通过粗到细的标签监督，提升膝骨关节炎3D MRI表征质量。
Learning Coarse-to-Fine Osteoarthritis Representations under Noisy Hierarchical Labels
- 设计双头网络，同时学习疾病有无与严重程度分级。
- ResNet3D和M3T在双任务下分别显著提升分级准确率和诊断AUC。
- 不同模型对多粒度监督响应不同，适合特定架构选择。
膝骨关节炎（OA）评估存在二分类疾病状态与Kellgren-Lawrence（KL）分级的天然标签层级关系。本文研究在两种粒度标签下，3D MRI表征的学习效果差异。采用共享编码器搭配OA与KL预测头，在ResNet3D、M3T和nnMamba三种骨干网络上对比单任务（仅OA、仅KL）与双头训练。评估结合预测指标、贝氏曼-霍尔德伯格校正下的配对统计检验、潜在严重度轴几何结构及显著性图与软骨重叠分析。结果表明：双监督使ResNet3D的KL分级性能显著提升，M3T在OA AUC上显著增益；而nnMamba在单任务下表现更优。表征分析显示：双监督增强ResNet3D和M3T的标签对齐潜空间结构，而nnMamba在单任务下保持更强对齐性；对响应型骨干网络，双监督产生更高显著性图与软骨重叠。结果表明，在噪声层级标签下，粗到细监督可重塑疾病表征，其效益依赖于骨干网络结构。代码已开源：https://github.com/jukieCheung/coarse2fine-oa-mri。
原文摘要 · Abstract (English)
Knee osteoarthritis (OA) assessment contains a natural label hierarchy between binary disease status and Kellgren--Lawrence (KL) severity. We study whether supervision at these two granularities changes learned 3D MRI representations. A shared encoder with OA and KL prediction heads is evaluated under single-OA, single-KL, and dual-head training across ResNet3D, M3T, and nnMamba backbones. Evaluation combines predictive metrics with paired statistical comparisons under Benjamini--Hochberg FDR control, latent severity-axis geometry, and saliency--cartilage overlap. Dual supervision yields significant KL-grading gains for ResNet3D and a significant OA AUC gain for M3T, whereas nnMamba retains stronger single-task performance. Representation analysis further shows an architecture-dependent effect: Dual strengthens label-aligned latent organization for ResNet3D and M3T, while nnMamba retains stronger alignment under single-task supervision. For the responsive backbones, Dual also produces descriptively higher saliency overlap with cartilage. These results show that coarse-to-fine supervision can reshape disease representations under noisy hierarchical labels, with benefits that depend on backbone architecture. Code is available at https://github.com/jukieCheung/coarse2fine-oa-mri.
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。