Medical & Biological Engineering & Computing最新文献_第2页

Deep ensemble framework with Bayesian optimization for multi-lesion recognition in capsule endoscopy images. 基于贝叶斯优化的胶囊内镜图像多病灶识别的深度集成框架。

IF 2.6 4区医学

Medical & Biological Engineering & Computing Pub Date : 2025-10-01 Epub Date: 2025-05-24 DOI: 10.1007/s11517-025-03380-4

Xudong Guo, Liying Pang, Peiyu Chen, Qinfen Jiang, Yukai Zhong

{"title":"Deep ensemble framework with Bayesian optimization for multi-lesion recognition in capsule endoscopy images.","authors":"Xudong Guo, Liying Pang, Peiyu Chen, Qinfen Jiang, Yukai Zhong","doi":"10.1007/s11517-025-03380-4","DOIUrl":"10.1007/s11517-025-03380-4","url":null,"abstract":"In order to address the challenges posed by the large number of images acquired during wireless capsule endoscopy examinations and fatigue-induced leakage and misdiagnosis, a deep ensemble framework is proposed, which consists of CA-EfficientNet-B0, ECA-RegNetY, and Swin transformer as base learners. The ensemble model aims to automatically recognize four lesions in capsule endoscopy images, including angioectasia, bleeding, erosions, and polyps. All the three base learners employed transfer learning, with the inclusion of attention modules in EfficientNet-B0 and RegNetY for optimization. The recognition outcomes from the three base learners were subsequently combined and weighted to facilitate automatic recognition of multi-lesion images and normal images of the gastrointestinal (GI) tract. The weights were determined through the Bayesian optimization. The experiment collected a total of 8358 images of 281 cases at Shanghai East Hospital from 2017 to 2021. These images were organized and labeled by clinicians to verify the performance of the algorithm. The experimental results showed that the model achieved an accuracy of 84.31%, m-Precision of 88.60%, m-Recall of 79.36%, and m-F1-score of 81.08%. Compared to mainstream deep learning models, the ensemble model effectively improves the classification performance of GI diseases and can assist clinicians in making initial diagnoses of GI diseases.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"3037-3052"},"PeriodicalIF":2.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144136553","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}

引用次数: 0

Slim UNETR++: A lightweight 3D medical image segmentation network for medical image analysis. Slim UNETR++：用于医学图像分析的轻量级3D医学图像分割网络。

IF 2.6 4区医学

Medical & Biological Engineering & Computing Pub Date : 2025-10-01 Epub Date: 2025-06-02 DOI: 10.1007/s11517-025-03390-2

Jiawei Jin, Sen Yang, Jigang Tong, Kai Zhang, Zenghui Wang

{"title":"Slim UNETR++: A lightweight 3D medical image segmentation network for medical image analysis.","authors":"Jiawei Jin, Sen Yang, Jigang Tong, Kai Zhang, Zenghui Wang","doi":"10.1007/s11517-025-03390-2","DOIUrl":"10.1007/s11517-025-03390-2","url":null,"abstract":"Convolutional neural network (CNN) models, such as U-Net, V-Net, and DeepLab, have achieved remarkable results across various medical imaging modalities, and ultrasound. Additionally, hybrid Transformer-based segmentation methods have shown great potential in medical image analysis. Despite the breakthroughs in feature extraction through self-attention mechanisms, these methods are computationally intensive, especially for three-dimensional medical imaging, posing significant challenges to graphics processing unit (GPU) hardware. Consequently, the demand for lightweight models is increasing. To address this issue, we designed a high-accuracy yet lightweight model that combines the strengths of CNNs and Transformers. We introduce Slim UNEt TRansformers++ (Slim UNETR++), which builds upon Slim UNETR by incorporating Medical ConvNeXt (MedNeXt), Spatial-Channel Attention (SCA), and Efficient Paired-Attention (EPA) modules. This integration leverages the advantages of both CNN and Transformer architectures to enhance model accuracy. The core component of Slim UNETR++ is the Slim UNETR++ block, which facilitates efficient information exchange through a sparse self-attention mechanism and low-cost representation aggregation. We also introduced throughput as a performance metric to quantify data processing speed. Experimental results demonstrate that Slim UNETR++ outperforms other models in terms of accuracy and model size. On the BraTS2021 dataset, Slim UNETR++ achieved a Dice accuracy of 93.12% and a 95% Hausdorff distance (HD95) of 4.23mm, significantly surpassing mainstream relevant methods such as Swin UNETR.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"3123-3137"},"PeriodicalIF":2.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144200646","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}

引用次数: 0

ToPoMesh: accurate 3D surface reconstruction from CT volumetric data via topology modification. ToPoMesh：通过拓扑修改从CT体积数据中精确重建三维表面。

IF 2.6 4区医学

Medical & Biological Engineering & Computing Pub Date : 2025-10-01 Epub Date: 2025-05-27 DOI: 10.1007/s11517-025-03381-3

Junjia Chen, Qing Zhu, Bowen Xie, Tianxing Li

{"title":"ToPoMesh: accurate 3D surface reconstruction from CT volumetric data via topology modification.","authors":"Junjia Chen, Qing Zhu, Bowen Xie, Tianxing Li","doi":"10.1007/s11517-025-03381-3","DOIUrl":"10.1007/s11517-025-03381-3","url":null,"abstract":"Traditional computed tomography (CT) methods for 3D reconstruction face resolution limitations and require time-consuming post-processing workflows. While deep learning techniques improve the accuracy of segmentation, traditional voxel-based segmentation and surface reconstruction pipelines tend to introduce artifacts such as disconnected regions, topological inconsistencies, and stepped distortions. To overcome these challenges, we propose ToPoMesh, an end-to-end 3D mesh reconstruction deep learning framework for direct reconstruction of high-fidelity surface meshes from CT volume data. To address the existing problems, our approach introduces three core innovations: (1) accurate local and global shape modeling by preserving and enhancing local feature information through residual connectivity and self-attention mechanisms in graph convolutional networks; (2) an adaptive variant density (Avd) mesh de-pooling strategy, which dynamically optimizes the vertex distribution; (3) a topology modification module that iteratively prunes the error surfaces and boundary smoothing via variable regularity terms to obtain finer mesh surfaces. Experiments on the LiTS, MSD pancreas tumor, MSD hippocampus, and MSD spleen datasets demonstrate that ToPoMesh outperforms state-of-the-art methods. Quantitative evaluations demonstrate a 57.4% reduction in Chamfer distance (liver) and a 0.47% improvement in F-score compared to end-to-end 3D reconstruction methods, while qualitative results confirm enhanced fidelity for thin structures and complex anatomical topologies versus segmentation frameworks. Importantly, our method eliminates the need for manual post-processing, realizes the ability to reconstruct 3D meshes from images, and can provide precise guidance for surgical planning and diagnosis.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"3083-3098"},"PeriodicalIF":2.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144152639","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}

引用次数: 0

Abnormal phase-amplitude coupling in patients with first-episode schizophrenia during the auditory steady-state response and resting states. 首发精神分裂症患者在听觉稳态反应和静息状态时的相幅耦合异常。

IF 2.6 4区医学

Medical & Biological Engineering & Computing Pub Date : 2025-10-01 Epub Date: 2025-05-29 DOI: 10.1007/s11517-025-03387-x

Jie Zhang, Xiong Jiao, Junjie Wang, Zhenying Qian, Yingchan Wang, Xiaochen Tang, Gai Kong, Junfeng Sun, Jijun Wang, Yingying Tang

{"title":"Abnormal phase-amplitude coupling in patients with first-episode schizophrenia during the auditory steady-state response and resting states.","authors":"Jie Zhang, Xiong Jiao, Junjie Wang, Zhenying Qian, Yingchan Wang, Xiaochen Tang, Gai Kong, Junfeng Sun, Jijun Wang, Yingying Tang","doi":"10.1007/s11517-025-03387-x","DOIUrl":"10.1007/s11517-025-03387-x","url":null,"abstract":"The auditory steady-state response (ASSR) is a robust index for schizophrenia. Abnormal phase-amplitude coupling (PAC) in schizophrenia might be influenced by the confounding factors of illness stages and antipsychotic treatments. To exclude the effects of confounding factors, we examined abnormal PAC in antipsychotic-naïve patients with first-episode schizophrenia (FES) during the ASSR. 67 FES and 84 healthy controls (CON) were recruited and their EEG data were collected during the 20 Hz ASSR, 30 Hz ASSR, 40 Hz ASSR, and resting states. All the possible PAC patterns at Fz were compared between FES and CON, and the electrodes of abnormal PACs were explored. Results showed that FES had significantly higher beta-high gamma PAC at the prefrontal cortex and lower theta-low gamma PAC at the fronto-central cortex than CON during all the three ASSR blocks but not in the Resting block. FES showed lower correlations of PAC values between any two of the ASSR blocks than CON. Beta-high gamma PAC was negatively correlated with the cognitive scores of visual learning and attention, while theta-low gamma PAC was positively correlated with the score of symbol coding. Abnormal PAC of FES in specific brain regions may provide electrophysiological biomarkers for abnormal circuits.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"3099-3111"},"PeriodicalIF":2.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144175402","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}

引用次数: 0

Towards understanding the functional connectivity patterns in visual brain network. 探讨视觉脑网络的功能连接模式。

IF 2.6 4区医学

Medical & Biological Engineering & Computing Pub Date : 2025-10-01 Epub Date: 2025-06-02 DOI: 10.1007/s11517-025-03389-9

Debanjali Bhattacharya, Neelam Sinha

{"title":"Towards understanding the functional connectivity patterns in visual brain network.","authors":"Debanjali Bhattacharya, Neelam Sinha","doi":"10.1007/s11517-025-03389-9","DOIUrl":"10.1007/s11517-025-03389-9","url":null,"abstract":"Recent advances in neuroimaging have enabled studies in functional connectivity (FC) of human brain, alongside investigation of the neuronal basis of cognition. One important FC study is the representation of vision in human brain. The release of publicly available dataset \"BOLD5000\" has made it possible to study the brain dynamics during visual tasks in greater detail. In this paper, a comprehensive analysis of fMRI time series (TS) has been performed to explore different types of visual brain networks (VBN). The novelty of this work lies in (1) constructing VBN with consistently significant direct connectivity using both marginal and partial correlation, which is further analyzed using graph theoretic measures, and (2) classification of VBNs as formed by image complexity-specific TS, using graphical features. In image complexity-specific VBN classification, XGBoost yields average accuracy in the range of 86.5 to 91.5% for positively correlated VBN, which is 2% greater than that using negative correlation. This result not only reflects the distinguishing graphical characteristics of each image complexity-specific VBN, but also highlights the importance of studying both correlated and anti-correlated VBN to understand how differently brain functions while viewing different complexities of real-world images.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"3139-3152"},"PeriodicalIF":2.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144200647","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}

引用次数: 0

Biomechanical evaluation of the effects of thread parameters on dental implant stability: a systematic review. 螺纹参数对种植体稳定性影响的生物力学评价：系统综述。

IF 2.6 4区医学

Medical & Biological Engineering & Computing Pub Date : 2025-10-01 Epub Date: 2025-05-06 DOI: 10.1007/s11517-025-03367-1

Masoud Arabbeiki, Mohammad Reza Niroomand

{"title":"Biomechanical evaluation of the effects of thread parameters on dental implant stability: a systematic review.","authors":"Masoud Arabbeiki, Mohammad Reza Niroomand","doi":"10.1007/s11517-025-03367-1","DOIUrl":"10.1007/s11517-025-03367-1","url":null,"abstract":"The threads of dental implants are critical components that transfer occlusal loads to the surrounding bone. The appropriate size of thread parameters can influence the stability of the implant after implantation. Despite several research studies on the effectiveness of implant thread parameters, there is limited structured information available. This study aims to conduct a systematic review to evaluate the biomechanical effects of thread parameters, namely, thread depth, thread width, thread pitch, and thread angle on implant stability. A comprehensive literature review was conducted in PubMed/MEDLINE, Scopus, ScienceDirect, and Web of Science for research published in English in the last two decades according to the PRISMA protocols. The extracted data were organized in the following order: area, bone layers, bone type, implant design, implant material, failure criteria/unit, loading type, statistical analysis/optimization, experimental validation, convergence analysis, boundary conditions, parts of the Finite Element Model, studied variables, and main findings. The search yielded 580 records, with 39 studies meeting the selection criteria and being chosen for the review. All four thread parameters were found to affect the stress and strain distribution in cancellous and cortical bones. Thread pitch and depth are more important for implant primary stability as they are directly correlated with the functional surface area between the implant and bone. Moreover, thread pitch, depth, and width can increase the insertion torque, which is favorable for implant primary stability, especially in low-quality bones. The thread angle can also direct occlusal forces to the bone more smoothly to prevent bone overloading and destructive shear stresses, which cause bone resorption. This structured review provides valuable insights into the biomechanical effects of thread parameters on implant stability.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"2833-2851"},"PeriodicalIF":2.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144037367","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}

引用次数: 0

Deep learning-based prognostic assessment of polyploid giant cancer cells and mitotic figures in liver cancer. 基于深度学习的肝癌多倍体巨细胞和有丝分裂图的预后评估。

IF 2.6 4区医学

Medical & Biological Engineering & Computing Pub Date : 2025-10-01 Epub Date: 2025-05-07 DOI: 10.1007/s11517-025-03360-8

Jingying Yang, Cuimin Chen, Qiming He, Jiayi Li, Houqiang Li, Jing Peng, Junru Cheng, Meihui Li, Xiaozhuan Zhou, Yonghong He, Tian Guan, Xi Li, Danling Jiang

{"title":"Deep learning-based prognostic assessment of polyploid giant cancer cells and mitotic figures in liver cancer.","authors":"Jingying Yang, Cuimin Chen, Qiming He, Jiayi Li, Houqiang Li, Jing Peng, Junru Cheng, Meihui Li, Xiaozhuan Zhou, Yonghong He, Tian Guan, Xi Li, Danling Jiang","doi":"10.1007/s11517-025-03360-8","DOIUrl":"10.1007/s11517-025-03360-8","url":null,"abstract":"Primary liver cancer is among the most lethal malignancies, with cell-level structural features such as polyploid giant cancer cells and mitotic figures strongly associated with poor patient prognosis. However, the quantification of these features is hindered by a shortage of pathologists, high workloads, and subjective discrepancies. To address these challenges, we leverage deep learning algorithms to enable the rapid detection of cell-level features, combining this capability with survival analysis to establish a novel, practical prognostic risk assessment system for liver cancer diagnosis and treatment. In collaboration with Peking University Shenzhen Hospital, we collected 172 liver cancer cases, comprising 340 pathology images, to construct the HCCP&M dataset. Our full-process calculation system integrates cell-level feature detection and survival analysis. During the detection phase, the CellFDet framework achieves F1 scores of 0.814, 0.819, and 0.935 for detecting polyploid giant cancer cells, mitotic figures, and general cells, respectively. In the survival analysis phase, patients were stratified into high-risk and low-risk groups based on the polyploid giant cancer cell index (P < 0.0001) and the mitotic index (P = 0.0025), with both indices demonstrating significant survival differences. Correlation analysis further confirmed these features as independent prognostic indicators for liver cancer. Our proposed system not only enables accurate detection of cell-level structural features but also provides reliable survival predictions, offering a valuable tool for improving the prognosis and treatment planning for liver cancer patients.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"2903-2921"},"PeriodicalIF":2.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144047307","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}

引用次数: 0

A deep learning model with interpretable squeeze-and-excitation for automated rehabilitation exercise assessment. 用于自动康复训练评估的具有可解释挤压和激励的深度学习模型。

IF 2.6 4区医学

Medical & Biological Engineering & Computing Pub Date : 2025-10-01 Epub Date: 2025-05-06 DOI: 10.1007/s11517-025-03372-4

Md Johir Raihan, Md Atiqur Rahman Ahad, Abdullah-Al Nahid

{"title":"A deep learning model with interpretable squeeze-and-excitation for automated rehabilitation exercise assessment.","authors":"Md Johir Raihan, Md Atiqur Rahman Ahad, Abdullah-Al Nahid","doi":"10.1007/s11517-025-03372-4","DOIUrl":"10.1007/s11517-025-03372-4","url":null,"abstract":"Rehabilitation exercises are critical for recovering from motor dysfunction caused by neurological conditions like stroke, back pain, Parkinson's disease, and spinal cord injuries. Traditionally, these exercises require constant monitoring by therapists, which is time-consuming and costly, often leading to therapist shortages. This paper introduces a deep learning model, convolutional neural network - squeeze excitation (CNN-SE), to automate rehabilitation exercise assessment. By optimizing its parameters with the grey wolf optimization algorithm, the model was fine-tuned for optimal performance. The model's effectiveness was tested on both healthy and unhealthy participants with motor dysfunction, providing a comprehensive evaluation of its capabilities. To interpret the model's decisions and understand its inner workings, we employed Shapley additive explanations (SHAP) to analyze feature importance at each time step. Our CNN-SE model achieved a state-of-the-art mean absolute deviation of 0.127 on the KIMORE dataset and a comparable MAD of 0.014 on the UI-PRMD dataset across various exercises, demonstrating its potential to provide a cost-effective, efficient alternative to traditional therapist-led evaluations.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"2871-2887"},"PeriodicalIF":2.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144037342","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}

引用次数: 0

Using baseline MRI radiomic features to predict the efficacy of repetitive transcranial magnetic stimulation in Alzheimer's patients. 使用基线MRI放射学特征预测阿尔茨海默病患者重复经颅磁刺激的疗效。

IF 2.6 4区医学

Medical & Biological Engineering & Computing Pub Date : 2025-10-01 Epub Date: 2025-05-08 DOI: 10.1007/s11517-025-03366-2

Chandan Saha, Chase R Figley, Brian Lithgow, Xikui Wang, Paul B Fitzgerald, Lisa Koski, Behzad Mansouri, Zahra Moussavi

{"title":"Using baseline MRI radiomic features to predict the efficacy of repetitive transcranial magnetic stimulation in Alzheimer's patients.","authors":"Chandan Saha, Chase R Figley, Brian Lithgow, Xikui Wang, Paul B Fitzgerald, Lisa Koski, Behzad Mansouri, Zahra Moussavi","doi":"10.1007/s11517-025-03366-2","DOIUrl":"10.1007/s11517-025-03366-2","url":null,"abstract":"The efficacy of repetitive transcranial magnetic stimulation (rTMS) as a treatment for Alzheimer's disease (AD) is uncertain at baseline. Herein, we aimed to investigate whether radiomic features from the pre-treatment MRI data could predict rTMS efficacy for AD treatment. Out of 110 participants with AD in the active (n = 75) and sham (n = 35) rTMS treatment groups having T1-weighted brain MRI data, we had two groups of responders (active = 55 and sham = 24) and non-responders (active = 20 and sham = 11). We extracted histogram-based radiomic features from MRI data using 3D Slicer software; the most important features were selected utilizing a combination of a two-sample t-test, correlation test, least absolute shrinkage, and selection operator. The support vector machine classified rTMS responders and non-responders with a cross-validated mean accuracy/AUC of 81.9%/90.0% in the active group and 87.4%/95.8% in the sham group. Further, the radiomic features of the active group significantly correlated with participants' AD assessment scale-cognitive subscale (ADAS-Cog) change after treatment (false discovery rate corrected p < 0.05). Given that baseline radiomic features were able to accurately predict AD patients' responses to rTMS treatment, these radiomic features warrant further investigation for personalizing AD therapeutic strategies.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"2943-2953"},"PeriodicalIF":2.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144046643","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}

引用次数: 0

Few-shot small vessel segmentation using a detail-preserving network enhanced by discriminator. 基于鉴别器增强的保细节网络的小样本船舶分割。

IF 2.6 4区医学

Medical & Biological Engineering & Computing Pub Date : 2025-10-01 Epub Date: 2025-05-13 DOI: 10.1007/s11517-025-03368-0

Yan Huang, Jinzhu Yang, Qi Sun, Yuliang Yuan, Yang Hou, Jin Shang

{"title":"Few-shot small vessel segmentation using a detail-preserving network enhanced by discriminator.","authors":"Yan Huang, Jinzhu Yang, Qi Sun, Yuliang Yuan, Yang Hou, Jin Shang","doi":"10.1007/s11517-025-03368-0","DOIUrl":"10.1007/s11517-025-03368-0","url":null,"abstract":"Accurate segmentation of small vessels, such as coronary and pulmonary arteries, is crucial for early detection and treatment of vascular diseases. However, challenges persist due to the vessel's small size, complex structures, morphological variations, and limited annotated data. To address these challenges, we propose a detail-preserving network enhanced by a discriminator to improve the few-shot small vessel segmentation performance. The detail-preserving network constructs a complex module with multi-residual hybrid dilated convolution, which can enhance the network's receptive field while preserving the image's full detail features, enabling it to better capture the small vessel's structural features. Simultaneously, discriminator enhancement is incorporated into the training process through adversarial learning, effectively utilizing large amounts of unlabeled data to boost the generalization and robustness of the segmentation model. We validate the proposed method on in-house and public coronary artery datasets and public pulmonary artery datasets. Experimental results demonstrate that the proposed method significantly improves segmentation accuracy, particularly for small vessels. Compared with other state-of-the-art methods, the proposed method achieves higher accuracy, a lower false positive rate, and superior generalization capability, effectively assisting the clinical diagnosis of vessel diseases.","PeriodicalId":49840,"journal":{"name":"Medical & Biological Engineering & Computing","volume":" ","pages":"2983-3001"},"PeriodicalIF":2.6,"publicationDate":"2025-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144039679","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}

引用次数: 0