Automatic analysis system of calcaneus radiograph: Rotation-invariant landmark detection for calcaneal angle measurement, fracture identification and fracture region segmentation. (July 2021)

• Record Type: Journal Article
• Authors: Guo, Jia; Mu, Yuxuan; Xue, Dong; Li, Huiqi; Chen, Junxian; Yan, Huanxin; Xu, Hailin; Wang, Wei
• Is Part Of: Computer methods and programs in biomedicine. Volume 206(2021)
• Publication Date: 2021-07
• Subjects: Calcaneus fractures -- Calcaneus radiograph -- Landmark detection -- Fracture detection -- Convolutional neural network -- Image segmentation; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2021.106124
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: We designed an automatic analysis system of calcaneus radiograph, including landmark detection, measurement of Bohler's Angle and Critical Angle of Gissane, fracture identification, and fracture region segmentation. We proposed a coarse-to-fine Rotation-Invariant Regression-Voting (RIRV) landmark detection method, which solves the problem of fickle rotation of calcaneus in radiographs. We designed a multi-task convolution neural network named U-Net with auxiliary classification output (U-Net-CH) for fracture identification and segmentation. The input ROIs of U-Net-CH are normalized by detected landmarks to uniform view, orientation, and scale so that satisfactory performance can be obtained with a small number of training data. Abstract: Background and objective: Calcaneus is the largest tarsal bone to withstand the daily stresses of weight-bearing. The calcaneal fracture is the most common type in the tarsal bone fractures. After a fracture is suspected, plain radiographs should be taken first. Bohler's Angle (BA) and Critical Angle of Gissane (CAG), measured by four anatomic landmarks in lateral foot radiograph, can guide fracture diagnosis and facilitate operative recovery of the fractured calcaneus. This study aims to develop an analysis system that can automatically locate four anatomic landmarks, measure BA and CAG for fracture assessment, identify fractured calcaneus, and segment fractured regions. Methods: For landmark detection, we proposed a coarse-to-fine Rotation-Invariant Regression-Voting (RIRV) landmark detection method based on regressive Multi-Layer Perceptron (MLP) and Scale Invariant Feature Transform (SIFT) patch descriptor, which solves the problem of fickle rotation of calcaneus. By implementing a novel normalization approach, the RIRV method is explicitly rotation-invariance comparing with traditional regressive methods. For fracture identification and segmentation, a convolution neural network (CNN) based on U-Net with auxiliary classification head (U-Net-CH) is designed. The input ROIs of the CNN are normalized by detected landmarks to uniform view, orientation, and scale. The advantage of this approach is the multi-task learning that combines classification and segmentation. Results: Our system can accurately measure BA and CAG with a mean angle error of 3.8 ○ and 6.2 ○ respectively. For fracture identification and fracture region segmentation, our system presents good performance with an F1-score of 96.55%, recall of 94.99%, and segmentation IoU-score of 0.586. Conclusion: A powerful calcaneal radiograph analysis system including anatomical angles measurement, fracture identification, and fracture segmentation can be built. The proposed analysis system can aid orthopedists to improve the efficiency and accuracy of calcaneus fracture diagnosis.