Visual Computing for Industry Biomedicine and Art最新文献

{"title":"Swin-WaveNet: frequency-guided boundary restoration for robust skin lesion segmentation.","authors":"Zhiping Dan, Run Zhang, Tinglong Tang, Yirong Wu, Xiaosheng Yu, Shuifa Sun, Ben Wang","doi":"10.1186/s42492-026-00235-z","DOIUrl":"https://doi.org/10.1186/s42492-026-00235-z","url":null,"abstract":"<p><p>Accurate skin lesion segmentation remains difficult when dermoscopic boundaries are fragmented by hair occlusion, uneven illumination, or weak local contrast. To address this problem, the authors propose Swin-WaveNet, a frequency-guided encoder-decoder that combines a Swin Transformer backbone with wavelet decomposition and selective state-space modeling. Rather than passing skip features directly to the decoder, the proposed method separates low-frequency semantic information from high-frequency details, selectively refines boundary-related responses, and suppresses artifact-induced activation prior to feature reconstruction. The main results are reported as the mean and standard deviation of the sample over three runs. Swin-WaveNet achieved a Dice score of 89.69% ± 0.51% and a 95th-percentile Hausdorff distance (HD95) of [Formula: see text] pixels on the International Skin Imaging Collaboration (ISIC) 2018 dataset. Without fine-tuning on ISIC 2017, it obtained a Dice score of 91.69% ± 1.36% and an HD95 of [Formula: see text] pixels. On Kvasir-SEG, the model achieved a Dice score of 91.63% ± 0.57% and an HD95 of [Formula: see text] pixels. In a single-run component ablation, the complete model improved the Dice score by 0.96 percentage points and reduced HD95 by 1.16 pixels relative to the internal baseline. These results indicate that frequency-selective feature processing can help preserve weak or interrupted lesion boundaries.</p>","PeriodicalId":29931,"journal":{"name":"Visual Computing for Industry Biomedicine and Art","volume":"9 1","pages":""},"PeriodicalIF":6.7,"publicationDate":"2026-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149224875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Adapting Segment Anything Model 3 for concept-driven lesion segmentation in medical images: an experimental study.","authors":"Guoping Xu, Jayaram K Udupa, Yubing Tong, Xin Long, Ying Zhang, Jie Deng, Weiguo Lu, You Zhang","doi":"10.1186/s42492-026-00234-0","DOIUrl":"10.1186/s42492-026-00234-0","url":null,"abstract":"<p><p>Accurate segmentation of lesions is fundamental for medical image analysis. However, most existing approaches are designed for specific anatomical sites and imaging modalities, limiting their applicability in heterogeneous clinical environments. Recent vision-language foundation models have enabled concept-driven segmentation of natural images, offering a promising path toward more flexible and generalizable medical image segmentation. However, to the best of the authors' knowledge, concept-prompt-based lesion segmentation in medical images, particularly using the latest Segment Anything Model 3 (SAM3), has not been thoroughly examined. In this paper, the authors present a systematic investigation of the SAM3 framework for lesion segmentation. An extensive evaluation of SAM3 was first conducted using geometric bounding boxes and concept-based text and image exemplars as prompts for lesion segmentation across multiple cancer types and imaging modalities, including magnetic resonance imaging, computed tomography, ultrasound, dermoscopy, and endoscopic imaging, with particular emphasis on volumetric medical imaging datasets. To improve robustness and segmentation accuracy, additional knowledge into the input representation was further integrated, including predictions from adjacent slices, multiparametric imaging information, and prior annotations. In addition, the study compared different SAM3 fine-tuning strategies on the BraTS2023-MET dataset, including partial module fine-tuning, adapter-based optimization, and full-model fine-tuning, under different training objectives. Extensive experiments conducted on 13 datasets covering 11 lesion types demonstrate that SAM3 achieves strong cross-modality generalization and accurate instance-specific lesion delineation. These results highlight the potential of concept-driven foundation models for scalable and practical medical-image segmentation in real-world clinical settings. The source code and dataset splits are publicly available at https://github.com/apple1986/lesion-sam3 .</p>","PeriodicalId":29931,"journal":{"name":"Visual Computing for Industry Biomedicine and Art","volume":"9 1","pages":""},"PeriodicalIF":6.7,"publicationDate":"2026-10-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13658689/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149168322","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"IP-ConTex: detail-consistent texture generation with image prompt.","authors":"Lei Wang, Jieqing Feng","doi":"10.1186/s42492-026-00232-2","DOIUrl":"10.1186/s42492-026-00232-2","url":null,"abstract":"<p><p>Textures are critical for enhancing the visual fidelity and diversity of three-dimensional (3D) models. Recently, generative models have significantly advanced texture generation. However, fine-grained control of the generation process remains challenging. Hence, we propose IP-ConTex, which is a novel image-guided texture-generation method that introduces appearance control into the diffusion process to ensure detail-consistent results. First, synchronized multiview diffusion is employed to maintain structural and layout consistency across multiple views. Subsequently, a new appearance-control module is designed for the pretrained diffusion model. By leveraging cross-attention control, self-attention control, diffusion feature synchronization, and color adjustment, appearance information from the reference image is effectively extracted and injected into the texture-generation process. Experimental results demonstrate that IP-ConTex successfully transfers appearance details to 3D geometries without fine-tuning or optimization, thus achieving high-quality and detail-consistent texture generation.</p>","PeriodicalId":29931,"journal":{"name":"Visual Computing for Industry Biomedicine and Art","volume":"9 1","pages":""},"PeriodicalIF":6.7,"publicationDate":"2026-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13624197/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149082037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"ProtoSurv: prototype-guided adaptation of computed tomography foundation model for lung-cancer prognosis prediction.","authors":"Chengcai Liu, Shitian Li, Haolin Sang, Xingyu Huang, Chenghao Wang, Yifei Shu, Yi Wu, Jie Tian, Huimao Zhang, Lei Zhang, Shuo Wang","doi":"10.1186/s42492-026-00233-1","DOIUrl":"10.1186/s42492-026-00233-1","url":null,"abstract":"<p><p>Prognosis prediction is important for precision treatment in lung cancer. Chest computed tomography (CT) and deep learning are feasible approaches for learning imaging-based prognostic representations. However, prognostic labels are difficult to obtain because survival endpoints require long-term follow-up; thus, labeled data for supervised training is limited, increasing the risk of overfitting. Vision-language pretraining offers an approach to mitigate this problem by leveraging large-scale unlabeled CT data; however, most existing methods are not specifically designed to learn prognosis-related features. We propose ProtoSurv, a prototype-guided learning framework for adapting large-scale pretrained CT representations for lung-cancer prognosis prediction under limited supervision. ProtoSurv first pretrains a CT-report vision-language model using 409,261 chest CT sequences from 104,783 patients. It then uses limited labeled prognosis data to construct class prototypes in the pretrained feature space. These prototypes guide pseudolabel assignment, confidence-based filtering, and feature calibration, allowing the selection and refinement of task-relevant unlabeled samples before downstream prognosis modeling. We evaluated ProtoSurv based on two lung-cancer prognosis tasks: progression-free survival prediction in 507 patients receiving targeted therapy and overall survival prediction in 420 patients receiving (chemo-)radiotherapy. ProtoSurv achieved area under the curve/concordance index values of 0.765/0.684 and 0.822/0.727 for the first and second datasets, respectively, outperforming the conventional clinical models and representative deep learning baselines. These results suggest that the prototype-guided adaptation can improve the use of large-scale unlabeled CT data for prognosis modeling when labeled survival data are limited.</p>","PeriodicalId":29931,"journal":{"name":"Visual Computing for Industry Biomedicine and Art","volume":"9 1","pages":""},"PeriodicalIF":6.7,"publicationDate":"2026-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13598028/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149026243","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Lightweight Transformer-based knowledge distillation framework for high-dimensional spatiotemporal radiomics in breast cancer risk prediction.","authors":"Haofan Huang, Han Zhou, Kaibin Huang, Jie Yang, Peixi Ying, Puxiang Lai, Yan Lin, Yi Gao","doi":"10.1186/s42492-026-00231-3","DOIUrl":"10.1186/s42492-026-00231-3","url":null,"abstract":"<p><p>Breast cancer exhibits significant spatiotemporal heterogeneity. Traditional radiomics approaches usually rely on low-temporal-resolution imaging and discrete image phases, failing to capture the rapid and continuous kinetic evolution within the tumor microenvironment. Although ultrafast dynamic contrast-enhanced magnetic resonance imaging captures precise contrast agent permeation, current methodologies lack systematic, dedicated computational frameworks to extract these high-dimensional dynamic features. To bridge this gap, this study developed and validated a robust two-stage spatiotemporal radiomics framework for high-dimensional feature selection and predictive modeling. First, a novel gradient-dynamics-based feature selection algorithm was designed to robustly identify highly discriminative kinetic trajectory patterns and overcome the dimensionality curse of time-series data. Second, a lightweight Transformer-based predictive network incorporating a self-attention knowledge distillation mechanism was deployed to capture deep representational knowledge and enhance the differentiation between benign and malignant lesions. Experimental results demonstrated that the proposed framework outperformed traditional baseline models using delta features or pharmacokinetic parameters, achieving an area under the curve of 0.959 ± 0.022 and an accuracy of 92%, an 8% improvement over conventional temporal radiomics models (P < 0.05). Furthermore, through the visualization of attention heat maps, the model provides highly interpretable evidence of the critical enhancement phases and spatiotemporal evolutionary patterns that drive model decisions. This framework introduces a viable, visually interpretable, and quantitative tool for characterizing tumor heterogeneity, demonstrating its potential to assist in personalized clinical decision-making for breast cancer.</p>","PeriodicalId":29931,"journal":{"name":"Visual Computing for Industry Biomedicine and Art","volume":"9 1","pages":""},"PeriodicalIF":6.7,"publicationDate":"2026-09-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13542040/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148888205","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hierarchical two-stage ensemble of dilated U-net models for brain tumor segmentation.","authors":"Vladyslav Koniukhov","doi":"10.1186/s42492-026-00230-4","DOIUrl":"10.1186/s42492-026-00230-4","url":null,"abstract":"<p><p>Ensemble methods for image segmentation improve performance by combining predictions from multiple models, yielding more accurate and reliable results. This study presents a two-stage hierarchical framework to enhance the accuracy and stability of brain tumor delineation in magnetic resonance imaging data. The proposed approach integrates ensemble strategies at different stages of the processing pipeline. The architecture operates in two stages: first, sub-ensembles resolve internal inconsistencies through simple averaging; second, their outputs are fused into a final prediction using union-based aggregation. The method was evaluated on the Figshare brain tumor dataset and demonstrated progressive performance improvements from individual models to the final hierarchical ensemble. The proposed approach achieved a Dice coefficient of 94.50% and an intersection over union of 89.91%, outperforming existing state-of-the-art methods. The statistical significance of these improvements was confirmed using one-way analysis of variance across three experimental groups, followed by post hoc pairwise testing. The proposed architecture preserves high fidelity in delineating diffuse tumor boundaries and complex morphological structures. By decomposing the ensemble process into two stages, the framework effectively reduces stochastic errors typical of single-model predictions, resulting in a more robust and stable segmentation system that performs reliably even in cases with low contrast and complex tissue interfaces.</p>","PeriodicalId":29931,"journal":{"name":"Visual Computing for Industry Biomedicine and Art","volume":"9 1","pages":""},"PeriodicalIF":6.7,"publicationDate":"2026-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13518662/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148833094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Text-to-hierarchical three-dimensional scene generation: a new approach for layered three-dimensional modeling from natural language.","authors":"Zuan Gu, Tianhan Gao, Lanxu Zhao, Huimin Liu","doi":"10.1186/s42492-026-00226-0","DOIUrl":"10.1186/s42492-026-00226-0","url":null,"abstract":"<p><p>Rapid advancements in generative models have enabled substantial progress in text-to-3D scene synthesis. However, existing approaches often lack hierarchical structure and geometric consistency, limiting their use in complex, editable scene creation. To address this issue, an end-to-end hierarchical framework for text-to-3D scene generation is introduced. The main contribution of this study lies not in advancing a single generative model but in the design of a framework that synergistically integrates state-of-the-art components for video synthesis and mesh reconstruction. By decoupling scene semantics from dynamic camera trajectory control, the proposed system efficiently produces structured object-level editable three-dimensional scenes from natural language. Comprehensive experiments showed that the proposed integrated approach achieved superior scene quality, consistency, and editing flexibility compared with existing methods, offering a powerful solution for applications, such as virtual reality and digital twins.</p>","PeriodicalId":29931,"journal":{"name":"Visual Computing for Industry Biomedicine and Art","volume":"9 1","pages":""},"PeriodicalIF":6.7,"publicationDate":"2026-08-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13518771/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148833059","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Semantic-guided 3D Gaussian splatting for sparse-view reconstruction in industrial digital twins.","authors":"Boyang Li, Tianhan Gao, Zuan Gu, Huimin Liu","doi":"10.1186/s42492-026-00229-x","DOIUrl":"10.1186/s42492-026-00229-x","url":null,"abstract":"<p><p>Novel view synthesis, which is essential for three-dimensional (3D) reconstruction, traditionally requires dense image sets and pre-calibrated camera parameters. However, in industrial digital twin applications spatial constraints often limit data acquisition to sparse views that fail to provide the feature correspondences necessary for accurate modeling. To overcome this bottleneck, a semantic-guided 3D Gaussian splatting (3DGS) framework tailored to sparse-view industrial reconstruction was introduced. Rather than relying on precise initialization and dense inputs, the proposed method couples explicit 3D Gaussian representations with the dense and unconstrained stereo 3D reconstruction (DUSt3R) end-to-end pose estimation model. The severe occlusions, typical of factory environments, are handled by incorporating Segment Anything Model 2 (SAM2) to hierarchically decompose the scene, yielding a structured representation that improves optimization stability. A probability density field-driven algorithm is subsequently applied to extract lightweight meshes directly from the optimized Gaussian point clouds. Evaluations on the MipNeRF360 benchmark and a custom industrial dataset demonstrated substantial improvements in the structural similarity index measure. By enabling robust reconstruction from limited viewpoints, this pipeline offers a practical geometric foundation for automated inspection and remote equipment monitoring.</p>","PeriodicalId":29931,"journal":{"name":"Visual Computing for Industry Biomedicine and Art","volume":"9 1","pages":""},"PeriodicalIF":6.7,"publicationDate":"2026-08-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13478055/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148762223","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mapping the generative era: a bibliometric and specialty-focused analysis of large language models in healthcare.","authors":"Jianding Peng, Yao Tuo, Gang Wang, Ruiqin Han, Qing Wang, Yi Wang, Zixin Hu, Xiaofei Hu","doi":"10.1186/s42492-026-00228-y","DOIUrl":"https://doi.org/10.1186/s42492-026-00228-y","url":null,"abstract":"<p><p>Large language models (LLMs) have been rapidly adopted in healthcare since 2022; however, field-level trends and specialty differences remain poorly characterized. This study aims to map the research landscape of LLMs in healthcare and generate comparative specialty profiles through a bibliometric analysis using the Web of Science Core Collection (2015-2025), including English-language articles and reviews analyzed for publication and citation trends, leading countries, institutions, authors, journals, co-citation networks, and keyword structures with VOSviewer and CiteSpace, with sub-analyses for medicine, general and internal; surgery; and radiology, nuclear medicine and medical imaging. Of the 2226 articles included, the annual output increased from four publications in 2022 to 1327 in 2025, yielding a compound annual growth rate (CAGR) of 592.26%; the United States of America contributed 43.5% of the publications, followed by China (14.3%), Germany (9.2%), Turkey (9.0%), and England (6.8%); the publications for each specialty were surgery (31.7%), medicine, general and internal (24.2%), and radiology, nuclear medicine and medical Iimaging (13.0%), with the last demonstrating the fastest 2023-2024 growth (CAGR 265%); and the collaboration networks were United States of America-centered, with dense trans-Atlantic ties. LLM research in healthcare is expanding rapidly with distinct specialty-specific trajectories, and interpreting these trajectories using the DECIDE-AI (developmental and exploratory clinical Iinvestigations of decision support systems driven by artificial intelligence) framework clarifies low-risk near-term applications and monitoring priorities, providing a specialty-aware baseline to support the safe, equitable, and regulation-aligned adoption of LLMs in clinical practice.</p>","PeriodicalId":29931,"journal":{"name":"Visual Computing for Industry Biomedicine and Art","volume":"9 1","pages":""},"PeriodicalIF":6.7,"publicationDate":"2026-08-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13476431/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148765427","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GCUNet: a graph neural network-based contextual learning network for tertiary lymphoid structure semantic segmentation in whole slide image.","authors":"Lei Su, Ruiyu Li, Guangyao Zhang, Zonghao Liu, Xuqing Geng, Hetong Wang, Weihao Gai, Huanwen Wu, Jie Tian, Yang Du","doi":"10.1186/s42492-026-00227-z","DOIUrl":"10.1186/s42492-026-00227-z","url":null,"abstract":"<p><p>This study focuses on tertiary lymphoid structure (TLS) semantic segmentation in whole slide images (WSIs). Unlike TLS binary segmentation, TLS semantic segmentation identifies boundaries and maturity and requires the integration of contextual information to discover discriminative features. Owing to the extensive scale of WSI (e.g., 100,000 × 100,000 pixels), TLS segmentation is typically performed using a patch-based strategy. However, this prevents the model from accessing information outside the patches, thereby limiting its performance. To address this issue, GCUNet, a graph neural network-based contextual learning network for TLS semantic segmentation, is proposed. Given an image patch (target) to be segmented, GCUNet first progressively aggregates the long-range and fine-grained contexts outside the target. Subsequently, a detail and context fusion block (DCFusion) was designed to integrate the context and details of the target to predict the segmentation mask. This study builds four TLS semantic segmentation datasets: TCGA-COAD, TCGA-LUSC, TCGA-BLCA, and PUMCH-PAAD. The first three, comprising 826 WSIs and 15,276 TLSs, will be made publicly available to promote TLS semantic segmentation. Experiments on these datasets demonstrate that GCUNet consistently improves the mean F1-score (mF1) performance compared with existing state-of-the-art methods, with an observed mF1 improvement of at least 7.41% over the best-performing baseline. These results highlight the potential of GCUNet for accurate TLS assessment and facilitate the development of computational pathology-based immune microenvironment analysis.</p>","PeriodicalId":29931,"journal":{"name":"Visual Computing for Industry Biomedicine and Art","volume":"9 1","pages":""},"PeriodicalIF":6.7,"publicationDate":"2026-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13427712/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148649358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}