Computers in biology and medicine最新文献

{"title":"Benign vs malignant tumors classification from tumor outlines in mammography scans using artificial intelligence techniques","authors":"Hamidreza Mortazavy Beni,&nbsp;Fatemeh Yekta Asaei","doi":"10.1016/j.compbiomed.2025.111118","DOIUrl":"10.1016/j.compbiomed.2025.111118","url":null,"abstract":"<div><div>Breast cancer is one of the most important causes of death among women due to cancer. With the early diagnosis of this condition, the probability of survival will increase. For this purpose, medical imaging methods, especially mammography, are used for screening and early diagnosis of breast abnormalities. The main goal of this study is to distinguish benign or malignant tumors based on tumor morphology features extracted from tumor outlines extracted from mammography images. Unlike previous studies, this study does not use the mammographic image itself but only extracts the exact outline of the tumor.</div><div>These outlines were extracted from a new and publicly available mammography database published in 2024. The features outlines were calculated using known pre-trained Convolutional Neural Networks (CNN), including VGG16, ResNet50, Xception65, AlexNet, DenseNet, GoogLeNet, Inception-v3, and a combination of them to improve performance. These pre-trained networks have been used in many studies in various fields. In the classification part, known Machine Learning (ML) algorithms, such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Neural Network (NN), Naïve Bayes (NB), Decision Tree (DT), and a combination of them have been compared in outcome measures, namely accuracy, specificity, sensitivity, and precision. Also, with the use of data augmentation, the dataset size was increased about 6–8 times, and the K-fold cross-validation technique (K = 5) was used in this study. Based on the performed simulations, a combination of the features from all pre-trained deep networks and the NB classifier resulted in the best possible outcomes with 88.13 % accuracy, 92.52 % specificity, 83.73 % sensitivity, and 92.04 % precision. Furthermore, validation on DMID dataset using ResNet50 features along with NB classifier, led to 92.03 % accuracy, 95.57 % specificity, 88.49 % sensitivity, and 95.23 % precision. This study sheds light on using AI algorithms to prevent biopsy tests and speed up breast cancer tumor classification using tumor outlines in mammographic images.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 ","pages":"Article 111118"},"PeriodicalIF":6.3,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145118158","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":"Machine learning–driven discovery of NSC828779 as a multi-mechanistic NLRP3 inflammasome inhibitor for inflammatory diseases","authors":"Sung-Ling Tang ,&nbsp;Maryam Rachmawati Sumitra ,&nbsp;Lung-Ching Chen ,&nbsp;Feng-Cheng Liu ,&nbsp;Han-Lin Hsu ,&nbsp;Yu-Cheng Kuo ,&nbsp;Muhamad Ansar ,&nbsp;Sheng-Liang Huang ,&nbsp;Shih-Yu Lee ,&nbsp;Hong-Jaan Wang ,&nbsp;Bashir Lawal ,&nbsp;Alexander T.H. Wu ,&nbsp;Ya-Ting Wen ,&nbsp;Hsu-Shan Huang","doi":"10.1016/j.compbiomed.2025.111110","DOIUrl":"10.1016/j.compbiomed.2025.111110","url":null,"abstract":"<div><div>The NLRP3 inflammasome is a key regulator of the innate immune response and a promising therapeutic target in inflammation-driven diseases. This study aimed to identify potent nature inspired small molecules using AI-guided in silico techniques integrated with NCI-60 high-throughput assays. We developed a machine learning–driven platform that combines pharmacophore modeling, molecular docking, MDS, and RNNs to prioritize candidate compounds. Among these, NSC828779 emerged as a lead scaffold, demonstrating high binding affinity to the ATP-binding site of NLRP3 and superior interaction energy and stability compared to known inhibitors. Docking scores were strongest for NLRP3 (−10.5 kcal/mol), caspase-1 (−8.6 kcal/mol), and ASC (−8.5 kcal/mol), outperforming MCC950, glyburide, and other reference compounds. MDS confirmed the stability of the NLRP3–ASC–caspase-1 complex, supported by RMSD and RMSF analyses showing enhanced conformational integrity. ADMET profiling predicted favorable drug-likeness, solubility, moderate lipophilicity, and low toxicity. Mechanistically, NSC828779 may act as a multi-mechanistic NLRP3 inhibitor by disrupting protein–protein interactions, inhibiting NF-κB signaling, and inducing autophagy. These results establish NSC828779 as a promising candidate for treating inflammation-related disorders and underscore the utility of AI-driven drug discovery platforms in identifying novel inflammasome-targeted therapeutics. Further in vitro and in vivo validation is warranted to support its clinical development.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 ","pages":"Article 111110"},"PeriodicalIF":6.3,"publicationDate":"2025-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145118159","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":"Automatic motor and visuospatial cognition screening with ensemble learning: A computerised clock drawing test approach","authors":"Andrius Lauraitis,&nbsp;Armantas Ostreika,&nbsp;Gintaras Palubeckis,&nbsp;Liudas Motiejunas","doi":"10.1016/j.compbiomed.2025.111107","DOIUrl":"10.1016/j.compbiomed.2025.111107","url":null,"abstract":"&lt;div&gt;&lt;div&gt;We propose a supervised ensemble learning-based approach to evaluate the significance of the digitised analogue clock drawing test (CDT) for the detection of neural impairments in patients with early-stage central nervous system disorders (CNSD). The research findings are based on the data samples that have been collected using the clock construction task of the Neural Impairment Test Suite (NITS) mobile application from 15 test subjects (including Huntington Disease (HD), Parkinson Disease (PD), cerebral palsy (CP), post-stroke, early dementia and control groups) during a pilot study in Lithuania. This work examines finger motion tracking (FMT) on a mobile device and the detection of potential inability of CNSD patients to accurately copy benchmark clock drawings without a pre-drawn clock contour circle, focusing on multimodal (datasets of FMT samples and CDT images) neural impairment screening. Considering the small size of the originally gathered imbalanced datasets, as pre-processing routines, Synthetic Minority Oversampling Technique (SMOTE) was used for the FMT augmentation, and the geometric image transformations (rotation, flip, zoom) were applied for the augmentation of CDT drawings.&lt;/div&gt;&lt;div&gt;The following methods for feature extraction are used regarding the FMT and CDT image datasets accordingly: 1) average finger speed while moving on the surface, finger velocity, magnitude of the rate at which finger tap changes its position, standard deviation (SD) of velocity, rate at which finger velocity changes, maximum finger acceleration, finger position change count, average finger screen pressure and touch area ratio (in range [0; 1]), total time duration (in seconds); 2) Edge Histogram Filter (EHD), Pyramid Histogram of Oriented Gradients (PHOG), Gabor wavelet and their fusion.&lt;/div&gt;&lt;div&gt;Two experiments (E1, E2) were conducted to solve healthy vs. impaired binary classification problem. The nature of E1 design that is tracking motor impairments in CNSD and detecting cognitive impairments is targeted in E2. All classifiers (K-NN, Naïve Bayes, ANN, SMO, SVM and their ensembles) were tested with a 5-fold stratified cross-validation procedure, and the performances of classification models were evaluated by accuracy, balanced accuracy (BA), F1 score, sensitivity, specificity, kappa, receiver-operating characteristic area under the curve (AUC-ROC), mean absolute error (MAE), root mean squared error (RMSE) metrics. The Principal Component Analysis (PCA) method was used for the dimensionality reduction in high-dimensional image feature vectors. The overfitting of models was addressed by comparing the learning curves (training and validation sets). Results: 1) in E1, the highest 99.20 % accuracy precision (boosted SMO algorithm with PuK kernel) was achieved on SMOTE synthesised FMT train set and 99.40 % accuracy on FMT test set; 2) in E2 (augmented dataset of CDT images), the highest 97.96 % accuracy (94.90 % on test set) was achieved wit","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 ","pages":"Article 111107"},"PeriodicalIF":6.3,"publicationDate":"2025-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145099573","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":"Antioxidant efficacy of hydroxytyrosol, tyrosol, homovanillic alcohol, and their acetate derivatives in Parkinson's disease: A synergistic computational approach","authors":"Rituraj Barman ,&nbsp;Benzir Ahmed ,&nbsp;Hemchandra Deka ,&nbsp;Manazira Ahmed ,&nbsp;Pratyashee Barukial ,&nbsp;Debabrat Baishya ,&nbsp;Bipul Bezbaruah","doi":"10.1016/j.compbiomed.2025.111104","DOIUrl":"10.1016/j.compbiomed.2025.111104","url":null,"abstract":"<div><div>Phenolic plant metabolites, including hydroxytyrosol, tyrosol, homovanillic alcohol, and their acetate derivatives, have emerged as potent antioxidants and promising therapeutic candidates for neurodegenerative disorders. These compounds exhibit dual functionality by efficiently scavenging reactive free radicals and targeting key protein residues, thereby alleviating oxidative stress and preventing cellular damage. Using multiscale <em>in silico</em> methodologies, their interactions with peroxyl (ROO^•) and hydroperoxyl (HOO^•) radicals, as well as with Monoamine Oxidase A (MAO-A), a pivotal enzyme in Parkinson's disease, were systematically investigated. Density Functional Theory (DFT) analyses illustrate radical stabilization pathways, supported by MEP, SD, NBO, FMO, and Fukui function descriptors. Hirshfeld surface analysis (HSA) and QTAIM further reveal strong binding hotspots, predominantly stabilized by conventional hydrogen bonding complemented with hydrophobic non-covalent contacts. ADMET profiling underscored favorable pharmacokinetic properties and drug-likeness. Finally, molecular docking and molecular dynamics (MD) simulations confirmed their stable accommodation within the MAO-A catalytic pocket, highlighting significant binding affinities and critical interacting residues. Overall, these findings establish hydroxytyrosol, tyrosol and homovanillic alcohol derivatives as potential multifunctional neuroprotective agents against Parkinson's disease.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 ","pages":"Article 111104"},"PeriodicalIF":6.3,"publicationDate":"2025-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145099575","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":"Effects of pulmonary hypertension on right ventricular mechanics and coronary perfusion: Insights from computational simulations","authors":"Chenghan Cai ,&nbsp;Jenny S. Choy ,&nbsp;Ge He ,&nbsp;Michael E. Widlansky ,&nbsp;Ghassan S. Kassab ,&nbsp;Lei Fan","doi":"10.1016/j.compbiomed.2025.111113","DOIUrl":"10.1016/j.compbiomed.2025.111113","url":null,"abstract":"<div><div>Pulmonary hypertension (PH), defined by elevated mean pulmonary arterial pressure (mPAP), is a leading cause of right heart failure (RHF). However, the mechanisms linking PH to ventricular dysfunction and coronary ischemia remain unclear. An advanced mechanistic understanding is critical for improving clinical diagnosis and treatment strategies. This study aimed to investigate the impact of acute and chronic PH on biventricular mechanics and coronary perfusion. We developed a computational model that integrates coronary perfusion in the major coronary arteries with a biventricular finite element (FE) model in a closed-loop systemic and pulmonary circulation. Validated against clinical measurements, the computational model was applied to simulate the hemodynamics and myocardial perfusion across coronary territories and myocardial walls under conditions of acute and chronic PH. Model predictions demonstrated that in acute PH, coronary flow in the right ventricular free wall (RVFW) and septum was reduced due to elevated intramyocardial pressure (IMP), especially in the endocardium. In chronic PH, coronary flow was reduced in the RVFW, septum, and left ventricular free wall (LVFW) due to diminished perfusion pressure. These findings are consistent with clinical observations: the right-dominant right coronary artery (RCA) is more vulnerable to ischemia in acute PH, whereas the left-dominant left circumflex artery (LCx) is more vulnerable in chronic PH. In conclusion, chronic PH may contribute to subclinical left ventricular dysfunction and increased ischemic risk through impaired coronary perfusion, highlighting potential targets for therapeutic interventions in PH-related RHF.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 ","pages":"Article 111113"},"PeriodicalIF":6.3,"publicationDate":"2025-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145099576","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":"Few-shot diagnosis of chest x-ray images using auxiliary information guided semi-deterministic infinite mixture prototypes","authors":"Prabhala Sandhya Gayatri ,&nbsp;Devi Prasad Maharathy ,&nbsp;Angshuman Paul","doi":"10.1016/j.compbiomed.2025.111053","DOIUrl":"10.1016/j.compbiomed.2025.111053","url":null,"abstract":"<div><div>We propose a few-shot learning (FSL) approach for the diagnosis of chest x-ray images. Our model can be trained with a small number of annotated data by utilizing auxiliary semantic information about the abnormalities under consideration. In our design, we consider the fact that because of various factors, there may be variations in the visual characteristics of an abnormality in x-rays. Hence, in a multi-label dataset, it is challenging to represent data points with a particular abnormality in one cluster based on visual features. Our few-shot learning approach dynamically generates multiple clusters to accurately represent a particular abnormality. The generation of multiple clusters is achieved using a semi-deterministic infinite mixture prototype method. The clustering process is guided by semantic information corresponding to the abnormalities. Thus, our method aims to create a discriminative representation for x-ray images utilizing semantic information about the abnormalities under consideration. Experiments on publicly available chest x-ray datasets show the efficacy of the proposed method for the diagnosis of chest x-ray images. Our code is publicly available in this <span><span>repository</span><svg><path></path></svg></span>.<span><span>²</span></span></div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 ","pages":"Article 111053"},"PeriodicalIF":6.3,"publicationDate":"2025-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145099574","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":"Enhancing the reliability of Alzheimer's disease prediction in MRI images","authors":"Junaidul Islam ,&nbsp;Elvin Nur Furqon ,&nbsp;Isack Farady ,&nbsp;John Sahaya Rani Alex ,&nbsp;Cheng-Ting Shih ,&nbsp;Chia-Chen Kuo ,&nbsp;Chih-Yang Lin","doi":"10.1016/j.compbiomed.2025.111111","DOIUrl":"10.1016/j.compbiomed.2025.111111","url":null,"abstract":"<div><div>Alzheimer's Disease (AD) diagnostic procedures employing Magnetic Resonance Imaging (MRI) analysis encounter considerable obstacles pertaining to reliability and accuracy, especially when deep learning models are utilized within clinical environments. Present deep learning methodologies for MRI-based AD detection frequently demonstrate spatial dependencies and exhibit deficiencies in robust validation mechanisms. Extant validation techniques inadequately integrate anatomical knowledge and exhibit challenges in feature interpretability across a range of imaging conditions. To address this fundamental gap, we introduce a reverse validation paradigm that systematically repositions anatomical structures to test whether models recognize features based on anatomical characteristics rather than spatial memorization. Our research endeavors to rectify these shortcomings by proposing three innovative methodologies: Feature Position Invariance (FPI) for the validation of anatomical features, biomarker location augmentation aimed at enhancing spatial learning, and High-Confidence Cohort (HCC) selection for the reliable identification of training samples. The FPI methodology leverages reverse validation approach to substantiate model predictions through the reconstruction of anatomical features, bolstered by our extensive data augmentation strategy and a confidence-based sample selection technique. The application of this framework utilizing YOLO and MobileNet architecture has yielded significant advancements in both binary and three-class AD classification tasks, achieving state-of-the-art accuracy with enhancements of 2–4 % relative to baseline models. Additionally, our methodology generates interpretable insights through anatomy-aligned validation, establishing direct links between model decisions and neuropathological features. Our experimental findings reveal consistent performance across various anatomical presentations, signifying that the framework effectively enhances both the reliability and interpretability of AD diagnosis through MRI analysis, thereby equipping medical professionals with a more robust diagnostic support system.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 ","pages":"Article 111111"},"PeriodicalIF":6.3,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145099571","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":"Early-stage Parkinson’s disease detection using multimodal brain–body biomarkers from fNIRS and IMU data","authors":"Maryam Sousani ,&nbsp;Raul Fernandez Rojas ,&nbsp;Elisabeth Preston ,&nbsp;Maryam Ghahramani","doi":"10.1016/j.compbiomed.2025.111096","DOIUrl":"10.1016/j.compbiomed.2025.111096","url":null,"abstract":"<div><div>Parkinson’s Disease (PD) is a progressive neurodegenerative disorder that impairs both motor and cognitive functions. Accurate detection of PD remains a major challenge, particularly at early stages when clinical symptoms are subtle. This study presents the first multimodal machine learning framework integrating functional near-infrared spectroscopy (fNIRS) and inertial measurement unit (IMU) data for early-stage PD detection during dual-task mobility assessments. Data were collected from 62 participants, including 28 people with PD and 34 age-matched controls, who performed the clinically recommended Timed Up and Go (TUG), Cognitive Dual-Task TUG (CDTUG), and Motor Dual-Task TUG (MDTUG) tests. This complex multimodal experimental design simultaneously captured brain activation and body motion under motor and cognitive dual-task conditions. Four machine learning models combined with two feature selection techniques were applied to unimodal and multimodal datasets. The multimodal approach achieved superior classification accuracy (96%) compared to fNIRS-only (87%) and IMU-only (95%) models. Key brain–body biomarkers were identified, including dorsolateral prefrontal and frontopolar cortex activations during dual tasks, alongside motor features such as turn, sit-to-stand, and stand-to-sit durations. These findings highlight the promise of combining brain and motion measures and complex functional mobility tests for early-stage PD detection and advance the development of non-invasive, AI-driven biomarker discovery frameworks.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 ","pages":"Article 111096"},"PeriodicalIF":6.3,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145099627","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":"Pitfalls of defacing whole-head MRI: re-identification risk with diffusion models and compromised research potential","authors":"Chenyu Gao ,&nbsp;Kaiwen Xu ,&nbsp;Michael E. Kim ,&nbsp;Lianrui Zuo ,&nbsp;Zhiyuan Li ,&nbsp;Derek B. Archer ,&nbsp;Timothy J. Hohman ,&nbsp;Ann Zenobia Moore ,&nbsp;Luigi Ferrucci ,&nbsp;Lori L. Beason-Held ,&nbsp;Susan M. Resnick ,&nbsp;Christos Davatzikos ,&nbsp;Jerry L. Prince ,&nbsp;Bennett A. Landman","doi":"10.1016/j.compbiomed.2025.111112","DOIUrl":"10.1016/j.compbiomed.2025.111112","url":null,"abstract":"<div><div>Defacing is often applied to head magnetic resonance image (MRI) datasets prior to public release to address privacy concerns. The alteration of facial and nearby voxels has provoked discussions about the true capability of these techniques to ensure privacy as well as their impact on downstream tasks. With advancements in deep generative models, the extent to which defacing can protect privacy is uncertain. Additionally, while the altered voxels are known to contain valuable anatomical information, their potential to support research beyond the anatomical regions directly affected by defacing remains uncertain. To evaluate these considerations, we develop a refacing pipeline that recovers faces in defaced head MRIs using cascaded diffusion probabilistic models (DPMs). The DPMs are trained on images from 180 subjects and tested on images from 484 unseen subjects, 469 of whom are from a different dataset. To assess whether the altered voxels in defacing contain universally useful information, we also predict computed tomography (CT)-derived skeletal muscle radiodensity from facial voxels in both defaced and original MRIs. The results show that DPMs can generate high-fidelity faces that resemble the original faces from defaced images, with surface distances to the original faces significantly smaller than those of a population average face (p &lt; 0.05). This performance also generalizes well to previously unseen datasets. For skeletal muscle radiodensity predictions, using defaced images results in significantly weaker Spearman’s rank correlation coefficients compared to using original images (p ≤ 10⁻⁴). For shin muscle, the correlation is statistically significant (p &lt; 0.05) when using original images but not statistically significant (p &gt; 0.05) when any defacing method is applied, suggesting that defacing might not only fail to protect privacy but also eliminate valuable information. We advocate two solutions for data sharing that comply with privacy: 1) share skull-stripped images along with measurements of facial and cranial features extracted before skull-stripping for public access, while acknowledging that this approach inherently compromises many research potentials; or 2) share the unaltered images with privacy enforced through policy restrictions.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 ","pages":"Article 111112"},"PeriodicalIF":6.3,"publicationDate":"2025-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145099572","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":"Tensor analysis of animal behavior by matricization and feature selection","authors":"Beichen Wang ,&nbsp;Jiazhang Cai ,&nbsp;Luyang Fang ,&nbsp;Motokazu Tsujikawa ,&nbsp;Ping Ma ,&nbsp;Yuk Fai Leung","doi":"10.1016/j.compbiomed.2025.110959","DOIUrl":"10.1016/j.compbiomed.2025.110959","url":null,"abstract":"<div><div>Contemporary neurobehavior research often collects multi-dimensional tensor (MDT) data containing time-series measurements for multiple features from multiple animals subjected to various perturbations. Proper analysis of the MDT data can reveal neural circuitries driving the behavior. However, many MDT analyses, such as tensor decomposition, may not yield results that are easy to interpret or directly compatible with standard multivariate analysis designed for 2-dimensional tensor (2DT) structures. To address this issue, the MDT data are transformed into 2DT by dimensionality reduction techniques, including matricization methods such as Index Construction and Feature Concatenation. Nonetheless, matricization may exclude key information or introduce spurious noise to multivariate analysis, so its impact on multivariate analysis remains elusive. Here, we demonstrated different matricization approaches and feature selection methods. We evaluated their impacts on multivariate analysis performance using an MDT dataset of zebrafish visual-motor response collected from wildtypes and visually-impaired mutants. We matricized the MDT dataset using various Index Construction and Feature Concatenation methods, then identified informative 2DT features using the filter and embedded methods. To evaluate these feature-selection methods, we applied several classifiers to distinguish zebrafish of different genotypes and assessed their performances with cross-validation and holdout validation. We found that most classifiers performed the best using 2DT features matricized by Feature Concatenation and selected by the embedded method or union operation. The results also revealed unique behavioral differences between the wildtypes and mutants, but not identified by multivariate analysis or MDT analysis. Our results demonstrate the utility of analyzing MDT behavioral data by matricization and feature selection.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"197 ","pages":"Article 110959"},"PeriodicalIF":6.3,"publicationDate":"2025-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145091308","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}