通过难易度排序训练，提升内镜图像炎症分级的准确性
CLoE: Curriculum Learning on Endoscopic Images for Robust MES Classification
- 按图像质量排序样本，从清晰到模糊逐步训练
- 在LIMUC数据集上达82.5%准确率，QWK达0.894
- 适合需要高鲁棒性分级的医疗影像研究者
基于内镜图像评估溃疡性结肠炎疾病严重程度至关重要，其中梅奥内镜评分（MES）被广泛用于炎症分级。然而，由于观察者间差异导致的标签噪声以及评分的有序性，传统模型常忽略这些特性，使分类仍具挑战。本文提出CLoE框架，结合课程学习思想，同时考虑标签可靠性与有序结构。利用轻量级模型基于波士顿肠道准备评分（BBPS）标签估计图像质量，作为标注置信度的代理，将样本从易（清晰）到难（模糊）排序。该课程策略进一步与ResizeMix增强方法结合，提升模型鲁棒性。在LIMUC和HyperKvasir数据集上，使用CNN与Transformer均取得显著改进。例如，ConvNeXt-Tiny在低计算成本下于LIMUC达到82.5%准确率与0.894的QWK。结果表明，考虑难度的学习策略可有效应对标签不确定性下的有序分类问题。
原文摘要 · Abstract (English)
Estimating disease severity from endoscopic images is essential in assessing ulcerative colitis, where the Mayo Endoscopic Subscore (MES) is widely used to grade inflammation. However, MES classification remains challenging due to label noise from inter-observer variability and the ordinal nature of the score, which standard models often ignore. We propose CLoE, a curriculum learning framework that accounts for both label reliability and ordinal structure. Image quality, estimated via a lightweight model trained on Boston Bowel Preparation Scale (BBPS) labels, is used as a proxy for annotation confidence to order samples from easy (clean) to hard (noisy). This curriculum is further combined with ResizeMix augmentation to improve robustness. Experiments on the LIMUC and HyperKvasir datasets, using both CNNs and Transformers, show that CLoE consistently improves performance over strong supervised and self-supervised baselines. For instance, ConvNeXt-Tiny reaches 82.5\% accuracy and a QWK of 0.894 on LIMUC with low computational cost. These results highlight the potential of difficulty-aware training strategies for improving ordinal classification under label uncertainty. Code will be released at https://github.com/zeynepozdemir/CLoE.
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。