[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"item-4429":3,"related-4429":63},{"id":4,"title":5,"url":6,"summary":7,"summary_zh":8,"source_name":9,"source_url":6,"published_at":10,"category":11,"cover_url":12,"hotness":13,"is_selected":14,"embedding_ready":15,"score":16,"sources":17,"tags":19,"primary_topic":12,"secondary_topics":20,"search_phrases":21,"slug":22,"view_count":16,"doi":23,"paper":24,"created_at":46,"content":12,"score_detail":47,"classification":49},4429,"A modular pancreas segmentation and multimodal fusion framework for clinical and CT decision support in acute pancreatitis","https:\u002F\u002Fdoi.org\u002F10.1007\u002Fs10791-026-10258-y","Timely decision support in emergency imaging requires robust integration of structured clinical variables and contrast-enhanced CT while minimizing reader-dependent processing and improving reproducibility. We propose a modular segmentation-to-fusion framework for multimodal clinical–CT prediction using acute pancreatitis as a case study. The pipeline uses automated pancreas ROI generation with post-segmentation quality control, extracts complementary radiomics and frozen deep features, and integrates multimodal evidence through a calibrated stacked ensemble. We evaluated the framework on a retrospective single-center contrast-enhanced CT cohort using internal training and held-out test splits, assessing discrimination, calibration, and decision-curve performance. The proposed multimodal stacked ensemble achieved an AUC of 0.913 (95% CI 0.840–0.972) on the internal held-out test cohort and showed improved calibration and decision-curve performance compared with comparator models. These results suggest that reproducible multimodal clinical-imaging fusion may provide complementary information for internal risk estimation of AP in a single-center retrospective setting.","急诊影像中的及时决策支持需要稳健地整合结构化临床变量与增强CT，同时尽量减少依赖阅片者的处理并提高可重复性。我们以急性胰腺炎为案例，提出了一种用于多模态临床–CT预测的模块化分割到融合框架。该流程采用自动胰腺感兴趣区（ROI）生成并结合分割后质量控制，提取互补的影像组学特征与冻结深度特征，并通过校准的堆叠集成整合多模态证据。我们在一个回顾性单中心增强CT队列上评估了该框架，采用内部训练与留出测试划分，评估了区分度、校准度和决策曲线性能。所提出的多模态堆叠集成在内部留出测试队列上达到AUC为0.913（95% CI 0.840–0.972），与对照模型相比，校准度和决策曲线性能均有所改善。这些结果表明，在单中心回顾性设置下，可重复的多模态临床–影像融合可为急性胰腺炎（AP）的内部风险估计提供补充信息。","Discover Computing","2026-10-06T00:00:00Z","论文",null,10,false,true,0,[18],{"name":9,"url":6},[11],[],[],"Amodularpancreassegmentationandmultimoda-4429","10.1007\u002Fs10791-026-10258-y",{"doi":23,"openalex_id":25,"authors":26,"venue":9,"cited_by_count":16,"oa_url":37,"card":38,"direction":44,"ingested_from":45},"W7220712460",[27,29,31,33,35],{"name":28,"orcid":12},"Zhang Gengning",{"name":30,"orcid":12},"Jianqi Li",{"name":32,"orcid":12},"Jie Jiang",{"name":34,"orcid":12},"Yue Yu",{"name":36,"orcid":12},"Jinguang Gu","https:\u002F\u002Flink.springer.com\u002Fcontent\u002Fpdf\u002F10.1007\u002Fs10791-026-10258-y.pdf",{"tldr":39,"method":40,"finding":41,"direction":42,"opportunity":43},"提出模块化胰腺分割与多模态融合框架，结合临床与CT数据预测急性胰腺炎风险。","自动胰腺ROI分割与质控，提取影像组学和冻结深度特征，用校准堆叠集成融合。","多模态堆叠集成AUC达0.913，校准和决策曲线优于对比模型。","农业人工智能与决策模型","可迁移至农业领域，探索作物影像与农艺数据融合的模块化决策支持框架。","农业遥感与作物表型","openalex","2026-10-08T23:30:21.373431Z",{"impact":16,"substance":16,"depth":16,"authority":16,"freshness":16,"relevant":16,"comment":48},"该论文研究急性胰腺炎的胰腺分割与多模态融合临床决策支持，属于医学影像与临床AI领域，与三农、农业信息化、智慧农业、数字乡村等主题无关，不建议进入每日精选。",{"status":50,"locked":14,"version":51,"method":52,"evidence":53},"needs_review","2026-10-22.2","rules",{"candidates":54,"agricultural_evidence":14,"reason":62},[55],{"code":56,"score":57,"supported":15,"title":58,"abstract":60,"tags":61},"I2",11,[59],"decision support",[59],[],"农业相关性需要复核",{"total":16,"page":64,"page_size":64,"items":65},1,[]]