基于多模态超声图像的深度学习类风湿关节炎疾病活动度自动评分模型
本研究收集静态与动态灰阶及能量多普勒超声图像,由两名专家放射科医师按EULAR-OMERACT滑膜炎评分系统评估,开发四种基于ResNet结构的深度学习模型,在两个独立测试队列中评估并与12名不同经验放射科医师比较。结果显示深度学习模型可定量客观评估RA活动度,动态模型在多数评分过程中表现优于静态模型,尤其DPD模型。
要点
- 共1244张图像用于模型训练,152张和354张分别用于测试队列1和2。
- 评分0/1/2/3的最佳模型分别为DPD、SGS、DGS和SPD模型(AUC=0.87/0.95/0.74/0.95,无显著差异)。
- 动态深度学习模型在多数评分过程中优于静态模型,且比多数资深放射科医师更准确,尤其DPD模型。
核心结论
- 基于多模态超声图像的深度学习模型可对RA活动度进行定量客观评估。
- 动态深度学习模型尤其有潜力辅助放射科医师提高基于超声的RA分级准确性。
研究设计与样本
- 收集静态灰阶(SGS)、动态灰阶(DGS)、静态能量多普勒(SPD)和动态能量多普勒(DPD)超声图像,由两名专家放射科医师按EULAR-OMERACT滑膜炎评分系统评估。
- 基于ResNet结构开发四种深度学习模型,在两个独立测试队列中评估,并与12名不同经验水平的放射科医师比较性能。
主要发现
- 共1244张图像用于模型训练,152张和354张分别用于测试队列1和队列2。
- 评分0/1/2/3的最佳模型分别为DPD、SGS、DGS和SPD模型(AUC=0.87/0.95/0.74/0.95;无显著差异)。
- 所有深度学习模型在单张图像基础上提供与经验丰富放射科医师相当的结果(组内相关系数:0.239-0.756,P < 0.05)。
- SPD模型在测试队列1中评分0/2/3的AUC=0.82/0.67/0.95,优于SGS模型的0.66/0.66/0.75;在测试队列2中评分0的AUC=0.89,优于SGS模型的0.81。
- 动态深度学习模型在多数评分过程中表现优于静态模型,且比多数资深放射科医师更准确,尤其DPD模型。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
OBJECTIVES: We aimed to investigate the value of deep learning (DL) models based on multimodal ultrasonographic (US) images to quantify RA activity. METHODS: Static greyscale (SGS), dynamic greyscale (DGS), static power Doppler (SPD) and dynamic power Doppler (DPD) US images were collected and evaluated by two expert radiologists according to the EULAR-OMERACT Synovitis Scoring system. Four DL models were developed based on the ResNet-type structure, evaluated on two separate test cohorts, and finally compared with the performance of 12 radiologists with different levels of experience. RESULTS: In total, 1244 images were used for the model training, and 152 and 354 for testing (cohort 1 and 2, respectively). The best-performing models for the scores of 0/1/2/3 were the DPD, SGS, DGS and SPD models, respectively (Area Under the receiver operating characteristic Curve [AUC] = 0.87/0.95/0.74/0.95; no significant differences). All the DL models provided results comparable to the experienced radiologists on a per-image basis (intraclass correlation coefficient: 0.239-0.756, P < 0.05). The SPD model performed better than the SGS one on test cohort 1 (score of 0/2/3: AUC = 0.82/0.67/0.95 vs 0.66/0.66/0.75, respectively) and test cohort 2 (score of 0: AUC = 0.89 vs 0.81). The dynamic DL models performed better than the static ones in most of the scoring processes and were more accurate than the most of senior radiologists, especially the DPD model. CONCLUSION: DL models based on multimodal US images allow a quantitative and objective assessment of RA activity. Dynamic DL models in particular have potential value in assisting radiologists to improve the accuracy of RA US-based grading.
引用
- He X, Wang M, Zhao C, et al. Deep learning-based automatic scoring models for the disease activity of rheumatoid arthritis based on multimodal ultrasound images. Rheumatology (Oxford). 2024. PMID: 37471602. doi:10.1093/rheumatology/kead366
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。