Department of Radiology, Children's Hospital of Soochow University, Suzhou, 215025, China.
School of Medical Imaging, Xuzhou Medical University, Xuzhou, 221004, China.
Biomed Eng Online. 2024 Oct 5;23(1):98. doi: 10.1186/s12938-024-01291-3.
Developmental dysplasia of the hip (DDH) is a common pediatric orthopedic condition characterized by varying degrees of acetabular dysplasia and hip dislocation. Current 2D imaging methods often fail to provide sufficient anatomical detail for effective treatment planning, leading to higher rates of misdiagnosis and missed diagnoses. MRI, with its advantages of being radiation-free, multi-planar, and containing more anatomical information, can provide the crucial morphological and volumetric data needed to evaluate DDH. However, manual techniques for measuring parameters like the center-edge angle (CEA) and acetabular index (AI) are time-consuming. Automating these processes is essential for accurate clinical assessments and personalized treatment strategies.
This study employed a U-Net-based CNN model to automate the segmentation of hip MRI images in children. The segmentation process was validated using a leave-one-out method during training. Subsequently, the segmented hip joint images were utilized in clinical settings to perform automated measurements of key angles: AI, femoral neck angle (FNA), and CEA. This automated approach aimed to replace manual measurements and provide an objective reference for clinical assessments.
The U-Net-based network demonstrates high effectiveness in hip segmentation compared to manual radiologist segmentations. In test data, it achieves average DSC values of 0.9109 (acetabulum) and 0.9244 (proximal femur), with a 91.76% segmentation success rate. The average ASD values are 0.3160 mm (acetabulum) and 0.6395 mm (proximal femur) in test data, with Ground Truth (GT) edge points and predicted segmentation maps having a mean distance of less than 1 mm. Using automated segmentation models for clinical hip angle measurements (CEA, AI, FNA) shows no statistical difference compared to manual measurements (p > 0.05).
Utilizing U-Net-based image segmentation and automated measurement of morphological parameters significantly enhances the accuracy and efficiency of DDH assessment. These methods improve precision in automatic measurements and provide an objective basis for clinical diagnosis and treatment of DDH.
发育性髋关节发育不良（DDH）是一种常见的小儿矫形骨科疾病，其特点是髋臼发育不良和髋关节脱位程度不同。目前的二维成像方法往往无法为有效的治疗计划提供足够的解剖细节，导致误诊和漏诊率较高。磁共振成像（MRI）具有无辐射、多平面和包含更多解剖信息的优势，可为评估 DDH 提供所需的关键形态和容积数据。然而，手动测量中心边缘角（CEA）和髋臼指数（AI）等参数的方法既耗时又费力。因此，实现这些过程的自动化对于准确的临床评估和个性化治疗策略至关重要。
本研究采用基于 U-Net 的卷积神经网络（CNN）模型自动分割儿童髋关节 MRI 图像。在训练过程中，采用留一法验证分割过程。随后，将分割后的髋关节图像应用于临床环境，自动测量关键角度：AI、股骨颈角（FNA）和 CEA。这种自动化方法旨在替代手动测量，为临床评估提供客观参考。
与手动放射科医生的分割相比，基于 U-Net 的网络在髋关节分割方面具有很高的有效性。在测试数据中，它的平均 DSC 值分别为 0.9109（髋臼）和 0.9244（近端股骨），分割成功率为 91.76%。测试数据中的平均 ASD 值分别为 0.3160mm（髋臼）和 0.6395mm（近端股骨），真实边界点和预测分割图之间的平均距离小于 1mm。使用自动分割模型进行临床髋关节角度测量（CEA、AI、FNA）与手动测量相比没有统计学差异（p＞0.05）。
利用基于 U-Net 的图像分割和形态参数的自动测量可显著提高 DDH 评估的准确性和效率。这些方法提高了自动测量的精度，并为 DDH 的临床诊断和治疗提供了客观依据。
