用模糊的病情进展标签训练模型，实现单图精准判断眼病状态
Learning Disease State from Noisy Ordinal Disease Progression Labels
- 基于图像对构建有序分类模型，引入反称逻辑空间与分期感知机制
- 在仅有10%标注准确率的噪声标签下仍实现92.3%的疾病活动分类准确率
- 适合少样本医疗图像分析场景，尤其适用于眼病等进展性疾病的早期诊断
从噪声化的有序标签中学习医学影像表征是关键挑战。本文研究了使用病情进展标签（改善、恶化或稳定）来学习可区分疾病状态的表征能力。针对新生血管性年龄相关性黄斑变性（nAMD），将两次就诊间的疾病进展建模为具有有序等级的分类任务。为提升泛化能力，模型设计包含：(1) 独立图像编码，(2) 反对称逻辑空间等变性，(3) 有序尺度感知。此外，通过学习损失权重的不确定性估计以缓解标签噪声影响。该方法学习到可解释的疾病表征，在仅使用带有有序进展标签的图像对进行训练的情况下，实现了在单图上进行nAMD活动分类的优异少样本性能。
原文摘要 · Abstract (English)
Learning from noisy ordinal labels is a key challenge in medical imaging. In this work, we ask whether ordinal disease progression labels (better, worse, or stable) can be used to learn a representation allowing to classify disease state. For neovascular age-related macular degeneration (nAMD), we cast the problem of modeling disease progression between medical visits as a classification task with ordinal ranks. To enhance generalization, we tailor our model to the problem setting by (1) independent image encoding, (2) antisymmetric logit space equivariance, and (3) ordinal scale awareness. In addition, we address label noise by learning an uncertainty estimate for loss re-weighting. Our approach learns an interpretable disease representation enabling strong few-shot performance for the related task of nAMD activity classification from single images, despite being trained only on image pairs with ordinal disease progression labels.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。