发表机构
College of Artificial Intelligence, Nankai University; Tianjin First Central Hospital; School of Electronics and Information Engineering, Tiangong University; School of Artificial Intelligence, Hebei University of Technology; North China Digital Health Technology Co., Ltd.; School of Computing and Information Systems, Singapore Management University（南开大学人工智能学院; 天津市第一中心医院; 天津工业大学电子与信息工程学院; 河北工业大学人工智能学院; 华北数字健康科技有限公司; 新加坡管理大学计算与信息系统学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对多参数MRI前列腺癌诊断局限，构建数据集并提出LSDT模型，利用零样本分割和多模态融合分类，在患者队列交叉验证中取得较好准确率和召回率，增强了前列腺MRI细粒度分类及风险分层。
AI 中文摘要
多参数MRI（mpMRI）前列腺癌诊断通常基于PI-RADS评估或二元分类，存在主观性且无法捕捉临床相关病理异质性。为解决此局限，构建前列腺癌组织病理学光谱数据集（PCa-HSD），制定有临床意义的四类分类任务。提出语言引导分割辅助诊断变压器模型（LSDT），利用零样本分割提供解剖先验并进行有效多模态切片融合分类。在344例患者队列的五折交叉验证中，该方法平均准确率达0.633，联合召回率达0.768，证明整合病理学监督和解剖先验可增强前列腺MRI细粒度分类并提供更具临床相关性的风险分层范式。
英文摘要
Prostate cancer diagnosis with multiparametric MRI (mpMRI) is commonly based on PI-RADS assessment or binary classification, which suffer from subjectivity and fail to capture clinically relevant pathological heterogeneity. To address this limitation, we construct a Prostate Cancer Histopathology Spectrum Dataset (PCa-HSD) and formulate a clinically meaningful four-class classification task, addressing the underrepresentation of benign lesions that are easily confounded with prostate cancer in existing datasets. We propose Language-guided Segmentation-assisted Diagnostic Transformer model (LSDT), which leverages zero-shot segmentation to provide anatomical priors and performs effective multi-modal slice fusion for classification. Our proposed method consistently improves accuracy across backbones, achieving the best average accuracy of 0.633 and JointRecall of 0.768 in five-fold cross-validation on a cohort of 344 patients. These results demonstrate that integrating pathology supervision and anatomical priors significantly enhances fine-grained prostate MRI classification and provides a more clinically relevant paradigm for risk stratification. Code will be made publicly available in a future revision.
Comments17 pages, 6 figures, and 4 tables. Code will be made publicly available in a future revision
