Medical & Biological Engineering & Computing最新文献

{"title":"Systematic review of artificial intelligence methods for detection and segmentation of unruptured intracranial aneurysms using medical imaging.","authors":"Mario Mata-Castillo, Andrea Hernández-Villegas, Nelly Gordillo-Castillo, José Díaz-Román","doi":"10.1007/s11517-025-03345-7","DOIUrl":"10.1007/s11517-025-03345-7","url":null,"abstract":"<p><p>Unruptured intracranial aneurysms are protuberances that appear in cerebral arteries, and their diagnostic evaluation can be a complex, time-consuming, and exhaustive task. In recent years, computer-aided systems have been developed to improve diagnostic processes. Although the proposed methods have already been reviewed to assess their suitability for clinical use, the segmentation methods have not been reviewed in detail, nor has there been a standardized way to compare segmentation and detection tasks. A systematic review was conducted to examine the technical and methodological factors contributing to this limitation. The analysis encompassed 49 studies conducted between 2019 and 2023 that utilized artificial intelligence methods and any medical imaging modality for the detection or segmentation of intracranial aneurysms. Most of the included studies focused exclusively on detection (57%), magnetic resonance angiography was the predominant imaging modality (47%), and the methodologies generally used 3D imaging as the input (71%). The reported sensitivities ranged from 0.68 to 0.90, specificities from 0.18 to 1.0, false positives per case from 0.18 to 13.8, and the Dice similarity coefficient from 0.53 to 0.98. Variations in aneurysm size were found to have a substantial impact on system performance. Studies were evaluated using a diagnostic accuracy study quality assessment tool, which revealed significant concerns regarding applicability. These concerns primarily stem from the poor reproducibility and inconsistent reporting of metrics. Recommendations for reporting outcomes were made to compare procedures across different types of imaging and tasks.</p>","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"2521-2536"},"PeriodicalIF":2.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143651681","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A machine learning approach for type 2 diabetes diagnosis and prognosis using tailored heterogeneous feature subsets.","authors":"J Ramón Navarro-Cerdán, Pedro Pons-Suñer, Laura Arnal, Joaquim Arlandis, Rafael Llobet, Juan-Carlos Perez-Cortes, Francisco Lara-Hernández, Celeste Moya-Valera, Maria Elena Quiroz-Rodriguez, Gemma Rojo-Martinez, Sergio Valdés, Eduard Montanya, Alfonso L Calle-Pascual, Josep Franch-Nadal, Elias Delgado, Luis Castaño, Ana-Bárbara García-García, Felipe Javier Chaves","doi":"10.1007/s11517-025-03355-5","DOIUrl":"10.1007/s11517-025-03355-5","url":null,"abstract":"<p><p>Type 2 diabetes (T2D) is becoming one of the leading health problems in Western societies, diminishing quality of life and consuming a significant share of healthcare resources. This study presents machine learning models for T2D diagnosis and prognosis, developed using heterogeneous data from a Spanish population dataset (Di@bet.es study). The models were trained exclusively on individuals classified as controls and undiagnosed diabetics, ensuring that the results are not influenced by treatment effects or behavioral changes due to disease awareness. Two data domains are considered: environmental (patient lifestyle questionnaires and measurements) and clinical (biochemical and anthropometric measurements). The preprocessing pipeline consists of four key steps: geospatial data extraction, feature engineering, missing data imputation, and quasi-constancy filtering. Two working scenarios (Environmental and Healthcare) are defined based on the features used, and applied to two targets (diagnosis and prognosis), resulting in four distinct models. The feature subsets that best predict the target have been identified based on permutation importance and sequential backward selection, reducing the number of features and, consequently, the cost of predictions. In the Environmental scenario, models achieved an AUROC of 0.86 for diagnosis and 0.82 for prognosis. The Healthcare scenario performed better, with an AUROC of 0.96 for diagnosis and 0.88 for prognosis. A partial dependence analysis of the most relevant features is also presented. An online demo page showcasing the Environmental and Healthcare T2D prognosis models is available upon request.</p>","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"2733-2752"},"PeriodicalIF":2.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12402034/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143812799","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Segmentation of lungs from chest X-ray images based on Deep Atrous Attention UNet (DAA-UNet) model.","authors":"Vivek Kumar Yadav, Jyoti Singhai","doi":"10.1007/s11517-025-03344-8","DOIUrl":"10.1007/s11517-025-03344-8","url":null,"abstract":"<p><p>Medical image segmentation is a critical aspect of medical image analysis, particularly in the realm of medical image processing. While the UNet architecture is widely acknowledged for its effectiveness in medical image segmentation, it falls short in fully harnessing inherent advantages and utilising contextual data efficiently. In response, this research introduces an architecture named Deep Atrous Attention UNet (DAA-UNet), incorporating the attention module and Atrous Spatial Pyramid Pooling (ASPP) module in UNet. The primary objective is to enhance both efficiency and accuracy in the segmentation of medical images, with a specific focus on chest X-ray (CXR) images. DAA-UNet combines the integral features of UNet, ASPP, and attention mechanisms. The addition of an attention block improves the segmentation process by prioritising features from the encoding layer to the decoding layers. Our evaluation employs a tuberculosis dataset to assess the performance of the proposed model. The validation results demonstrate an average accuracy of 97.15%, an average Intersection over Union (IoU) value of 92.37%, and an average Dice Coefficient (DC) value of 93.25%. Notably, both qualitative and quantitative assessments for lung segmentation produce better outcomes than UNet and other relevant selected architectures.</p>","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"2553-2565"},"PeriodicalIF":2.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143606424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An efficient network with state space model under evidential training for fetal echocardiography standard view recognition.","authors":"Changzhao Chen, Yiman Liu, Tongtong Liang, Shibin Lin, Xiaoxiang Han, Xiaohong Liu, Jing Yang, Yuqi Zhang, Xueping Yan","doi":"10.1007/s11517-025-03347-5","DOIUrl":"10.1007/s11517-025-03347-5","url":null,"abstract":"<p><p>Fetal congenital heart disease (FCHD) represents a serious and prevalent congenital malformation. However, there exist notable regional disparities in the detection rates of fetal heart abnormalities. To enhance the diagnostic capabilities of ultrasound physicians in primary hospitals regarding fetal heart structures, the adoption of artificial intelligence technology to assist in acquiring high-quality, standard fetal echocardiographic images is of paramount importance. Currently, primary hospitals face challenges in recognizing standard views in fetal echocardiography, particularly under resource-constrained conditions. Efficient and accurate identification of fetal heart structures has become an urgent issue to address. Despite existing research efforts dedicated to the recognition of standard views in fetal echocardiography, current methods still suffer from limitations in computational complexity, feature extraction capabilities, and long-distance feature capturing, hindering their widespread application in ultrasound diagnosis at primary hospitals. Specifically, the literature lacks an efficient and robust model that can effectively balance high accuracy in standard view recognition with low computational complexity and fast inference times. The need for a model that can accurately capture long-distance features while maintaining efficiency is particularly acute in the context of primary hospitals, where resources are limited and the demand for accurate fetal heart assessments is high. To address these issues, the present study proposes an efficient network based on a state-space model trained with evidence for standard view recognition in fetal echocardiography. This method integrates a visual state space (VSS) model, which boasts powerful feature extraction capabilities and effective long-distance feature capturing, while significantly reducing computational complexity and facilitating efficient model inference. In the collected dataset, the proposed model achieved an accuracy of 99.32% and an F1-score of 99.29% in identifying eight standard views of fetal echocardiography. Furthermore, the model exhibited the lowest floating point operations per second (FLOPs), parameters, and inference time, while achieving the highest frames per second (FPS). This achievement not only provides a solid technical foundation for intelligent diagnosis of FCHD but also serves as an auxiliary tool for junior or novice sonographers at primary hospitals in acquiring basic views of fetal heart structures.</p>","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"2693-2706"},"PeriodicalIF":2.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143765595","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Developing a gene expression classifier for breast cancer diagnosis.","authors":"Zahra Hosseinpour, Mostafa Rezaei-Tavirani, Mohammad-Esmaeil Akbari, Masoumeh Farahani","doi":"10.1007/s11517-025-03329-7","DOIUrl":"10.1007/s11517-025-03329-7","url":null,"abstract":"<p><p>Breast cancer (BC) is the most common type of cancer in women worldwide. Solid tumors are complex structures composed of many cell types and extracellular matrix components. Understanding solid tumors is crucial for developing effective treatments. This study aimed to develop a gene expression classifier to predict BC with high accuracy. The study first identified the most important genes for cancer through differential expression analysis (DEA) between breast cancer and adjacent normal breast samples. The R package STRINGdb was then used to create a protein-protein interaction network (PPI) to examine upregulated genes and find clusters. Enrichment analyses were performed to identify overrepresented biological functions and pathways. A logistic regression prediction model was developed using a breast cancer dataset from TCGA and evaluated using discrimination and calibration measures. BUB1 expression in breast cancer was also investigated using quantitative analysis. Two significant clusters were identified, with cell cycle checkpoints and M phase key pathways in one cluster and extracellular matrix organization in the other. A prediction model using the hub gene set (COMP, FN1, SDC1, BUB1, TTK, and NUSAP1) showed high sensitivity (97.2%) and specificity (96.1%), and an AUC of 0.994. Three hub genes (COMP, FN1, and SDC1) were identified through the PPI network, strongly linked to extracellular matrix organization (BUB1, TTK, and NUSAP1) as hub genes involved in M phase and cell cycle checkpoints. Overall, the study identified hub pathways and genes that accurately distinguish between cancer and normal samples, presenting promising new possibilities for early cancer detection and improved BC therapy.</p>","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"2567-2583"},"PeriodicalIF":2.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143626548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Correction to: Machine learning models based on FEM simulation of hoop mode vibrations to enable ultrasonic cuffless measurement of blood pressure.","authors":"Ravinder Kumar, Vishal Kumar, Collin Rich, David Lemmerhirt, Balendra, J Brian Fowlkes, Ashish Kumar Sahani","doi":"10.1007/s11517-025-03351-9","DOIUrl":"10.1007/s11517-025-03351-9","url":null,"abstract":"","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"2829-2831"},"PeriodicalIF":2.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143712005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automated pulmonary nodule classification from low-dose CT images using ERBNet: an ensemble learning approach.","authors":"Yashar Ahmadyar, Alireza Kamali-Asl, Rezvan Samimi, Hossein Arabi, Habib Zaidi","doi":"10.1007/s11517-025-03358-2","DOIUrl":"10.1007/s11517-025-03358-2","url":null,"abstract":"<p><p>The aim of this study was to develop a deep learning method for analyzing CT images with varying doses and qualities, aiming to categorize lung lesions into nodules and non-nodules. This study utilized the lung nodule analysis 2016 challenge dataset. Different low-dose CT (LDCT) images, including 10%, 20%, 40%, and 60% levels, were generated from the full-dose CT (FDCT) images. Five different 3D convolutional networks were developed to classify lung nodules from LDCT and reference FDCT images. The models were evaluated using 400 nodule and 400 non-nodule samples. An ensemble model was also developed to achieve a generalizable model across different dose levels. The model achieved an accuracy of 97.0% for nodule classification on FDCT images. However, the model exhibited relatively poor performance (60% accuracy) on LDCT images, indicating that dedicated models should be developed for each low-dose level. Dedicated models for handling LDCT led to dramatic increases in the accuracy of nodule classification. The dedicated low-dose models achieved a nodule classification accuracy of 90.0%, 91.1%, 92.7%, and 93.8% for 10%, 20%, 40%, and 60% of FDCT images, respectively. The accuracy of the deep learning models decreased gradually by almost 7% as LDCT images proceeded from 100 to 10%. However, the ensemble model led to an accuracy of 95.0% when tested on a combination of various dose levels. We presented an ensemble 3D CNN classifier for lesion classification, utilizing both LDCT and FDCT images. This model is able to analyze a combination of CT images with different dose levels and image qualities.</p>","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"2767-2779"},"PeriodicalIF":2.6,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12402046/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144028777","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"IF-MMCL: an individual focused network with multi-view and multi-modal contrastive learning for cross-subject emotion recognition.","authors":"Qiaoli Zhou, Jiawen Song, Yi Zhao, Shun Zhang, Qiang Du, Li Ke","doi":"10.1007/s11517-025-03430-x","DOIUrl":"https://doi.org/10.1007/s11517-025-03430-x","url":null,"abstract":"<p><p>Electroencephalography (EEG) usage in emotion recognition has garnered significant interest in brain-computer interface (BCI) research. Nevertheless, in order to develop an effective model for emotion identification, features need to be extracted from EEG data in terms of multi-view. In order to tackle the problems of multi-feature interaction and domain adaptation, we suggest an innovative network, IF-MMCL, which leverages multi-modal data in multi-view representation and integrates an individual focused network. In our approach, we build an individual focused network with multi-view that utilizes individual focused contrastive learning to improve model generalization. The network employs different structures for multi-view feature extraction and uses multi-feature relationship computation to identify the relationships between features from various views and modalities. Our model is validated using four public emotion datasets, each containing various emotion classification tasks. In leave-one-subject-out experiments, IF-MMCL performs better than the previous methods in model generalization with limited data.</p>","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2025-08-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144976538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep learning-based dual-energy subtraction synthesis from single-energy kV x-ray fluoroscopy for markerless tumor tracking.","authors":"Jiaoyang Wang, Kei Ichiji, Yuwen Zeng, Xiaoyong Zhang, Yoshihiro Takai, Noriyasu Homma","doi":"10.1007/s11517-025-03432-9","DOIUrl":"https://doi.org/10.1007/s11517-025-03432-9","url":null,"abstract":"<p><p>Markerless tumor tracking in x-ray fluoroscopic images is an important technique for achieving precise dose delivery for moving lung tumors during radiation therapy. However, accurate tumor tracking is challenging due to the poor visibility of the target tumor overlapped by other organs such as rib bones. Dual-energy (DE) x-ray fluoroscopy can enhance tracking accuracy with improved tumor visibility by suppressing bones. However, DE x-ray imaging requires special hardware, limiting its clinical use. This study presents a deep learning-based DE subtraction (DES) synthesis method to avoid hardware limitations and enhance tracking accuracy. The proposed method employs a residual U-Net model trained on a simulated DES dataset from a digital phantom to synthesize DES from single-energy (SE) fluoroscopy. Experimental results using a digital phantom showed quantitative evaluation results of synthesis quality. Also, experimental results using clinical SE fluoroscopic images of ten lung cancer patients showed improved tumor tracking accuracy using synthesized DES images, reducing errors from 1.80 to 1.68 mm on average. The tracking success rate within a 25% movement range increased from 50.2% (SE) to 54.9% (DES). These findings indicate the feasibility of deep learning-based DES synthesis for markerless tumor tracking, offering a potential alternative to hardware-dependent DE imaging.</p>","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144976427","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"E-TBI: explainable outcome prediction after traumatic brain injury using machine learning.","authors":"Thu Ha Ngo, Minh Hieu Tran, Hoang Bach Nguyen, Van Nam Hoang, Thi Lan Le, Hai Vu, Trung Kien Tran, Huu Khanh Nguyen, Van Mao Can, Thanh Bac Nguyen, Thanh-Hai Tran","doi":"10.1007/s11517-025-03431-w","DOIUrl":"https://doi.org/10.1007/s11517-025-03431-w","url":null,"abstract":"<p><p>Traumatic brain injury (TBI) is one of the most prevalent health conditions, with severity assessment serving as an initial step for management, prognosis, and targeted therapy. Existing studies on automated outcome prediction using machine learning (ML) often overlook the importance of TBI features in decision-making and the challenges posed by limited and imbalanced training data. Furthermore, many attempts have focused on quantitatively evaluating ML algorithms without explaining the decisions, making the outcomes difficult to interpret and apply for less-experienced doctors. This study presents a novel supportive tool, named E-TBI (explainable outcome prediction after TBI), designed with a user-friendly web-based interface to assist doctors in outcome prediction after TBI using machine learning. The tool is developed with the capability to visualize rules applied in the decision-making process. At the tool's core is a feature selection and classification module that receives multimodal data from TBI patients (demographic data, clinical data, laboratory test results, and CT findings). It then infers one of four TBI severity levels. This research investigates various machine learning models and feature selection techniques, ultimately identifying the optimal combination of gradient boosting machine and random forest for the task, which we refer to as GBMRF. This method enabled us to identify a small set of essential features, reducing patient testing costs by 35%, while achieving the highest accuracy rates of 88.82% and 89.78% on two datasets (a public TBI dataset and our self-collected dataset, TBI_MH103). Classification modules are available at https://github.com/auverngo110/Traumatic_Brain_Injury_103 .</p>","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":""},"PeriodicalIF":2.6,"publicationDate":"2025-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144976487","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}