弱监督空间定位用于前列腺癌分级中基于判别性注意力的超声-组织病理学对齐
Weakly Supervised Spatial Grounding for Discriminative Attention-Based Ultrasound-Histopathology Alignment in Prostate Cancer Grading
- University of British Columbia（不列颠哥伦比亚大学）
- Vector Institute（向量研究所）
- Ordensklinikum Linz（林茨教团医院）
- University of Alberta（阿尔伯塔大学）
- Exact Imaging（Exact Imaging公司）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究提出弱监督空间定位方法，解耦非配对跨模态蒸馏中的判别与选择功能，利用活检百分比受累监督微超声编码器，在前列腺癌分级中显著提升对齐性能。
AI中文摘要：
非配对跨模态蒸馏通过仅利用分级组对应关系，将池化的针区嵌入与冻结的组织病理学教师模型对齐，从而将分级结构从组织病理学转移到微超声（micro-US）编码器中。因此，单一目标函数需要同时服务于两个不同的功能：使斑块特征对组织状态具有判别性，以及选择哪些斑块进入池化表示。我们将这两个功能解耦。由活检中常规记录的百分比受累衍生的弱空间监督，约束每个核心内恶性组织的预测比例，独立于对齐目标作用于编码器特征。随后，对齐损失作用于核心内存在差异的特征，注意力集中于斑块的子集而非保持近似均匀。在来自七个中心的811名患者的7,166个活检核心上，采用患者级5折交叉验证，该方法达到了67.1的宏AUC和68.5的临床显著性前列腺癌（csPCa）AUC，而现有的非配对对齐方法分别为61.2和52.8，最强单模态基线分别为63.1和62.6。与旨在防止注意力均匀性崩溃的现有注意力正则化器的消融实验表明，此类正则化器不能替代标签派生的监督：它们约束注意力分布，而所需信号作用于注意力读取的特征。
英文摘要：
Unpaired cross-modal distillation transfers grade structure from histopathology into a micro-ultrasound (micro-US) encoder by aligning a pooled needle-region embedding to a frozen histopathology teacher under grade-group correspondence alone. A single objective is thereby required to serve two distinct functions: rendering patch features discriminative of tissue state, and selecting which patches enter the pooled representation. We decouple them. Weak spatial supervision derived from percentage involvement, recorded routinely at biopsy, constrains the predicted proportion of malignant tissue within each core, acting on the encoder features independently of the alignment objective. The alignment loss then operates on features that differ across a core, and attention concentrates on a subset of patches rather than remaining near-uniform. On 7,166 biopsy cores from 811 patients across seven centers under patient-level 5-fold cross-validation, the method reaches 67.1 macro AUC and 68.5 csPCa AUC, against 61.2 and 52.8 for the existing unpaired alignment method and 63.1 and 62.6 for the strongest unimodal baselines. Ablation against existing attention regularizers designed to prevent attention-uniformity collapse shows that such regularizers do not substitute for label-derived supervision: they constrain the attention distribution, whereas the signal required acts on the features that attention reads.
