Computers in biology and medicine最新文献

{"title":"Spatially Aware GCNs for efficient, high-accuracy cancer grading: Mitigating oversmoothing via frequency analysis","authors":"Luke Johnston ,&nbsp;Zhangsheng Yu","doi":"10.1016/j.compbiomed.2025.111037","DOIUrl":"10.1016/j.compbiomed.2025.111037","url":null,"abstract":"<div><div>We present a Spatially Aware Graph Convolutional Network (SA-GCN) for classifying colorectal and non-small cell lung cancer grades, with a focus on preserving high-resolution spatial features and leveraging frequency information in histopathological data. Cancer grading relies on complex, cell-level spatial relationships—an ideal setting for Graph Convolutional Networks (GCNs). However, deeper GCNs typically suffer from oversmoothing, which severely limits their ability to capture intricate structures. To overcome this, we develop SA-GCN, incorporating both a dilated layer and a quantile-based aggregation function to balance low- and high-frequency information in graph-structured data.</div><div>Our experiments on colorectal and non-small cell lung cancer datasets show a 0.87% and 0.81% improvement respectively in accuracy over state-of-the-art methods, with the dilated layer alone achieving 98.05% <span><math><mo>±</mo></math></span> 0.99% accuracy at seven layers in the colorectal dataset. Additionally, SA-GCN offers significant computational advantages: by optimising graph construction, we reduce complexity from <span><math><mrow><mi>O</mi><mrow><mo>(</mo><msup><mrow><mi>N</mi></mrow><mrow><mn>2</mn></mrow></msup><mo>)</mo></mrow></mrow></math></span> to <span><math><mrow><mi>O</mi><mrow><mo>(</mo><mi>N</mi><mo>)</mo></mrow></mrow></math></span>. Theoretical analyses further guarantee preserved graph signal diversity, ensuring robust performance on both sparse and dense tissue structures. Overall, SA-GCN advances the state of the art by delivering higher accuracy, deeper architectures, and the ability to scale to large datasets, a problem other oversmoothing mitigating techniques face.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"198 ","pages":"Article 111037"},"PeriodicalIF":6.3,"publicationDate":"2025-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145218883","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Breast cancer prediction using mammography exams for real hospital settings","authors":"Shreyasi Pathak ,&nbsp;Jörg Schlötterer ,&nbsp;Jeroen Geerdink ,&nbsp;Jeroen Veltman ,&nbsp;Maurice van Keulen ,&nbsp;Nicola Strisciuglio ,&nbsp;Christin Seifert","doi":"10.1016/j.compbiomed.2025.111136","DOIUrl":"10.1016/j.compbiomed.2025.111136","url":null,"abstract":"<div><div>Breast cancer prediction models for mammography assume that annotations are available for individual images or regions of interest (ROIs), and that there is a fixed number of images per patient. These assumptions do not hold in real hospital settings, where clinicians provide only a final diagnosis for the entire mammography exam (case). Since data in real hospital settings scales with continuous patient intake, while manual annotation efforts do not, we develop a framework for case-level breast cancer prediction that does not require any manual annotation and can be trained with case labels readily available at the hospital. Specifically, we propose a two-level multi-instance learning (MIL) approach at patch and image level for case-level breast cancer prediction and evaluate it on two public and one private dataset. We propose a novel domain-specific MIL pooling observing that breast cancer may or may not occur in both sides, while images of both breasts are taken as a precaution during mammography. We propose a dynamic training procedure for training our MIL framework on a variable number of images per case. We show that our two-level MIL model can be applied in real hospital settings where only case labels, and a variable number of images per case are available, without any loss in performance compared to models trained on image labels. Only trained with weak (case-level) labels, it has the capability to point out in which breast side, mammography view and view region the abnormality lies.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"198 ","pages":"Article 111136"},"PeriodicalIF":6.3,"publicationDate":"2025-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145218523","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A systematic review on automatic segmentation of renal tumors and cysts using various convolutional neural network architectures in radiological images.","authors":"Chintam Anusha, Kunjam Nageswara Rao, T Lakshmana Rao","doi":"10.1016/j.compbiomed.2025.111177","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2025.111177","url":null,"abstract":"<p><p>Premature diagnosis of kidney cancer is crucial for saving lives and enabling better treatment. Medical experts utilize radiological images, such as CT, MRI, US, and histopathological analysis, to identify kidney tumors and cysts, providing valuable information on their size, shape, location, and metabolism, thus aiding in diagnosis. In radiological image processing, precise segmentation remains difficult when done manually, despite numerous noteworthy efforts and encouraging results in this field. Thus, there's an emergent need for automatic methods for renal and renal mass segmentation. In this regard, this article reviews studies on utilizing deep learning models to detect renal masses early in medical imaging examinations, particularly various CNN (Convolutional Neural Network) models that have demonstrated excellent outcomes in the segmentation of radiological images. Furthermore, we addressed the detailed dataset characteristics that the researchers adapted, as well as the accuracy and efficiency metrics obtained using various parameters. However, several studies employed datasets with limited images, whereas only a handful used hundreds of thousands of images. Those examinations did not fully determine the tumor and cyst diagnosis. The key goals are to describe recent accomplishments, examine the methodological approaches used by researchers, and recommend potential future research directions.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"198 Pt A","pages":"111177"},"PeriodicalIF":6.3,"publicationDate":"2025-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145231586","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Revised NMS-driven pipeline for heart valve regurgitation and Kawasaki disease coronary aneurysm localization","authors":"Shih-Hsin Chen ,&nbsp;Ho-Chang Kuo ,&nbsp;Ken-Pen Weng ,&nbsp;Kai-Sheng Hsieh ,&nbsp;Ting-Yi Kao ,&nbsp;Yi-Hui Chen ,&nbsp;Mindy Ming-Huey Guo ,&nbsp;Shih-Feng Liu ,&nbsp;Chia-Hsuan Liao","doi":"10.1016/j.compbiomed.2025.111125","DOIUrl":"10.1016/j.compbiomed.2025.111125","url":null,"abstract":"<div><div>Object detection in echocardiography is still uncommon, yet precise localization of pediatric valvular regurgitation and Kawasaki-related coronary aneurysms is critical. We introduce two lightweight variants of non-maximum suppression, rNMS-P (used only at inference) and rNMS-TP (used during both training and inference), that improve YOLO v5 to v9 detectors without altering their backbones. The system combines horizontal boxes for valve jets with rotation-aware oriented boxes for coronary segments, applies anatomical constraints by keeping a single high-confidence box per class, and can relax this rule for well-represented lesions. On color and grayscale echocardiograms, rNMS-TP increased [email protected] from 79.7% to 80.5% for regurgitation and from 85.7% to 86.5% for Kawasaki disease, with gains up to 2.3% at the stricter [email protected]:.95 threshold; rNMS-P provided up to a 2.1% boost, all with negligible computational cost, offering a practical path toward explainable, operator-independent cardiac image assessment.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"198 ","pages":"Article 111125"},"PeriodicalIF":6.3,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145218447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Graph theory analysis based on cross frequency coupling methods in major depressive disorder: A resting state EEG study","authors":"Sepideh Baghernezhad ,&nbsp;Parisa Raouf ,&nbsp;Vahid Shalchyan ,&nbsp;Reza Rostami ,&nbsp;Mohammad Reza Daliri","doi":"10.1016/j.compbiomed.2025.111168","DOIUrl":"10.1016/j.compbiomed.2025.111168","url":null,"abstract":"<div><div>Major depressive disorder (MDD) is a common and debilitating mental disorder that affects the personal and social activities of individuals. Conventional diagnostic approaches are based on the validity of the information provided by the patient and the expertise of the psychiatrist, which may limit precision. This study aimed to identify potential EEG-based biomarkers for diagnosing depression severity. Resting-state EEG signals were recorded from 37 subjects (15 healthy, 10 moderately depressed, and 12 severely depressed), and then analyzed using cross-frequency coupling (CFC) measures and graph theory metrics. Using the statistical analysis results, it was observed that depression affects the entire cerebral cortex, especially the frontal and occipital regions. The degree and K-coreness centrality measures showed statistically significant differences in almost all regions. In scaling depression severity, the Support Vector Machine (SVM) classifier achieved an accuracy of 94.25 % using 4 selected features derived from CFC between the low <span><math><mrow><mi>α</mi></mrow></math></span> and the low <span><math><mrow><mi>γ</mi></mrow></math></span> band. To the best of our knowledge, this is the first study combining CFC and graph-theoretical analysis for multi-level depression severity classification.Using our proposed method along with psychological scales may be effective for diagnosing and treatment of MDD.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"198 ","pages":"Article 111168"},"PeriodicalIF":6.3,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145218522","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A rationally designed multi-epitope vaccine candidate targeting conserved FiuA for broad Pseudomonas aeruginosa protection","authors":"Anahita Hessami ,&nbsp;Mona Moosavi ,&nbsp;Fatemeh Rahim ,&nbsp;Zahra Mogharari ,&nbsp;Mahdieh Heidari ,&nbsp;Farnoosh Farzam ,&nbsp;Mohammad Reza Rahbar","doi":"10.1016/j.compbiomed.2025.111170","DOIUrl":"10.1016/j.compbiomed.2025.111170","url":null,"abstract":"<div><div><em>Pseudomonas aeruginosa</em> is a significant opportunistic pathogen, and developing a broadly protective vaccine has been hindered by its antigenic variability and immune evasion mechanisms. This study presents a rationally designed multi-epitope vaccine construct targeting the highly conserved iron acquisition protein FiuA to overcome these challenges. Our approach incorporates conserved epitope selection, epitope reciprocity (pairing B-cell epitopes with HLA class II T-cell epitopes), and optimized epitope density to maximize both cellular and humoral immune responses. We identified conserved B-cell and T-cell epitopes from FiuA and designed a construct incorporating a self-assembling peptide unit to enhance antigen presentation. In silico modeling predicts strong HLA binding affinities and broad population coverage. The resulting construct mimics pathogen-associated molecular patterns and is predicted to stimulate a robust, cross-protective immune response. This innovative strategy addresses limitations of previous <em>P. aeruginosa</em> vaccine efforts and offers a promising avenue for developing a broadly effective vaccine, warranting further experimental validation for its immunogenicity and protective efficacy.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"198 ","pages":"Article 111170"},"PeriodicalIF":6.3,"publicationDate":"2025-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145218448","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Corrigendum to “Bioactive potential of Centella asiatica leaf extract in acetylcholinesterase (AChE) inhibition: Insights from multiple ligand mapping” [Comput. Biol. Med. 197 (2025) 110970]","authors":"Miski Aghnia Khairinisa ,&nbsp;Taufik Muhammad Fakih ,&nbsp;Dwi Syah Fitra Ramadhan","doi":"10.1016/j.compbiomed.2025.111108","DOIUrl":"10.1016/j.compbiomed.2025.111108","url":null,"abstract":"","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 ","pages":"Article 111108"},"PeriodicalIF":6.3,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145130420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"UNSX-HRNet: Modeling anatomical uncertainty for landmark detection in total hip arthroplasty","authors":"Jiaxin Wan ,&nbsp;Lin Liu ,&nbsp;Haoran Wang ,&nbsp;Liangwei Li ,&nbsp;Wei Li ,&nbsp;Shuheng Kou ,&nbsp;Runtian Li ,&nbsp;Jiayi Tang ,&nbsp;Juanxiu Liu ,&nbsp;Jing Zhang ,&nbsp;Xiaohui Du ,&nbsp;Ruqian Hao","doi":"10.1016/j.compbiomed.2025.111146","DOIUrl":"10.1016/j.compbiomed.2025.111146","url":null,"abstract":"<div><h3>Background</h3><div>Accurate detection of anatomical landmarks from radiographic images is critical for total hip arthroplasty (THA) surgical planning and postoperative evaluation. However, existing methods face significant challenges in unstructured data, such as irregular patient postures or occluded landmarks, which hinder their robustness and reliability. This study aims to develop an advanced deep learning framework to address these challenges, by leveraging uncertainty estimation to handle unstructured data and assigning uncertainty scores to predicted landmarks, thereby alerting clinicians to focus on these results.</div></div><div><h3>Methods</h3><div>We propose Unstructured X-ray - High-Resolution Net (UNSX-HRNet), a framework that integrates high-resolution networks with uncertainty estimation based on anatomical relationships to predict landmarks without relying on a fixed number of points. The method suppresses low-certainty landmarks to accurately handle unstructured data while highlighting the certainty level of each landmark to provide correction guidance. The model was trained and tested on both structured and unstructured datasets, with performance evaluated using multiple precision metrics.</div></div><div><h3>Results</h3><div>Experimental results demonstrate that UNSX-HRNet achieves improvement, exceeding 60 % across multiple evaluation metrics when applied to unstructured datasets. On structured datasets, the framework maintains high performance, showcasing its robustness and adaptability across varying data conditions.</div></div><div><h3>Conclusions</h3><div>UNSX-HRNet offers a reliable and automated solution for THA landmark detection, addressing the challenges of unstructured data through uncertainty-aware predictions. This approach not only improves accuracy but also provides actionable insights for clinicians, contributing to the development of AI-driven expert systems for surgical planning and monitoring.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"198 ","pages":"Article 111146"},"PeriodicalIF":6.3,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145211901","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Introducing surgical workflow recognition in orthopaedic surgery with timestamp supervision.","authors":"Camille Graëff, Nicolas Padoy, Philippe Liverneaux, Thomas Lampert","doi":"10.1016/j.compbiomed.2025.110995","DOIUrl":"10.1016/j.compbiomed.2025.110995","url":null,"abstract":"<p><p>Surgical workflow recognition (SWR) is associated with numerous potential applications to improve patient safety and surgeon performance. So far, SWR studies have mainly focused on endoscopic procedures due to the scarcity of publicly available open surgery video datasets. In this article, we propose for the first time to work on an open orthopaedic surgery called minimally invasive plate osteosynthesis (MIPO) for distal radius fractures (DRFs). For this purpose, we introduce a new dataset with 50 videos of the DRF MIPO procedure, representing almost 30 h of surgery. As far as we know, this currently constitutes the largest publicly available dataset of open surgery videos for SWR. This problem and dataset are particularly challenging due to some specific issues associated with open surgery videos (occlusions, improper camera placements, domain variations, etc.). Using this dataset, we evaluate several state-of-the-art fully-supervised methods to establish a baseline for the prediction of MIPO surgical steps. Then, to reduce the annotation burden required to train such fully-supervised models, we propose a novel weakly-supervised method for SWR, called Uncertainty- and Cluster-Aware Temporal Diffusion (UCATD). UCATD generates reliable pseudo-labels from timestamp annotations (i.e. a single annotated frame per class occurrence) by leveraging uncertainty estimation and clustering information. UCATD significantly outperforms previous state-of-the-art methods based on timestamp supervision, and achieves competitive performance compared to fully-supervised baseline methods, while requiring only 0.1% of the dataset to be annotated.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 Pt A","pages":"110995"},"PeriodicalIF":6.3,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145005994","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Image-based reconstruction of anthropomorphic breast phantoms for synthetic mammogram generation","authors":"Martina Oria ,&nbsp;Riccardo Ferrero ,&nbsp;Chiara Andreis ,&nbsp;Marta Vicentini ,&nbsp;Ruben van Engen ,&nbsp;Carlijn Roozemond ,&nbsp;Paola Lamberti ,&nbsp;Sara Remogna ,&nbsp;Alessandra Manzin","doi":"10.1016/j.compbiomed.2025.111121","DOIUrl":"10.1016/j.compbiomed.2025.111121","url":null,"abstract":"<div><div>The aim of this work is the generation of realistic synthetic mammograms, using as an input of the imaging acquisition simulation process digital anthropomorphic phantoms, reconstructed from sets of dedicated breast computed tomography (BCT) images from different patients. The voxel-based structure and the segmentation into fibroglandular, adipose and skin tissues are performed through trivariate tensor-product B-spline approximation and morphological operations. The obtained phantoms can be modified by means of geometrical transformations that replicate typical breast shape deformities, and by locally introducing virtual masses and calcifications. After simulating biomechanical compression of the 3D breast phantoms, we generate the mammograms in both craniocaudal (CC) and mediolateral oblique (MLO) views, modelling the x-ray interaction with breast tissues with a Monte Carlo approach implemented in the <em>in silico</em> breast imaging pipeline VICTRE.</div><div>The methodology proposed here can contribute to the creation of synthetic mammogram databases, to be used for <em>in silico</em> testing of diagnostic and therapeutic techniques, as well as for the validation of artificial intelligence (AI) systems in diagnostic imaging and cancer screening. The great advantage is that, from a single BCT scan, it is possible to generate multiple realistic mammograms, with different anatomical features, in terms of breast shape and size, and type and location of lesions.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"198 ","pages":"Article 111121"},"PeriodicalIF":6.3,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145211954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}