级联卷积神经网络设计进一步提升类风湿关节炎超声图像关节炎疾病活动度自动评分
该研究在原有神经网络基础上,采用级联卷积神经网络(CNN)设计对类风湿关节炎(RA)患者超声图像按EULAR-OMERACT滑膜炎评分系统进行自动评分。使用1678张图像训练、322张图像测试,模型四分类准确率达83.9%,在患者层面与专家风湿科医生的分类无显著差异(p=0.85),优于原CNN的75.0%准确率。
要点
- 级联CNN在RA超声图像四分类评分中准确率达83.9%,优于原CNN的75.0%。
- 患者层面模型分类与专家风湿科医生无显著差异(p=0.85)。
- 该方法在未见数据上表现出与专家较强的一致性,可作为客观评估RA疾病活动度的辅助工具。
核心结论
- 采用级联卷积神经网络架构可进一步提升RA超声图像关节炎疾病活动度自动评分的性能,并在关节层面和患者层面与专家风湿科医生表现出强一致性。
研究设计与样本
- 研究使用1678张图像训练模型、322张图像测试模型,由专家风湿科医生按EULAR-OMERACT滑膜炎评分系统对图像进行评分,系统训练CNN以寻找最佳配置,并在独立测试集上评估算法。
主要发现
- 模型总体四分类准确率为83.9%,原CNN四分类准确率为75.0%。
- 在患者层面,模型分类与人类专家分类之间无显著差异(p=0.85)。
- 在关节层面使用Kappa统计量评估模型与专家风湿科医生评分的一致性。
关键数值与推荐
- 评分依据为EULAR-OMERACT滑膜炎评分系统,模型四分类准确率为83.9%,患者层面与专家比较p=0.85,原CNN四分类准确率为75.0%。
临床怎么用
- 该级联CNN架构可作为RA患者疾病活动度客观评估的强辅助工具,在关节层面和患者层面与专家风湿科医生评分具有强一致性。
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 have previously shown that neural network technology can be used for scoring arthritis disease activity in ultrasound images from rheumatoid arthritis (RA) patients, giving scores according to the EULAR-OMERACT grading system. We have now further developed the architecture of this neural network and can here present a new idea applying cascaded convolutional neural network (CNN) design with even better results. We evaluate the generalisability of this method on unseen data, comparing the CNN with an expert rheumatologist. METHODS: The images were graded by an expert rheumatologist according to the EULAR-OMERACT synovitis scoring system. CNNs were systematically trained to find the best configuration. The algorithms were evaluated on a separate test data set and compared with the gradings of an expert rheumatologist on a per-joint basis using a Kappa statistic, and on a per-patient basis using a Wilcoxon signed-rank test. RESULTS: With 1678 images available for training and 322 images for testing the model, it achieved an overall four-class accuracy of 83.9%. On a per-patient level, there was no significant difference between the classifications of the model and of a human expert (p=0.85). Our original CNN had a four-class accuracy of 75.0%. CONCLUSIONS: Using a new network architecture we have further enhanced the algorithm and have shown strong agreement with an expert rheumatologist on a per-joint basis and on a per-patient basis. This emphasises the potential of using CNNs with this architecture as a strong assistive tool for the objective assessment of disease activity of RA patients.
引用
- Christensen ABH, Just SA, Andersen JKH, et al. Applying cascaded convolutional neural network design further enhances automatic scoring of arthritis disease activity on ultrasound images from rheumatoid arthritis patients. Ann Rheum Dis. 2020. PMID: 32503859. doi:10.1136/annrheumdis-2019-216636
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。