.008. Online ahead of print.

ABSTRACT

BACKGROUND: Improving the accessibility of screening diabetic kidney disease (DKD) and differentiating isolated diabetic nephropathy from non-diabetic kidney disease (NDKD) are two major challenges in the field of diabetes care. We aimed to develop and validate an artificial intelligence (AI) deep learning system to detect DKD and isolated diabetic nephropathy from retinal fundus images.

METHODS: In this population-based study, we developed a retinal image-based AI-deep learning system, DeepDKD, pretrained using 734 084 retinal fundus images. First, for DKD detection, we used 486 312 retinal images from 121 578 participants in the Shanghai Integrated Diabetes Prevention and Care System for development and internal validation, and ten multi-ethnic datasets from China, Singapore, Malaysia, Australia, and the UK (65 406 participants) for external validation. Second, to differentiate isolated diabetic nephropathy from NDKD, we used 1068 retinal images from 267 participants for development and internal validation, and three multi-ethnic datasets from China, Malaysia, and the UK (244 participants) for external validation. Finally, we conducted two proof-of-concept studies: a prospective real-world study with 3 months' follow-up to evaluate the effectiveness of DeepDKD in screening DKD; and a longitudinal analysis of the effectiveness of DeepDKD in differentiating isolated diabetic nephropathy from NDKD on renal function changes with 4·6 years' follow-up.

FINDINGS: For detecting DKD, DeepDKD achieved an area under the receiver operating characteristic curve (AUC) of 0·842 (95% CI 0·838-0·846) on the internal validation dataset and AUCs of 0·791-0·826 across external validation datasets. For differentiating isolated diabetic nephropathy from NDKD, DeepDKD achieved an AUC of 0·906 (0·825-0·966) on the internal validation dataset and AUCs of 0·733-0·844 across external validation datasets. In the prospective study, compared with the metadata model, DeepDKD could detect DKD with higher sensitivity (89·8% vs 66·3%, p<0·0001). In the longitudinal study, participants with isolated diabetic nephropathy and participants with NDKD identified by DeepDKD had a significant difference in renal function outcomes (proportion of estimated glomerular filtration rate decline: 27·45% vs 52·56%, p=0·0010).

INTERPRETATION: Among diverse multi-ethnic populations with diabetes, a retinal image-based AI-deep learning system showed its potential for detecting DKD and differentiating isolated diabetic nephropathy from NDKD in clinical practice.

FUNDING: National Key R & D Program of China, National Natural Science Foundation of China, Beijing Natural Science Foundation, Shanghai Municipal Key Clinical Specialty, Shanghai Research Centre for Endocrine and Metabolic Diseases, Innovative research team of high-level local universities in Shanghai, Noncommunicable Chronic Diseases-National Science and Technology Major Project, Clinical Special Program of Shanghai Municipal Health Commission, and the three-year action plan to strengthen the construction of public health system in Shanghai.

PMID:40312169 | DOI:10.1016/j.landig.2025.02.008

Gastroenterology. 2025 Apr 29:S0016-5085(25)00648-1. doi: 10.1053/j.gastro.2025.04.011. Online ahead of print.

ABSTRACT

This review explores the transformative potential of artificial intelligence in the diagnosis and management of biliopancreatic disorders. By leveraging cutting-edge techniques such as deep learning and convolutional neural networks, artificial intelligence has significantly advanced gastroenterology, particularly in endoscopic procedures such as colonoscopy, upper endoscopy, and capsule endoscopy. These applications enhance adenoma detection rates, and improve lesion characterization and diagnostic accuracy. Artificial intelligence's integration in cross-sectional imaging modalities, such as computed tomography and magnetic resonance imaging, has shown remarkable potential. Models have demonstrated high accuracy in identifying pancreatic ductal adenocarcinoma, pancreatic cystic lesions, and pancreatic neuroendocrine tumors, aiding in early diagnosis, resectability assessment, and personalized treatment planning. In advanced endoscopic procedures, like digital single-operator cholangioscopy and endoscopic ultrasound, artificial intelligence enhances anatomical recognition, improves lesion classification, with potential reduction in procedural variability, enabling more consistent diagnositc and therapeutic outcomes. Promising applications in biliopancreatic endoscopy include the detection of biliary stenosis, classification of dysplastic precursor lesions, and assessment of pancreatic abnormalities. This review aims to capture the current state of artificial intelligence application in biliopancreatic disorders, summarizing the results of early studies, and paving the path for future directions.

PMID:40311821 | DOI:10.1053/j.gastro.2025.04.011

Am J Pathol. 2025 Apr 29:S0002-9440(25)00143-9. doi: 10.1016/j.ajpath.2025.04.004. Online ahead of print.

ABSTRACT

Conventional ascitic fluid cytology for detecting ovarian cancer is limited by its low sensitivity. To address this issue, our multicenter study developed patch image (PIs)-based fully supervised convolutional neural network (CNN) models and clustering-constrained attention multiple-instance learning (CLAM) algorithms for detecting ovarian cancer using ascitic fluid cytology. We collected 356 benign and 147 cancer whole-slide images (WSIs), from which 14,699 benign and 8,025 cancer PIs were extracted. Additionally 131 WSIs (44 benign and 87 cancer) were used for external validation. Six CNN algorithms were developed for cancer detection using PIs. Subsequently, two CLAM algorithms, single branch (CLAM-SB) and multiple branch (CLAM-MB), were developed. ResNet50 demonstrated the best performance, achieving an accuracy of 0.973. The performance when interpreting internal WSIs was an area under the curve (AUC) of 0.982. CLAM-SB outperformed CLAM-MB with an AUC of 0.944 in internal WSIs. Notably, in the external test, CLAM-SB exhibited superior performance with an AUC of 0.866 compared to ResNet50's AUC of 0.804. Analysis of the heatmap revealed that cases frequently misinterpreted by AI were easily interpreted by humans, and vice versa. Because AI and humans were found to function complementarily, implementing computer-aided diagnosis is expected to significantly enhance diagnostic accuracy and reproducibility. Furthermore, the WSI-based learning in CLAM, eliminating the need for patch-by-patch annotation, offers an advantage over the CNN model.

PMID:40311756 | DOI:10.1016/j.ajpath.2025.04.004