Department of Biomedical Engineering, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea.
Department of Convergence Medicine, Asan Medical Institute of Convergence Science and Technology, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Republic of Korea; Department of Computer Science and Engineering, Seoul National University, Seoul, South Korea.
Comput Biol Med. 2022 Jun;145:105400. doi: 10.1016/j.compbiomed.2022.105400. Epub 2022 Mar 14.
Robust labeling for semantic segmentation in radiographs is labor-intensive. No study has evaluated flatfoot-related deformities using semantic segmentation with U-Net on weight-bearing lateral radiographs. Here, we evaluated the robustness, accuracy enhancement, and efficiency of automated measurements for flatfoot-related angles using semantic segmentation in an active learning manner. A total of 300 consecutive weight-bearing lateral radiographs of the foot were acquired. The first 100 radiographs were used as the test set, and the following 200 radiographs were used as the training and validation sets, respectively. An expert orthopedic surgeon manually labeled ground truths. U-Net was used for model training. The Dice similarity coefficient (DSC) and Hausdorff distance (HD) were used to evaluate the segmentation results. In addition, angle measurement errors with a minimum moment of inertia (MMI) and ellipsoidal fitting (EF) based on the segmentation results were compared between active learning and learning with a pooled dataset. The mean values of DSC, HD, MMI, and EF of the average of all bones were 0.967, 1.274 mm, 0.792°, and 1.147° in active learning, and 0.964, 1.292 mm, 0.828°, and 1.186° in learning with a pooled dataset, respectively. The mean DSC and HD were significantly better in active learning than in learning with a pooled dataset. Labeling of all bones required 0.82 min in active learning and 0.88 min in learning with a pooled dataset. The accuracy and angle errors generally converged in both learning. However, the accuracies based on DSC and HD were significantly better in active learning. Moreover, active learning took less time for labeling, suggesting that active learning could be an accurate and efficient learning strategy for developing flatfoot classifiers based on semantic segmentation.
在 X 光片中进行语义分割的稳健标签是一项劳动密集型工作。没有研究使用 U-Net 在负重侧位 X 光片上对扁平足相关畸形进行语义分割。在这里，我们以主动学习的方式评估了使用语义分割进行自动测量扁平足相关角度的稳健性、准确性提高和效率。共采集了 300 例连续负重侧足部 X 光片。前 100 张 X 光片作为测试集，后 200 张 X 光片分别作为训练集和验证集。一名专业矫形外科医生手动标记了地面真相。使用 U-Net 进行模型训练。使用 Dice 相似系数 (DSC) 和 Hausdorff 距离 (HD) 评估分割结果。此外，还比较了基于分割结果的最小惯性矩 (MMI) 和椭球拟合 (EF) 的角度测量误差，比较了主动学习和基于池化数据集的学习。在主动学习中，所有骨骼平均值的 DSC、HD、MMI 和 EF 的平均值分别为 0.967、1.274mm、0.792°和 1.147°，在基于池化数据集的学习中，平均值分别为 0.964、1.292mm、0.828°和 1.186°。主动学习中的平均 DSC 和 HD 明显优于基于池化数据集的学习。在主动学习中，标记所有骨骼需要 0.82 分钟，在基于池化数据集的学习中需要 0.88 分钟。在两种学习中，准确性和角度误差通常都在收敛。然而，主动学习在 DSC 和 HD 上的准确率明显更高。此外，主动学习的标记时间更短，这表明主动学习可能是基于语义分割开发扁平足分类器的一种准确高效的学习策略。
