发表机构
University College London; Medical University of Vienna（伦敦大学学院; 维也纳医科大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究针对前列腺MRI分级模型，提出因果推理框架，通过对抗框架抑制临床协变量可解码性来探究其依赖性。经实验，在2903例检查及576例患者验证，发现不同临床变量与分级模型的关系，为区分有害依赖和信息信号提供分析。
AI 中文摘要
基于前列腺MRI的癌症分级深度学习模型可能会编码反映有用疾病相关信号或非通用捷径信息的临床协变量，但其作用通常是假设的。我们提出了一个因果推理框架，用于探究基于MRI的国际泌尿病理学会（ISUP）分级组预测中的协变量依赖性。我们将MRI表现和ISUP分级建模为潜在肿瘤病理学的观察结果，而不是将mpMRI视为分级的直接原因，并测试候选临床变量在学习表示中是作为干扰相关因素、疾病相关代理还是无关协变量。我们使用对抗框架来实现这一点，该框架一次抑制单个临床协变量的可解码性，同时保留基于MRI的分级预测。该方法在2903例前列腺MRI检查中进行了开发和评估，并在576例患者中进行了外部验证。我们报告了一组在深度学习泛化背景下有趣且以前未被充分探索的成像与临床变量之间的相互作用。例如，在二元ISUP分级组≥2分类中，抑制年龄、BMI和饮酒分别使AUC提高了1.23%、0.84%和1.42%（均p<0.05），表明非通用协变量信息减少；相比之下，抑制PSA和前列腺体积使AUC降低了1.91%和7.61%（均p<0.001），表明这些变量携带了与任务相关的信号。这些发现表明，对抗性协变量抑制可以为区分前列腺MRI分级模型中潜在有害的依赖性和信息性信号提供一种实用的表示级分析。
英文摘要
Deep learning models for prostate MRI-based cancer grading may encode clinical covariates that either reflect useful disease-related signal or non-generalising shortcut information, but their role is usually assumed. We propose a causal-reasoning framework for probing covariate dependence in MRI-based International Society of Urological Pathology (ISUP) Grade Group prediction. Rather than treating mpMRI as a direct cause of grade, we model MRI appearance and ISUP grade as observations of latent tumour pathology, and test whether candidate clinical variables act as nuisance correlates, disease-related proxies, or irrelevant covariates in the learned representation. We implement this using an adversarial framework that suppresses the decodability of individual clinical covariate at a time while preserving MRI-based grade prediction. The approach is developed and evaluated on 2,903 prostate MRI examinations, with external validation on 576 patients. We report a set of interesting and previously under-explored imaging-to-clinical-variable interactions in the context of deep learning generalisation. For examples, in binary ISUP Grade Group $\geq2$ classification, suppressing age, BMI, and alcohol use improved AUC by 1.23%, 0.84%, and 1.42%, respectively (all p < 0.05), suggesting reduced non-generalising covariate information; In contrast, suppressing PSA and prostate volume degraded AUC by 1.91% and 7.61% (all p < 0.001), indicating that these variables carried task-relevant signal. These findings show that adversarial covariate suppression can provide a practical representation-level analysis for distinguishing potentially harmful dependence from informative signal in prostate MRI grading models.
