Accurate and Automatic 3D Segmentation of Femur and Pelvis from CT Images of the Hip based on Deep Learning

Abstract

Background: Prosthesis design of hip joint and computer-assisted surgical planning can benefit from segmentation-based computed tomography (CT). Purpose: To automatically segment the three-dimensional (3D) hip joint images, the authors developed a deep learning-based segmentation algorithm and verified its feasibility with CT image of hip joint. Methods: Conventional image augmentation strategies and specific image augmentation strategies, which were designed to mimic the deformed shape and blurring boundaries of the diseased hips, were applied to obtain a large number of training samples of diseased hips to avoid overfitting. A 3D segmentation algorithm named light 3D U-net, which segmented images from coarse to fine, was developed to improve the segmentation accuracy and reduce the computation time in 3D hip joint image with multiple targets. Results and Discussion: The test results showed that the proposed method would exceed 0.9 in the aspects of Dice score, Specificity, and Sensitivity. Comparing with traditional method, the proposed method is more efficient, accurate, and robust. The proposed method has shown great potential to be applied in prosthesis design and computer-assisted surgical planning.