发表机构
Shanghai Jiao Tong University School of Medicine; Ruijin Hospital; Fudan University; Shandong Provincial Hospital Affiliated to Shandong First Medical University; Air Force Medical University（上海交通大学医学院; 瑞金医院; 复旦大学; 山东第一医科大学附属省立医院; 空军军医大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出MedIDL框架，通过三个正交潜在空间解耦疾病、协变量和个体差异，在7个数据集上超越现有方法，实现精准分类与可解释性。
AI 中文摘要
在医学图像分类中，准确地将疾病相关特征与混杂协变量（如年龄、性别、部位）及个体差异分离开来，仍然是一个基本挑战。传统的基于回归的方法可能忽略图像特征与真实协变量之间的非线性关系。为克服这一问题，我们提出了一种广义的医学影像解耦学习（MedIDL）框架。MedIDL通过专门的解耦头将图像特征映射到三个相互正交的潜在空间：由监督损失引导的疾病分类头、受跨受试者相似性匹配约束的协变量对齐头，以及吸收个体差异的高斯头。我们在涵盖多种成像模态的7个数据集上评估了该框架。在所有数据集上，MedIDL在准确性方面均优于最先进的监督和自监督分类方法。关联分析表明，MedIDL成功分离了目标特定的潜在表示。基于梯度的可解释性映射定位了与既定临床文献一致的病理性模式。
英文摘要
Accurately isolating disease-related features from confounding covariates (e.g., age, gender, site) and individual variations remains a fundamental challenge in medical image classification. Traditional regression-based approaches may ignore non-linear relations between image features and true covariates. To overcome this issue, we present a generalized Medical Imaging Disentanglement Learning (MedIDL) framework. MedIDL maps image features into three mutually orthogonal latent spaces through specialized disentanglement heads: a disease classification head guided by a supervised loss, a covariate-alignment head constrained by cross-subject similarity matching, and a Gaussian head absorbing individual variations. We evaluated our framework across 7 datasets encompassing diverse imaging modalities. MedIDL outperforms state-of-the-art supervised and self-supervised classification methods in accuracy across all datasets. Association analyses demonstrate that MedIDL successfully isolates target-specific latent representations. Gradient-based interpretability mappings localize pathognomonic patterns aligning with established clinical literature.
Comments14 pages, including a 4-page appendix
