Robust Hough and Spatial-To-Angular Transform Based Rotation Estimation for Orthopedic X-Ray Images

Standardized image rotation is essential to improve reading performance in interventional X-ray imaging. To minimize user interaction and streamline the 2D imaging workflow, we present a new automated image rotation method. Image rotation can follow two steps: First, an anatomy specific centerline image is predicted which depicts the desired anatomical axis to be aligned vertically after rotation. In a second step, the necessary rotation angle is calculated from the orientation of the predicted line image. We propose an end-to-end trainable model with the Hough transform (HT) and a differentiable spatial-to-angular transform (DSAT) embedded as known operators. This model allows to robustly regress a rotation angle while maintaining an explainable inner structure and allows to be trained with both a centerline segmentation and angle regression loss. The proposed method is compared to a Hu moments-based method on anterior-posterior X-ray images of spine, knee, and wrist. For the wrist images, the HT based method reduces the mean absolute angular error (MAE) from 9.28. using the Hu moments-based method to 3.54.. Similar results for the spinal and knee images can be reported. Furthermore, a large improvement of the 90th percentile of absolute angular error by a factor of 3 indicates a better robustness and reduction of outliers for the proposed method.