Journal of imaging informatics in medicine最新文献_第2页

Computer-Aided Diagnosis of Clinically Significant Prostate Cancer in Transrectal Ultrasound. 经直肠超声诊断临床意义前列腺癌的计算机辅助诊断。

IF 3.1

Journal of imaging informatics in medicine Pub Date : 2026-10-21 DOI: 10.1007/s10278-026-02409-w

Zetian Feng, Juan Fu, Xuebin Zou, Hongsheng Ye, Haoyu Pan, Yong-Hong Li, Jianhua Zhou, Yi Wang

{"title":"Computer-Aided Diagnosis of Clinically Significant Prostate Cancer in Transrectal Ultrasound.","authors":"Zetian Feng, Juan Fu, Xuebin Zou, Hongsheng Ye, Haoyu Pan, Yong-Hong Li, Jianhua Zhou, Yi Wang","doi":"10.1007/s10278-026-02409-w","DOIUrl":"https://doi.org/10.1007/s10278-026-02409-w","url":null,"abstract":"Diagnosing clinically significant prostate cancer (csPCa) using transrectal ultrasound (TRUS) remains a challenging task due to limited image contrast and the subtle appearance of malignant lesions. In this study, we propose a novel hybrid framework that integrates multi-modality and multi-task learning for csPCa classification from TRUS data. The framework leverages complementary information from B-mode and strain elastography (SE) imaging via a dual-stream encoder, enhanced by cross-modal attention gate (CMAG) modules at each level. These CMAG modules first adaptively integrate cross-modal features and then employ a gating mechanism to regulate the flow of cross-modal context into each modality-specific stream. To mitigate the scarcity of segmentation annotations, we introduce a multi-scale prototype-guided learning (MSPL) strategy, which propagates supervision signals from a small set of labeled samples to unlabeled ones by leveraging learned prototypes across multiple feature scales. This design allows the task-shared encoder to benefit from structural cues captured by the segmentation branch, even with minimal voxel-level supervision. Additionally, a context-aware multi-scale classifier (CMSC) aggregates hierarchical decoder features to further exploit the synergy between classification and segmentation tasks. The proposed method is evaluated on an in-house dataset containing 612 subjects who underwent prostate biopsy and attains favorable performance in identifying csPCa with an area under the curve (AUC) of 0.86. Extensive comparative and ablation results further highlight the efficacy of incorporating cross-modal interaction, prototype-guided learning, and context-aware classification for accurate and annotation-efficient csPCa diagnosis. The code is publicly available at https://github.com/mock1ngbrd/ProstateMMTNet .","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149241125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Toward Verifiable Medical Imaging World Models: An Engineering Framework for Evaluating Simulation Fidelity, Roll-Out Stability, and Clinical Plausibility. 迈向可验证的医学成像世界模型：评估模拟保真度、推出稳定性和临床合理性的工程框架。

IF 3.1

Journal of imaging informatics in medicine Pub Date : 2026-10-21 DOI: 10.1007/s10278-026-02413-0

Chathura Wimalasiri

{"title":"Toward Verifiable Medical Imaging World Models: An Engineering Framework for Evaluating Simulation Fidelity, Roll-Out Stability, and Clinical Plausibility.","authors":"Chathura Wimalasiri","doi":"10.1007/s10278-026-02413-0","DOIUrl":"https://doi.org/10.1007/s10278-026-02413-0","url":null,"abstract":"Medical world models simulate how a patient's imaged state evolves over time and, in some systems, under clinical interventions. Their value comes from multi-step, action-conditioned roll-outs, yet evaluation is still dominated by perceptual or single-step metrics. We treat assessment of these models as a verification problem, distinct from later evidence of clinical benefit, and organize it around three axes. Simulation fidelity asks whether predicted states are correct at the level claimed by the model. Roll-out stability asks whether that correctness is maintained over multiple steps; we summarize this using an effective planning horizon, defined as the last step before a stated loss quantile first exceeds a clinical tolerance under the observed action policy. Clinical plausibility and reliability ask whether simulated responses are counterfactually consistent, calibrated, and adequate across patient subgroups. We also propose a claim-proportionate reporting standard and a reproducible procedure for estimating the horizon from retrospective data. Applying the framework to a purposively selected sample of nine imaging world models, we find that reported evidence is uneven across capability tiers. Under the proposed standard, every model claiming action-conditioned prediction or above omits at least one applicable item: none reports an explicit counterfactual-consistency check or a clinically meaningful subgroup analysis of the type specified in Item 7, and none reports an effective planning horizon at a stated clinical tolerance. Because the effective planning horizon is estimated on-policy, it should not be interpreted as evidence of off-policy counterfactual reliability.","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149241095","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

TRACE-CLDN: An Integrated Computational Pathology Framework for Tumor-Restricted Quantification of CLDN18.2 Expression Burden from H&E Whole-Slide Images in Intrahepatic Cholangiocarcinoma. TRACE-CLDN：用于肝内胆管癌H&E全切片图像中CLDN18.2表达负荷肿瘤限制性定量的综合计算病理学框架

IF 3.1

Journal of imaging informatics in medicine Pub Date : 2026-10-21 DOI: 10.1007/s10278-026-02433-w

Yu-Meng Pan, Hao-Tian Zhang, Meng-Ling Liu, Xin-Yi Jiang, Zhi-Qiang Yang, Li Sui

{"title":"TRACE-CLDN: An Integrated Computational Pathology Framework for Tumor-Restricted Quantification of CLDN18.2 Expression Burden from H&E Whole-Slide Images in Intrahepatic Cholangiocarcinoma.","authors":"Yu-Meng Pan, Hao-Tian Zhang, Meng-Ling Liu, Xin-Yi Jiang, Zhi-Qiang Yang, Li Sui","doi":"10.1007/s10278-026-02433-w","DOIUrl":"https://doi.org/10.1007/s10278-026-02433-w","url":null,"abstract":"Claudin-18.2 (CLDN18.2) is a membrane-associated biomarker with emerging translational relevance in biliary tract cancers. In intrahepatic cholangiocarcinoma (ICC), whole-slide image (WSI)-level assessment is complicated by abundant stroma, dispersed tumor glands, non-neoplastic epithelial structures, and heterogeneous membranous staining. We developed TRACE-CLDN (Tumor-Restricted Analysis for Computational Estimation of CLDN18.2), an integrated computational pathology framework for tumor-restricted quantification of CLDN18.2 expression burden from hematoxylin and eosin (H&E) WSIs. This retrospective study included 135 ICC cases with paired H&E and CLDN18.2 immunohistochemistry (IHC) WSIs. After cross-modal registration, IHC-derived annotations were mapped to H&E images to generate patch-level training data. TRACE-CLDN integrates two independently trained H&E-based modules for tumor region identification and CLDN18.2 expression label prediction, followed by WSI-level tumor-restricted aggregation. Agreement with pathologist consensus was assessed in a 45-case pathologist-validation subset, and exploratory survival analysis was performed in the full cohort. ROC-AUCs were 0.9968 ± 0.0009 for tumor identification and 0.9633 ± 0.0174 for expression prediction. The TRACE-CLDN-derived Ratio showed strong agreement with pathologist assessment (Spearman ρ = 0.876; weighted κ = 0.767). In exploratory survival analysis, the log-rank P value was 0.010 and the concordance index was 0.668. TRACE-CLDN enables tumor-restricted, continuous assessment of CLDN18.2 expression burden from H&E WSIs, with strong agreement with pathologist assessment and an exploratory association with survival in ICC.","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-10-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149241107","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Operational Ontology for Radiology: A Framework for Profiling and Characterizing CT Imaging Data. 放射学的操作本体：一个分析和表征CT成像数据的框架。

IF 3.1

Journal of imaging informatics in medicine Pub Date : 2026-10-20 DOI: 10.1007/s10278-026-02370-8

Njood Alsaihati, Yunrong Cai, Jered Wells, Justin Solomon, Donald P Frush, Ehsan Samei

{"title":"Operational Ontology for Radiology: A Framework for Profiling and Characterizing CT Imaging Data.","authors":"Njood Alsaihati, Yunrong Cai, Jered Wells, Justin Solomon, Donald P Frush, Ehsan Samei","doi":"10.1007/s10278-026-02370-8","DOIUrl":"https://doi.org/10.1007/s10278-026-02370-8","url":null,"abstract":"Medical imaging data are increasingly used for benchmarking, quality improvement, research, and artificial intelligence applications. However, the lack of consistent metadata characterization limits the reliability and scalability of such analyses. Existing standards provide syntactic interoperability but often fail to capture the semantic clinical context and workflow details necessary for secondary uses such as AI development and radiation safety assessment, affecting the utility for reproducible profiling of imaging examinations across institutions. In this work, we describe key gaps in current approaches to imaging data standardization. These include syntactic interoperability without semantic equivalence, limited representation of clinically relevant context, inconsistent definitions of radiology procedures across institutions, and the absence of mechanisms to systematically profile imaging examinations for analysis. These limitations make it difficult to compare imaging practices, aggregate datasets, and interpret results across sites. To address these challenges, we have devised an ontology framework, the Operational Ontology for Radiology (OOR), that models the radiology study workflow from ordering through interpretation using explicitly defined entities, relationships, and annotated data properties. A CT-focused implementation of the framework was then formed, including 34 classes, 15 object properties, and 156 data properties in this present formation. The framework was deployed in a demonstrative use case scenario to illustrate the utility of OOR in drawing more clinically relevant radiation dose aggregates from clinical CT data. The work demonstrates that OOR provides both a structured representation of imaging data and a foundation for more transparent data aggregation, scalable secondary analysis, and reproducible characterization of imaging practices across institutions.","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149229681","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

M4DTrack: A DICOM-Based Imaging Informatics Workflow for User-Supervised 4DCT Lung Tumor Motion Reporting. M4DTrack：基于dicom的图像信息学工作流，用于用户监督的4DCT肺肿瘤运动报告。

IF 3.1

Journal of imaging informatics in medicine Pub Date : 2026-10-20 DOI: 10.1007/s10278-026-02435-8

Tae Kyu Lee

{"title":"M4DTrack: A DICOM-Based Imaging Informatics Workflow for User-Supervised 4DCT Lung Tumor Motion Reporting.","authors":"Tae Kyu Lee","doi":"10.1007/s10278-026-02435-8","DOIUrl":"https://doi.org/10.1007/s10278-026-02435-8","url":null,"abstract":"Four-dimensional computed tomography (4DCT) is routinely used in radiotherapy simulation to evaluate respiration-induced tumor motion, but the motion information is often reviewed visually rather than captured as structured, phase-resolved data. We developed and evaluated M4DTrack, a DICOM-based imaging-informatics workflow for user-supervised 4DCT lung tumor motion analysis and structured, exportable three-dimensional center-of-mass (CoM) motion reporting. M4DTrack imports phase-resolved DICOM CT images, groups images by respiratory phase, displays linked axial/coronal/sagittal views, supports crosshair-based tumor localization and HU inspection, and applies seed or linked 3D-box initialization with sequential phase-to-phase HU-volume propagation. An 8-case lower-lobe lung 4DCT dataset (80 respiratory phases) was analyzed. Directional amplitudes, 3D vector amplitude, maximum phase-wise displacement, and agreement with independent ITV-GTV reference amplitudes were quantified. HU-weighted CoM amplitudes were 2.44 ± 1.44 mm, 2.64 ± 1.37 mm, and 6.04 ± 2.48 mm in X, Y, and Z patient-coordinate directions, respectively. Mean 3D vector amplitude was 7.26 ± 2.50 mm, and mean maximum phase-wise 3D displacement was 6.20 ± 2.10 mm. Biases versus ITV-GTV reference amplitudes were 0.01, - 0.84, and 0.23 mm for X, Y, and Z, respectively, with a 3D vector amplitude bias of - 0.29 mm. M4DTrack provides a user-supervised imaging-informatics bridge between qualitative 4DCT cine review and structured quantitative motion documentation. The pilot results support feasibility for generating exportable, phase-resolved tumor-motion metrics while preserving user-supervised review of 4DCT artifacts, HU-capture uncertainty, adjacent anatomy, and differences between CoM-based and extent-based measurements.","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149229668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

TurkRadLLM: A Compact MedGemma-Based Model for Structuring Turkish Lumbar and Cervical Spine MRI Reports-A Multi-reader Validation Study. TurkRadLLM：一种基于medgemma的紧凑模型，用于构建土耳其腰椎和颈椎MRI报告-一项多阅读器验证研究。

IF 3.1

Journal of imaging informatics in medicine Pub Date : 2026-10-20 DOI: 10.1007/s10278-026-02427-8

Ahmet Harun Turgan, Hasan Çolakoğlu, Akif Demir, Zakir Sakcı

{"title":"TurkRadLLM: A Compact MedGemma-Based Model for Structuring Turkish Lumbar and Cervical Spine MRI Reports-A Multi-reader Validation Study.","authors":"Ahmet Harun Turgan, Hasan Çolakoğlu, Akif Demir, Zakir Sakcı","doi":"10.1007/s10278-026-02427-8","DOIUrl":"https://doi.org/10.1007/s10278-026-02427-8","url":null,"abstract":"To develop and validate a compact, locally deployable MedGemma-based model converting unstructured Turkish spine MRI reports into structured six-field output. In this retrospective single-institution study, 5210 lumbar and 5017 cervical Turkish spine MRI reports were used to fine-tune MedGemma 4B IT with QLoRA. Silver-standard labels from a proprietary large language model served as training targets and as the reference for automated fidelity analyses, but not as the clinical reference standard. Evaluation comprised multi-reader validation of 180 authentic reports interleaved with 20 adversarial cases, a second round in which the readers scored the silver labels themselves, and comparison on the full held-out set against a rule-based baseline, the non-fine-tuned base model, and a much larger model. Every output was valid, schema-conformant JSON, and the grouped acceptance rate was 100% (95% CI 97.9-100), though one reader judged negative-finding lists incomplete in 57.8% of reports. On the full held-out set (1025 reports), fine-tuning increased agreement with the silver-label impression from 17.7% to 67.1% and urgent-flag sensitivity against the silver reference from 18.8% to 62.5% (both p < .001); the larger non-fine-tuned model reached 27.5% and 50.0%, and a rule-based baseline 99.0% on body region. When the readers scored the silver labels themselves, the model was rated higher on negative findings and lower on the impression. Deployment required 14.75 GB of GPU memory on a consumer card. Fine-tuning a compact medical language model produced structured output rated acceptable by clinicians, though negative-finding completeness remained reader-dependent. The gain lay in content-level fidelity rather than output validity.","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149229740","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

3D-DDN Faster R-CNN: Pulmonary Nodule Detection Through Cross-Slice Feature Fusion and Dynamic Displacement Modeling. 3D-DDN Faster R-CNN：基于横切面特征融合和动态位移建模的肺结节检测。

IF 3.1

Journal of imaging informatics in medicine Pub Date : 2026-10-20 DOI: 10.1007/s10278-026-02432-x

Chuantao Guan, Dongliang Yang, Zihao Leng, Shuo Liu, Ang Zu, Dongmei Luo, Hai Chen, Jiamei Wang

{"title":"3D-DDN Faster R-CNN: Pulmonary Nodule Detection Through Cross-Slice Feature Fusion and Dynamic Displacement Modeling.","authors":"Chuantao Guan, Dongliang Yang, Zihao Leng, Shuo Liu, Ang Zu, Dongmei Luo, Hai Chen, Jiamei Wang","doi":"10.1007/s10278-026-02432-x","DOIUrl":"https://doi.org/10.1007/s10278-026-02432-x","url":null,"abstract":"Accurate pulmonary nodule detection in computed tomography (CT) remains challenging because small- and low-contrast nodules may resemble vessels and other anatomical structures on individual axial slices. We propose 3D-DDN Faster R-CNN, a multi-slice detection framework that incorporates structured local axial context into a two-stage detector. The five-slice interactive blending (5-SIB) strategy organizes five consecutive CT slices as an ordered contextual group and preserves slice-specific feature streams extracted by a shared two-dimensional backbone. The cross-slice feature fusion (CSFF) module applies slice-wise spatial self-attention at shallow feature levels and learnable cross-slice aggregation at deep feature and region-of-interest levels. The dynamic displacement constraint (DDC) models proposal displacement across adjacent slices using a positive-sample regression loss and a margin-based negative-sample contrastive loss, while a class-weighted focal loss alleviates foreground-background imbalance. The model was evaluated on a private hospital dataset, LIDC-IDRI, and LNDb using patient-level data partitions. On the private hospital dataset, 3D-DDN achieved an average precision at an IoU threshold of 0.5 (AP0.5) of 75.80% ± 1.05%, a sensitivity of 89.33% ± 1.91%, and a competition performance metric (CPM) of 91.20% ± 1.50%. The corresponding AP0.5 values on LIDC-IDRI and LNDb were 66.27% ± 0.45% and 48.20% ± 0.30%, respectively. Ablation experiments showed that direct five-slice stacking degraded performance, whereas structured feature fusion and displacement supervision recovered the performance loss and improved the overall detection profile. These results indicate that ordered cross-slice representation, hierarchical feature fusion, and proposal-displacement supervision provide complementary mechanisms for incorporating local three-dimensional context.","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-10-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149229742","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The Performance Ceiling of LIDC-IDRI Is Label-Defined Rather than Image-Defined: A Computable Bound and a Purposive Audit of Published Studies. LIDC-IDRI的性能上限是标签定义的而不是图像定义的：一个可计算的边界和对已发表研究的有目的审计。

IF 3.1

Journal of imaging informatics in medicine Pub Date : 2026-10-19 DOI: 10.1007/s10278-026-02420-1

Yen-Hsiang Wang

{"title":"The Performance Ceiling of LIDC-IDRI Is Label-Defined Rather than Image-Defined: A Computable Bound and a Purposive Audit of Published Studies.","authors":"Yen-Hsiang Wang","doi":"10.1007/s10278-026-02420-1","DOIUrl":"https://doi.org/10.1007/s10278-026-02420-1","url":null,"abstract":"Benchmarks labelled by panels of human readers underpin most medical image analysis. We ask whether such a dataset has a single attainable ceiling. All 1319 annotation files of the Lung Image Database Consortium image collection (LIDC-IDRI) were parsed into 7034 reader-level ratings. Modelling each nodule by a latent malignancy propensity of which the four reader verdicts are conditionally independent draws, we prove that no image-based model can exceed, against a reader-derived label, the area under the receiver operating characteristic curve (AUC) of the propensity itself; we derive how that bound depends on the labelling policy, test the independence assumption against a prediction the fit does not use, simulate its failures, and audit a purposive sample of 22 published studies against the rules they declare. Among 905 nodules read by all four radiologists, all four agreed exactly for 11.7% and 58.0% carried ratings spanning two or more points. Across three latent families, retaining every nodule the ceiling is 0.898-0.913; discarding the 19.6% the readers split two-two lifts it to 0.946-0.954; retaining only unanimous nodules discards 57.7% and lifts it to 0.991-0.994. On the binary scale, no family predicted more reader agreement than observed; simulated reader heterogeneity would make these ceilings slightly low. Of 27 reported figures, 11 lie above the bound implied by the study's own declared rule, four beyond sampling error and two if modest heterogeneity is also allowed for. The ceiling is set by the label, not by the images.","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149225568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SVF-net: A Dual-encoder Network with Adaptive Gated Fusion for Colorectal Polyp Segmentation. 基于自适应门控融合的双编码器网络的结直肠息肉分割。

IF 3.1

Journal of imaging informatics in medicine Pub Date : 2026-10-19 DOI: 10.1007/s10278-026-02415-y

Zepeng Zhang, Long Yu, Shengwei Tian

{"title":"SVF-net: A Dual-encoder Network with Adaptive Gated Fusion for Colorectal Polyp Segmentation.","authors":"Zepeng Zhang, Long Yu, Shengwei Tian","doi":"10.1007/s10278-026-02415-y","DOIUrl":"https://doi.org/10.1007/s10278-026-02415-y","url":null,"abstract":"Automatic colorectal polyp segmentation in retrospective still colonoscopy images remains challenging for small, low-contrast, partially occluded, or irregular lesions. We propose SVF-Net, a heterogeneous dual-encoder network combining a frozen SAM2 Hiera-L image trunk with a trainable MaxViT-RMLP-Small specialist branch. At four feature scales, the two streams are projected to a common width, spatially aligned, and reconciled by complementary channel-spatial gating before progressive decoding. Across five public benchmarks, three-run mean mDice is 0.922 on CVC-ClinicDB, 0.898 on Kvasir-SEG, 0.805 on CVC-ColonDB, 0.770 on ETIS-LaribPolypDB, and 0.896 on CVC-300. Matched projected-concatenation and fixed-weight ( <math><mrow><mi>G</mi> <mo>=</mo> <mn>0.5</mn></mrow> </math> ) controls retain the surrounding fusion path while removing input-dependent weighting; across ten matched training runs, adaptive gating gives higher mean mDice than both controls on all five datasets. Dataset-wide gate diagnostics on all 380 CVC-ColonDB and 196 ETIS cases indicate non-collapsed, scale- and region-dependent activations, while targeted one-factor sensitivity checks cover the MaxViT learning-rate multiplier, gate initialization, and auxiliary-loss weight. Matched per-case analyses further show that cross-domain gains are heterogeneous across lesion size, brightness, and an image-derived specular-reflection proxy. SVF-Net requires 92.8 ms per image (10.8 FPS) and 8.5 GB peak GPU memory on an NVIDIA RTX 3090 under the reported profiling protocol. The study evaluates retrospective static images only and does not establish real-time colonoscopy performance, prospective clinical effectiveness, or clinician benefit.","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149225611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Automated MRI Series Classification Across Heterogeneous Datasets Using Limited Manual Annotation. 自动化MRI系列分类跨异构数据集使用有限的手动注释。

IF 3.1

Journal of imaging informatics in medicine Pub Date : 2026-10-19 DOI: 10.1007/s10278-026-02425-w

Ryan Fishman, Evan Calabrese

{"title":"Automated MRI Series Classification Across Heterogeneous Datasets Using Limited Manual Annotation.","authors":"Ryan Fishman, Evan Calabrese","doi":"10.1007/s10278-026-02425-w","DOIUrl":"https://doi.org/10.1007/s10278-026-02425-w","url":null,"abstract":"The purpose of this study is to determine the smallest tested fraction of manually labeled training data required for a multimodal artificial intelligence (AI) classifier to achieve satisfactory MRI series classification performance (macro-F1 ≥ 0.80) across five heterogeneous public MRI datasets using digital imaging and communications in medicine (DICOM) metadata, image data, or both. This retrospective study included 3804 examinations and 14,054 MRI series from five public DICOM datasets spanning brain, knee, lumbar spine, liver, and breast MRI, accessed February-April 2026. AI classification models included a random forest classifier using DICOM header metadata, a deep convolutional neural network classifier using the geometric center slice of each MRI series, and decision-fusion models. Models were trained with 5%-40% of studies manually labeled in 5-percentage-point increments, with additional 1%-4% fractions for the knee and lumbar spine. Model performance was evaluated on the remaining studies using study-level splits across five random seeds. Results were summarized as mean ± standard deviation. Zero-label unsupervised clustering results were evaluated separately on the full dataset. The macro-F1 target was reached at the smallest tested training fraction of 1% in the lumbar spine (0.945 ± 0.013), at 2% in the knee (0.818 ± 0.006), at 10% in the brain (0.872 ± 0.027), and at 20% in the liver (0.827 ± 0.016) and the breast (0.847 ± 0.012). The best-performing model differed by dataset, reflecting different contributions from metadata versus image data. Across five separately evaluated public MRI datasets, at least one header-based, image-based, or combined model achieved macro-F1 ≥ 0.80 using no more than 20% manually labeled studies.","PeriodicalId":516858,"journal":{"name":"Journal of imaging informatics in medicine","volume":" ","pages":""},"PeriodicalIF":3.1,"publicationDate":"2026-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149225778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0