用解剖感知的多实例学习，自动预测类风湿关节炎影像评分。
Interpretable Rheumatoid Arthritis Scoring via Anatomy-aware Multiple Instance Learning
- 基于注意力机制提取关键病变区域，融合多图块进行评分预测。
- 最佳模型相关系数达0.943，误差15.73，接近放射科医生水平。
- 结果可解释，决策依据符合临床关注的关节结构。
类风湿性关节炎（RA）的Sharp/van der Heijde（SvdH）评分广泛用于临床试验中量化影像损伤，但其复杂性限制了在常规临床中的应用。为解决人工评分效率低的问题，本文提出一种两阶段可解释的图像级SvdH评分预测方法，利用双侧手部X光片。该方法通过注意力引导的多实例学习，提取与疾病相关的图像区域并整合生成图像级特征。提出两种区域提取方案：1）采样最可能含异常的图像块；2）裁剪包含关键关节的区域。采用方案2的最优单模型在预测上达到皮尔逊相关系数（PCC）0.943，均方根误差（RMSE）15.73。集成学习进一步提升性能，实现PCC 0.945，RMSE 15.57，达到当前最优水平，与经验放射科医生表现（PCC=0.97，RMSE=18.75）相当。最终，该流程能有效识别并基于临床关注的解剖结构做出决策。
原文摘要 · Abstract (English)
The Sharp/van der Heijde (SvdH) score has been widely used in clinical trials to quantify radiographic damage in Rheumatoid Arthritis (RA), but its complexity has limited its adoption in routine clinical practice. To address the inefficiency of manual scoring, this work proposes a two-stage pipeline for interpretable image-level SvdH score prediction using dual-hand radiographs. Our approach extracts disease-relevant image regions and integrates them using attention-based multiple instance learning to generate image-level features for prediction. We propose two region extraction schemes: 1) sampling image tiles most likely to contain abnormalities, and 2) cropping patches containing disease-relevant joints. With Scheme 2, our best individual score prediction model achieved a Pearson's correlation coefficient (PCC) of 0.943 and a root mean squared error (RMSE) of 15.73. Ensemble learning further boosted prediction accuracy, yielding a PCC of 0.945 and RMSE of 15.57, achieving state-of-the-art performance that is comparable to that of experienced radiologists (PCC = 0.97, RMSE = 18.75). Finally, our pipeline effectively identified and made decisions based on anatomical structures which clinicians consider relevant to RA progression.
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。