用AI自动评类风湿关节炎严重程度，减少医生差异。
Automated Radiographic Total Sharp Score (ARTSS) in Rheumatoid Arthritis: A Solution to Reduce Inter-Intra Reader Variation and Enhancing Clinical Practice
- 用深度学习分步处理手部X光片，识别关节并评分
- 模型对关节识别准确率达99%，预测误差极低（Huber损失0.87）
- 适合临床医生快速、客观评估类风湿患者病情
类风湿关节炎（RA）的严重程度评估依赖于总Sharp/Van Der Heijde评分（TSS），但人工评分耗时且主观性强。本研究提出自动化放射学Sharp评分（ARTSS）框架，利用深度学习分析全手X光片，以降低阅片者间与阅片者内差异。该方法特别处理关节消失及不同数量关节的情况。基于970名患者的资料，构建四阶段流程：1）使用ResNet50进行图像预处理与重定向；2）采用UNet.3实现手部分割；3）通过YOLOv7识别关节；4）使用VGG16、VGG19、ResNet50、DenseNet201、EfficientNetB0和视觉变压器（ViT）等模型进行TSS预测。评估指标包括交并比（IoU）、平均精度（MAP）、平均绝对误差（MAE）、均方根误差（RMSE）和Huber损失。以两位放射科医生的平均TSS为真实标签，训练采用3折交叉验证，每折包含452个训练样本与227个验证样本，外部测试包含291个未见受试者。关节识别模型准确率达99%。表现最佳的模型（ViT）在TSS预测中取得0.87的低Huber损失。结果表明，深度学习可有效自动化RA评分，显著提升临床实践效率，减少人为偏差，提高诊断准确性，并辅助风湿科医生决策。
原文摘要 · Abstract (English)
Assessing the severity of rheumatoid arthritis (RA) using the Total Sharp/Van Der Heijde Score (TSS) is crucial, but manual scoring is often time-consuming and subjective. This study introduces an Automated Radiographic Sharp Scoring (ARTSS) framework that leverages deep learning to analyze full-hand X-ray images, aiming to reduce inter- and intra-observer variability. The research uniquely accommodates patients with joint disappearance and variable-length image sequences. We developed ARTSS using data from 970 patients, structured into four stages: I) Image pre-processing and re-orientation using ResNet50, II) Hand segmentation using UNet.3, III) Joint identification using YOLOv7, and IV) TSS prediction using models such as VGG16, VGG19, ResNet50, DenseNet201, EfficientNetB0, and Vision Transformer (ViT). We evaluated model performance with Intersection over Union (IoU), Mean Average Precision (MAP), mean absolute error (MAE), Root Mean Squared Error (RMSE), and Huber loss. The average TSS from two radiologists was used as the ground truth. Model training employed 3-fold cross-validation, with each fold consisting of 452 training and 227 validation samples, and external testing included 291 unseen subjects. Our joint identification model achieved 99% accuracy. The best-performing model, ViT, achieved a notably low Huber loss of 0.87 for TSS prediction. Our results demonstrate the potential of deep learning to automate RA scoring, which can significantly enhance clinical practice. Our approach addresses the challenge of joint disappearance and variable joint numbers, offers timesaving benefits, reduces inter- and intra-reader variability, improves radiologist accuracy, and aids rheumatologists in making more informed decisions.
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。