Automatic virtual reconstruction of acetabular fractures using a statistical shape model

Purpose: Automatic virtual reconstruction of complex fractures would be helpful for pre-operative surgical planning. We developed a statistical shape model (SSM) which contains data of 200 intact 3D hemipelves. It allows for quantification of shape differences and is able to reconstruct abnormal shaped pelvises. We applied our SSM to reconstruct elementary and associate type acetabular fractures and assessed the reconstruction performance of the SSM, by comparing the reconstructed shape with the intact contralateral hemipelvis. Methods: In this retrospective diagnostic imaging study, we used our SSM to virtually reconstruct fractured hemipelves of eighty-three patients with an acetabular fracture. A root mean square error (RMSE) was computed between the reconstructed shape and intact contralateral shape for the whole hemipelvis and for regions relevant for plate-fitting. These plate-fitting relevant regions were defined as: (1) Iliopectineal line length and radius; (2) ischial body line length and radius; (3) acetabular diameter, (4) quadrilateral slope and (5) weight-bearing acetabular dome. Results: The median RMSE of the whole hemipelvis of the elementary type fractures was 2.2 (1.7–2.5) mm versus 3.2 (2.2–3.9) mm for the associate type fractures (p < 0.001). The median RMSE for the plate-fitting regions of elementary type fractures was 1.7 (1.4–2.1) mm versus 2.7 (2.0–4.1) mm for associate type fractures (p < 0.001). Conclusion: Using a statistical shape model allows for accurate virtual reconstructions of elementary and associate type acetabular fractures within a clinically acceptable range, especially within regions important for plate-fitting. SSM-based reconstructions can serve as a valuable tool for pre-operative planning in clinical practice, when a template of the contralateral hemipelvis is unavailable.