面向开放世界半监督肝脏病变识别的OOD感知可靠性学习
OOD-aware Reliability Learning for open-world semi-supervised liver lesion recognition.
摘要(中文译文)
预定位局灶性肝脏病灶的多期磁共振成像分类在多中心临床实践中仍具挑战性，原因在于病灶级标注有限、各机构成像方案存在差异，且常规未标注数据可能包含预定义训练分类体系之外的类别。现有半监督方法通常假设标签空间封闭，因此当未标注池中出现未知或支持较弱的病灶时，可能受到不可靠伪标签的影响。这些挑战与类别不匹配和临床分布偏移所导致的分布外（OOD）效应密切相关。为解决该问题，我们提出OOD感知可靠性学习（ORL），这是一种用于稀疏标注、部分标签空间不匹配和多中心分布偏移下预定位肝脏病灶分类的半监督框架。ORL利用原型约束表示学习（PCRL）学习紧凑的已知类别参考流形，通过基于非对称松弛最优传输（AROT）的传输导出兼容性估计（TCE）估计样本级流形支持度，并将该支持度与分类器置信度和原型亲和度相结合以调控伪标签学习。该框架还学习一种摊销可靠性预测器，用于推理阶段的支持度评分以及病灶定位后基于可靠性的病例排序。我们在一个多中心肝脏磁共振成像队列及选定的回顾性压力设置下评估ORL，包括外部中心评估、未标注池污染、缺失期相测试和面向OOD的复合评分分析。ORL在已知类别分类上优于代表性半监督基线，并在污染和分布偏移下保持更优性能。这些结果表明，流形支持度估计可改善标签高效的预定位肝脏病灶分类，并可能在所评估的回顾性设置中改善病灶定位后基于可靠性的病例排序。
Abstract
Prelocalized focal liver lesion classification from multi-phase magnetic resonance imaging remains challenging in multi-center clinical practice because lesion-level annotation is limited, imaging protocols vary across institutions, and routine unlabeled data may contain categories outside the predefined training taxonomy. Existing semi-supervised methods usually assume a closed label space and can therefore be affected by unreliable pseudo-labels when unknown or weakly supported lesions appear in the unlabeled pool. These challenges are closely related to out-of-distribution (OOD) effects caused by category mismatch and clinical distribution shift. To address this problem, we propose OOD-aware Reliability Learning (ORL), a semi-supervised framework for prelocalized liver lesion classification under sparse annotation, partial label-space mismatch, and multi-center distribution shift. ORL learns a compact known-class reference manifold using Prototype-Constrained Representation Learning (PCRL), estimates sample-wise manifold support through Transport-derived Compatibility Estimation (TCE) with Asymmetric Relaxed Optimal Transport (AROT), and combines this support with classifier confidence and prototype affinity to regulate pseudo-label learning. The framework also learns an amortized reliability predictor for inference-time support scoring and reliability-based case ranking after lesion localization. We evaluated ORL on a multi-center liver magnetic resonance imaging cohort and selected retrospective stress settings, including external-center evaluation, unlabeled-pool contamination, missing-phase testing, and composite OOD-oriented score analyses. ORL improved known-category classification over representative semi-supervised baselines and maintained better performance under contamination and distribution shift. These results indicate that manifold support estimation can improve label-efficient prelocalized liver lesion classification and may improve reliability-based case ranking after lesion localization in the evaluated retrospective setting.
如何引用
AMA
Yulin Pu, Wei Xia, Lin Deng, Yang Xiao, Weiming Liu, Zhehan Shen, et al. OOD-aware Reliability Learning for open-world semi-supervised liver lesion recognition.. Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society. 2026; doi:10.1016/j.compmedimag.2026.102810.
APA
Yulin Pu, Wei Xia, Lin Deng, Yang Xiao, Weiming Liu, Zhehan Shen, et al (2026). OOD-aware Reliability Learning for open-world semi-supervised liver lesion recognition.. Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society. https://doi.org/10.1016/j.compmedimag.2026.102810
GB/T 7714
Yulin Pu, Wei Xia, Lin Deng, Yang Xiao, Weiming Liu, Zhehan Shen, et al. OOD-aware Reliability Learning for open-world semi-supervised liver lesion recognition.[J]. Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society, 2026 doi:10.1016/j.compmedimag.2026.102810.
在 PubMed增强版 阅读全文
翻译全文 · AI 文献问答 · PDF 原文下载 · 引用导出