Lumbar spine posterior corner detection in X-rays using Haar-based features

3D reconstruction of the spine using biplanar X-rays remains approximate and sometimes requires human-machine interactions to adjust the position of important features such as vertebral corners and endplates. The purpose of this study is to develop a method to extract automatically the accurate position of lumbar vertebrae posterior corners. In the proposed method we select corner point candidates from an initial edge map. A dedicated pipeline is designed to discard unwanted candidates, involving polyline simplification, curvature thresholding and multiscale Haar filtering. Ultimately, we use a priori knowledge derived from an initial 3D spine model to define search areas and select the final corner points. The framework was tested on 21 biplanar X-rays from scoliotic children. Corner positions are compared with manual selections by two experts. The results report a localization accuracy between 0.6 mm and 1.4 mm, comparable to manual expert variability.