METHODS: DenseNet-based DL model was used and both training and testing are implemented in TensorFlow 1.13.1 with Keras DL libraries. The area under curve (AUC), accuracy, sensitivity, and specificity values with 95% CIs were reported. The statistical analysis was performed by using scikit-learn libraries in Python 3.7.
RESULTS: A total of 1337 RA ultrasound images were acquired from 208 patients, the number of images is 313, 657, 178, and 189 in OESS Grade L0, L1, L2, and L3, respectively. In Classification Scenario 1 SP-no versus SP-yes, three experiments with region of interest of size 192 × 448 (Group 1), 96 × 224 (Group 2), and 96 × 224 stacked with pre-segmented annotated mask of SP area (Group 3) as input achieve an AUC of 0.863 (95% CI: 0.809, 0.917), 0.861 (95% CI: 0.805, 0.916), and 0.886 (95% CI: 0.836, 0.936), respectively. In Classification Scenario 2 Healthy versus Diseased, experiments in Group 1, Group 2 and Group 3 achieve an AUC of 0.848 (95% CI: 0.799, 0.896), 0.864 (95% CI: 0.819, 0.909), and 0.916 (95% CI: 0.883, 0.952), respectively.
CONCLUSIONS: We combined DenseNet model with ultrasound images for RA condition assessment. The feasibility of using DL to create an automatic RA condition classification system was also demonstrated. The proposed method can be an alternative to the initial screening of RA patients.
方法:使用基于DenseNet的DL模型,训练和测试都在TensorFlow1.13.1中使用KerasDL库实现。曲线下面积(AUC),准确度,灵敏度,报告了95%CI的特异性值。统计分析是通过使用Python3.7中的scikit-learn库进行的。
结果:共采集了208例RA患者的1337张超声图像,在OESS等级L0、L1、L2和L3中,图像的数量分别为313、657、178和189。在分类方案1中,SP-否与SP-是,三个感兴趣区域大小为192×448的实验(第1组),96×224(第2组),和96×224与预分割的带注释的SP面积(组3)作为输入堆叠实现0.863的AUC(95%CI:0.809,0.917),0.861(95%CI:0.805,0.916),和0.886(95%CI:0.836,0.936),分别。在分类方案2中,健康与患病,第1组,第2组和第3组的实验达到0.848的AUC(95%CI:0.799,0.896),0.864(95%CI:0.819,0.909),和0.916(95%CI:0.883,0.952),分别。
结论:我们将DenseNet模型与超声图像相结合,用于RA病情评估。还证明了使用DL创建自动RA状况分类系统的可行性。所提出的方法可以替代RA患者的初始筛查。