Yousefvand Reza, Pham Thanh-Tu, Le Lawrence H, Andersen John, Lou Edmond
Department of Electrical and Computer Engineering, University of Alberta, 11-263 Donadeo Innovation Centre for Engineering, 9211-116 St, Edmonton, AB, T6G 1H9, Canada.
Department of Radiology and Diagnostic Imaging, University of Alberta, Edmonton, AB, Canada.
Med Biol Eng Comput. 2025 Apr;63(4):1177-1188. doi: 10.1007/s11517-024-03259-w. Epub 2024 Dec 15.
Migration percentage (MP) is the gold standard to assess the severity of hip displacement in children with cerebral palsy, which is measured on anteroposterior hip radiographs. Recently, the ultrasound (US) method has been developed as a safe alternative imaging modality to image and monitor children's hips. However, measuring MP on US images (MP) is time-consuming, challenging, and user-dependent. This study aimed to develop machine learning algorithms to automatically measure MP and validate the algorithms with MP. A combination of signal filtering, convolution neural networks (CNNs), and UNets was applied to segment the regions of interest (ROI), detect edges or feature points, and select the desired US frames. A total of 62 hips including both coronal and transverse scans per hip were acquired, out of which 36 with applying augmentation method were utilized for training, 8 for validation, and 18 for testing. The intraclass correlation coefficient (ICC) and the mean absolute difference (MAD) between the automated MP versus manual MP were 0.86 and 6.5% ± 5.5%, respectively. To report the MP, it took an average of 104 s/hip. This preliminary result demonstrated that MP was able to extract automatically within 2 min with a clinical acceptance accuracy (10%).
迁移百分比（MP）是评估脑瘫患儿髋关节移位严重程度的金标准，它通过髋关节前后位X线片进行测量。最近，超声（US）方法已被开发出来，作为一种安全的替代成像方式，用于对儿童髋关节进行成像和监测。然而，在超声图像上测量MP是耗时的、具有挑战性的且依赖于使用者。本研究旨在开发机器学习算法以自动测量MP，并使用MP对算法进行验证。应用信号滤波、卷积神经网络（CNN）和U-Net的组合来分割感兴趣区域（ROI）、检测边缘或特征点，并选择所需的超声帧。共采集了62个髋关节，每个髋关节包括冠状面和横断面扫描，其中36个采用增强方法的用于训练，8个用于验证，18个用于测试。自动测量的MP与手动测量的MP之间的组内相关系数（ICC）和平均绝对差（MAD）分别为0.86和6.5%±5.5%。报告MP平均每个髋关节需要104秒。这一初步结果表明，MP能够在2分钟内以临床可接受的准确率（10%）自动提取。
