Computers in biology and medicine最新文献

{"title":"Modeling for dynamical aspects of smoking abuse with e-cigarette users: Threshold dynamics and optimal control strategies","authors":"Abdullah ,&nbsp;Ghaus ur Rahman ,&nbsp;Faira Kanwal Janjua ,&nbsp;Ravi P. Agarwal ,&nbsp;J.F. Gómez-Aguilar","doi":"10.1016/j.compbiomed.2026.111457","DOIUrl":"10.1016/j.compbiomed.2026.111457","url":null,"abstract":"<div><div>Smoking is one of the leading causes of mortality and morbidity around the globe, and e-cigarette use introduces new challenges to public health concerns. Understanding the connection between traditional smoking, e-cigarette adoption, and cessation dynamics is critical for developing effective tobacco-related harm reduction initiatives. In this paper, we present a compartmental mathematical model that captures the transitions between nonsmokers, smokers, e-cigarette users, and quitters while explicitly integrating relapse and cessation behaviors. In the paradigm, e-cigarettes serve as a harm-reduction transition for current smokers, from which users can either quit entirely or return to smoking. The model is analyzed using threshold dynamics to determine the conditions under which smoking behavior persists or declines in a population, and stability analysis is employed to characterize equilibrium states and identify crucial parameters that influence long-term outcomes. Building on this paradigm, we formulate an optimal-control problem by linking control functions to intervention-sensitive processes such as the transition from smoking to e-cigarette usage, the cessation rate among e-cigarette users, and the relapse rate from vaping to smoking. Following harm-reduction principles, the framework prioritizes reducing explosive smoking while discouraging consistent vaping, provided that doing so does not increase smoking prevalence. This paradigm enables researchers to investigate how policy-relevant levers may alter the trajectory of tobacco use over time; however, the report does not compare specific treatments. The model can be extended with numerical simulations that compare the efficacy of interventions like awareness campaigns, taxation, and cessation programs. Such simulations might also include cost-effectiveness studies to determine how limited public health resources could be best allocated across various initiatives. The proposed paradigm provides a theoretical foundation for embedding public health interventions into the dynamics of smoking and e-cigarette use, allowing policymakers and academics to explore how different strategies affect long-term prevalence and reduction outcomes. The graphs illustrate the difference between uncontrolled baseline dynamics and the implementation of an effective management method, demonstrating how interventions can accelerate smoking prevalence reductions. The findings provide a theoretical basis for evaluating how interventions can influence the trajectories of tobacco/vaping use, without claiming to have identified a single “most effective” policy. Future developments could include comparative simulations and cost-effectiveness assessments to help inform targeted decisions related to public health.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111457"},"PeriodicalIF":6.3,"publicationDate":"2026-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146075230","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":"Dementia severity index: A threshold-based approach to classifying dementia levels using resting state EEG","authors":"Shivani Ranjan ,&nbsp;Robin Badal ,&nbsp;Pramod Yadav ,&nbsp;Lalan Kumar","doi":"10.1016/j.compbiomed.2026.111505","DOIUrl":"10.1016/j.compbiomed.2026.111505","url":null,"abstract":"<div><h3>Background</h3><div>Alzheimer’s Disease (AD) and FrontoTemporal Dementia (FTD) are dementia conditions that often overlap clinically, leading to misdiagnoses. Traditional questionnaires are subjective and time-intensive, while neuroimaging is costly and less accessible. EEG-based methods offer a cost-effective alternative but primarily focus on spectral and source analyses, with a limited exploration into quantitative range identification for differentiating dementia states.</div></div><div><h3>Methods</h3><div>This study presents a threshold-based approach to dementia-level classification using resting-state EEG. In particular, an algorithm is presented for threshold computation followed by Dementia Severity Index (DSI) formulation. Two potential biomarkers for cognitive decline that capture band-specific alterations are explored. These biomarkers form the basis of the DSI, categorizing individuals into AD, FTD, or Healthy Control (HC). The classification performance of the proposed DSI is evaluated comprehensively using multiple machine learning classifiers and subject validation strategies.</div></div><div><h3>Results</h3><div>The proposed DSI-based approach achieves classification accuracies of 81.62% using kNN. The approach reliability is validated across three diverse EEG datasets and through threshold variation analysis. Furthermore, the relationship between EEG features and cognitive performance is analyzed using Spearman’s correlation. A significant correlation of 0.79 and 0.62 is obtained between predicted and actual MMSE.</div></div><div><h3>Conclusion</h3><div>The proposed DSI effectively differentiates AD, FTD, and HC, providing a robust threshold-based framework for dementia assessment. It enhances interpretability by assigning quantitative values to dementia states and reduces subjective reliance. This study offers a potential EEG-based biomarker suitable for clinical settings, offering minimal stress to patients during assessments.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111505"},"PeriodicalIF":6.3,"publicationDate":"2026-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146075229","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":"Gender-based data bias and model fairness evaluation in benchmarked open-access disease prediction datasets","authors":"Shahadat Uddin ,&nbsp;Huan Liang ,&nbsp;Haolan Guo","doi":"10.1016/j.compbiomed.2026.111503","DOIUrl":"10.1016/j.compbiomed.2026.111503","url":null,"abstract":"<div><div>The widespread use of open-access datasets for validating machine learning (ML) models has raised critical concerns about data bias and model fairness, particularly in relation to gender. This study systematically investigates gender-based data bias in disease prediction datasets and evaluates the fairness of ML algorithms trained on them. A total of 74 datasets were selected from Kaggle and the UCI Machine Learning Repository, based on the inclusion of gender as a feature and classification labels. Data bias was quantified using Earth Mover's Distance to measure disparities in class-wise gender distributions, with statistical significance assessed via bootstrapping. Fairness was evaluated across seven ML algorithms (Decision Tree, Random Forest, Logistic Regression, Artificial Neural Networks, Support Vector Machine, K-Nearest Neighbours, and Naïve Bayes) using k-fold cross-validation and statistical tests. Two fairness definitions, Equalised Odds and Treatment Equality, were applied. Results showed that 35 datasets exhibited gender-based data bias, disproportionately affecting females. Heart disease datasets had the highest prevalence of data bias, while the lung cancer and mental health datasets were found to be bias-free. Fairness outcomes varied significantly across algorithms, with Decision Tree showing the fewest issues and Logistic Regression the most. Bias-free datasets consistently produced fewer fairness concerns, with statistically significant differences (p &lt; 0.01) across all algorithm groups. These findings highlight the importance of addressing gender-based data bias and selecting appropriate algorithms to improve fairness in ML applications. The study highlights the importance of addressing gender-based data bias in enhancing model fairness. It contributes to the development of equitable AI systems, thereby supporting data-driven decision-making in healthcare.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111503"},"PeriodicalIF":6.3,"publicationDate":"2026-01-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146075228","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":"Peptide-nanoparticle platforms for antisense therapeutics: A coarse-grained modeling approach to brain delivery","authors":"Burcu Yesildag Uner ,&nbsp;Alper Demir ,&nbsp;Pingkun Zhou ,&nbsp;Ekim Z. Taskiran ,&nbsp;Tsjerk Wassenaar","doi":"10.1016/j.compbiomed.2026.111479","DOIUrl":"10.1016/j.compbiomed.2026.111479","url":null,"abstract":"<div><div>Traumatic brain injury (TBI) is a leading cause of long-term neurological deficits, often resulting in complex, unresolved molecular and cellular dysfunctions. Among these, gene–circuit disruptions—particularly those affecting neuroinflammation, oxidative stress, and mitochondrial dynamics—have emerged as critical mediators of post-traumatic neuropathology. In this study, we utilized artificial intelligence (AI)-driven proteomics and RNA sequence integration to map altered signaling pathways following TBI. Computational predictions identified specific gene–circuit nodes susceptible to therapeutic intervention, including redox-sensitive mitochondrial regulators and genes involved in the neuroimmune interface. Importantly, although our analyses are derived from rodent models, the conserved signaling pathways and regulatory circuits identified here provide a translational window with strong relevance to human TBI pathophysiology, thereby bridging preclinical findings with potential therapeutic application. Based on these insights, we designed a suite of responsive nanoparticle formulations optimized in silico for targeted delivery to dysregulated brain regions. These carriers incorporated ligands targeting disrupted circuits and incorporated redox-sensitive release mechanisms. Our platform demonstrates the feasibility of a closed-loop, data-guided strategy that integrates AI-based gene network profiling with rational nanocarrier design. This approach provides a scalable framework for precision neurotherapeutics, particularly for complex disorders such as TBI where conventional monotherapies have proven inadequate.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111479"},"PeriodicalIF":6.3,"publicationDate":"2026-01-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146046221","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":"Reconstructing in-vitro and in-vivo signals and parameters in networks of elastic vessels using physics-informed neural networks","authors":"J. Orera,&nbsp;J. Mairal,&nbsp;L. Sánchez-Fuster,&nbsp;J. Murillo","doi":"10.1016/j.compbiomed.2026.111472","DOIUrl":"10.1016/j.compbiomed.2026.111472","url":null,"abstract":"<div><div>The reconstruction of waveforms and hidden parameters is crucial for the physical modeling of steady and transient flows in networks of elastic vessels (arteries), where many mechanical properties are not directly measurable. This work investigates the potential of Physics-Informed Neural Networks (PINNs) to address the challenge of reconstructing pressure and flow signals and inferring parameters from experimental data. We incorporate the zero-dimensional (0D) system of coupled differential equations that describe flow in elastic vessels into the neural network, which we call 0D-PINN. We evaluate our methodology with several test cases representing different dynamical systems, including an experimental mock arterial network with 37 silicone vessels replicating the human arterial system, as well as a clinical case based on in-vivo MRI data from a healthy adult’s thoracic aorta. It is shown that coupling 0D models with Physics-Informed Neural Networks (PINNs) enables the recovery of parameters and waveforms from experimental in-vitro or in-vivo data.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111472"},"PeriodicalIF":6.3,"publicationDate":"2026-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146036224","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 neural network-guided identification and biological evaluation of potential AKT1 inhibitors for triple-negative breast cancer","authors":"Ravishankar Jaiswal ,&nbsp;Girdhar Bhati ,&nbsp;Santosh Shukla ,&nbsp;Shakil Ahmed ,&nbsp;Mohammad Imran Siddiqi","doi":"10.1016/j.compbiomed.2026.111481","DOIUrl":"10.1016/j.compbiomed.2026.111481","url":null,"abstract":"<div><div>Triple-negative breast cancer (TNBC) presents a significant therapeutic challenge due to its aggressive behavior and lack of targeted therapies. The PI3K/AKT/mTOR signaling pathway, particularly AKT1, is frequently dysregulated in TNBC, driving disease progression. Despite extensive research, many clinically evaluated AKT1 inhibitors have encountered challenges related to both efficacy and tolerability, highlighting the need for novel therapeutics. Here, we employed graph neural networks (GNNs) for molecular graph-based prediction of potential AKT1 inhibitors. Six GNN architectures, including attention-based (AttentiveFP, GATv2Conv, TransformerConv) and non-attention-based (GCNConv, GINConv, GraphSAGE) models were trained and benchmarked against traditional machine learning (ML) methods using random and scaffold-based data splits. To enhance predictive relevance and model generalizability, we integrated phenotypic screening data from breast cancer (BC) cell lines alongside AKT1 bioassay data to capture broader pathway effects. Screening the Maybridge chemical library, we identified 9 novel scaffold compounds through consensus hit selection, molecular docking, and novelty filtration. Enzymatic validation confirmed 4 early-stage AKT1 inhibitors with low-micromolar potency (IC₅₀ down to 2.5 μM). Explainable AI analyses using Integrated Gradients and Captum saliency maps highlighted key structural features driving AKT1 inhibition, providing interpretable structure-activity relationship (SAR) insights. Scaffold diversity analysis further confirmed that the validated hits occupy chemical space distinct from known AKT1 inhibitors. Overall, this study presents an interpretable AI-driven discovery framework that identifies novel AKT1 inhibitor scaffolds and provides a validated starting point for hit-to-lead optimization in TNBC drug discovery.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111481"},"PeriodicalIF":6.3,"publicationDate":"2026-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146036157","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":"HybridDeepSynergy: A hybrid deep learning model integrating CNN, LSTM, and attention mechanisms for cancer drug synergy prediction","authors":"Sajid Naveed ,&nbsp;Mujtaba Husnain ,&nbsp;Najah Alsubaie","doi":"10.1016/j.compbiomed.2026.111471","DOIUrl":"10.1016/j.compbiomed.2026.111471","url":null,"abstract":"<div><div>A variety of AI-based approaches have been employed to analyze complex genomic datasets. Predicting the synergy of drug combinations is a critical step toward optimizing cancer treatment by identifying the most effective drug pairs. This study presents HybridDeepSynergy, a novel hybrid deep learning model that integrates Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Transformer attention mechanisms to predict drug synergy across diverse drug combinations and cancer cell lines. The model is designed to enhance precision medicine and cancer treatment outcomes.</div><div>HybridDeepSynergy leverages CNNs to capture local feature interactions, LSTMs to model sequential dependencies, and attention mechanisms to extract long-range relationships within the data. The model was trained and evaluated on a comprehensive dataset containing numerous drug combinations, using five established synergy scoring models: Bliss Independence (BLISS), Zero Interaction Potency (ZIP), Loewe Additivity (LOEWE), Highest Single Agent (HSA), and General Synergy (S).</div><div>Our model demonstrated superior performance compared to existing approaches, achieving a lower Root Mean Squared Error (RMSE = 3.911) and Mean Absolute Error (MAE = 2.922), along with higher coefficients of determination (<span><math><msup><mi>R</mi><mn>2</mn></msup></math></span> = 0.953), Pearson correlation (0.917), and Spearman correlation (0.886). These results confirm its predictive efficiency and consistency across multiple synergy scoring models. Furthermore, the incorporation of attention mechanisms provides interpretability by highlighting significant features associated with drug resistance.</div><div>Future work will focus on incorporating additional cancer datasets, enhancing model predictive capabilities, and validating the approach in clinical settings to support personalized medicine. The findings suggest that HybridDeepSynergy has the potential to substantially improve treatment strategies for cancer and may be applicable to other disease contexts.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111471"},"PeriodicalIF":6.3,"publicationDate":"2026-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146028663","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":"MS-CoTF: Multi-scale chain-of-thought fusion for interpretable biological reasoning with large language models","authors":"Zeyuan Song ,&nbsp;Xiao-Cong Zhen","doi":"10.1016/j.compbiomed.2026.111467","DOIUrl":"10.1016/j.compbiomed.2026.111467","url":null,"abstract":"<div><div>Large language models (LLMs) have demonstrated impressive proficiency in various science and engineering applications. However, due to the innate multi-scale property of biological systems, existing LLMs face severe limitations in capturing hierarchical relationships and context-dependent interactions across molecular, cellular, tissue, and systemic levels. These models often lack the architectural mechanisms needed to reason effectively across different biological scales, resulting in reduced accuracy and limited interpretability when applied to complex tasks. Here, we introduce a novel framework named multi-scale chain-of-thought fusion (MS-CoTF), which fuses reasoning at molecular, cellular, tissue, and system scales to enhance accuracy and interpretability when solving biological tasks. Through adaptive reasoning depth control, multi-scale integration, bi-directional flow and dynamic fusion strategies, our MS-CoTF model effectively processes queries of varying complexity, enabling scalable and interpretable reasoning across multiple biological levels. Ablation studies demonstrate that these components function synergistically to enhance model accuracy while simultaneously providing biologically meaningful insights. Furthermore, our MS-CoTF model consistently outperforms state-of-the-art reasoning models by 10–15% across three benchmark problems and two case studies in terms of accuracy, expert ratings, and the capacity to produce reasonable inference chains. Technically, MS-CoTF orchestrates a frozen biomedical LLM backbone with trainable cross-scale modules, employing a precise definition of per-step chain-of-thought (CoT) construction and linking. To ensure rigorous evaluation, we implement an explicit dataset splitting protocol (entity-disjoint and temporal) and utilize the Reasoning Coherence Score strictly as a post-hoc metric to ensure fair comparisons. We further validate the framework through extended baselines, including structure-conditioned and multimodal biomedical LLMs, alongside detailed human evaluation protocols and hallucination stress tests.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111467"},"PeriodicalIF":6.3,"publicationDate":"2026-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146028623","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 hybrid hierarchical transformer model for ECG classification and age prediction","authors":"Pedro Dutenhefner ,&nbsp;Turi Rezende ,&nbsp;José Geraldo Fernandes ,&nbsp;Diogo Tuler ,&nbsp;Gabriela M.M. Paixão ,&nbsp;Gisele Pappa ,&nbsp;Antønio Ribeiro ,&nbsp;Wagner Meira Jr.","doi":"10.1016/j.compbiomed.2026.111462","DOIUrl":"10.1016/j.compbiomed.2026.111462","url":null,"abstract":"<div><div>Electrocardiograms (ECGs) play a crucial role in cardiovascular healthcare, requiring effective analytical models. ECG analysis is inherently hierarchical, involving multiple temporal scales from individual waveforms to intervals within heartbeats, and finally to the distances between heartbeats. Convolutional Neural Networks (CNNs) have demonstrated strong performance in ECG classification tasks due to their inductive bias toward local connectivity and translation invariance. In other domains, Transformers have emerged as powerful models for capturing long-range dependencies. This paper introduces HiT-NeXt, a hybrid hierarchical model designed to capture both local morphological patterns and global temporal dependencies by combining CNNs with transformer blocks featuring restricted attention windows. The model incorporates ConvNeXt-based convolutional layers to extract local features and perform patch merging, enabling hierarchical representation learning. Transformer blocks are constrained with local attention windows and leverage relative contextual positional encoding to incorporate positional information effectively into embeddings, enhancing robustness to translations in ECG signal patterns. Experimental results demonstrate that HiT-NeXt outperforms state-of-the-art methods on tasks including ECG abnormality classification and cardiological age prediction, achieving superior performance compared to both existing models and cardiologist evaluations.<span><span>²</span></span></div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111462"},"PeriodicalIF":6.3,"publicationDate":"2026-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146028640","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":"Research on breast ultrasound images lesion localization and diagnosis based on knowledge-driven and data-driven methods","authors":"Jianqiang Li ,&nbsp;Lintao Song ,&nbsp;Xiaoling Liu ,&nbsp;Yiming Liu ,&nbsp;Tianbao Ma ,&nbsp;Jun Bai ,&nbsp;Qing Zhao ,&nbsp;Xi Xu","doi":"10.1016/j.compbiomed.2026.111465","DOIUrl":"10.1016/j.compbiomed.2026.111465","url":null,"abstract":"<div><div>Breast cancer poses the most significant threat to women’s health, yet early detection through screening can markedly reduce mortality. Ultrasound imaging, with its affordability, non-invasiveness, and efficacy in dense breast tissue, has emerged as a crucial tool for early screening. Recent advancements in computer vision have spurred the development of computer-aided diagnostic systems that focus on the automated localization and diagnosis of breast lesions. However, challenges such as speckle noise, blurred boundaries, and low contrast in ultrasound images impede accurate lesion detection. This review examines recent studies on breast ultrasound lesion localization and diagnosis, emphasizing model feature construction. It provides an overview of the task, available datasets, and evaluation metrics, and outlines selection criteria through a comprehensive literature analysis. The review categorizes models into three groups: domain knowledge-driven, data-driven, and hybrid approaches. It also discusses current challenges and future directions, aiming to enhance the accuracy of breast lesion localization and diagnosis.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"203 ","pages":"Article 111465"},"PeriodicalIF":6.3,"publicationDate":"2026-01-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146017584","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}