Segmenting Bones Using Statistical Shape Modeling and Local Template Matching

Accurate bone segmentation is necessary to develop chair-side manufacturing of implants based on additive manufacturing. Various automatic segmentation techniques have been proposed to streamline the process (e.g. graph-cut or deep-learning), but these techniques do not provide anatomical correspondences during the segmentation process, which makes exploitation of segmentation more difficult to predict missing bone parts in case of fracture or its premorbid shape for degenerative diseases. Bone segmentation using active shape model (ASM) would provide anatomical correspondences. However, this technique is error prone for thin structures, such as the scapular blade or orbital walls. Therefore, we developed a new method relying on shape model fitting and local correction relying on image similarities. The method was evaluated on three challenging anatomical locations: (i) healthy and osteoarthritic scapulae, (ii) orbital bones, and (iii) mandible. On average, results were accurate with surface distance of about 0.5 mm and average Dice coefficients above 90%. This approach was able to separate joint bone surfaces, even in challenging pathological situations such as osteoarthritis. Since anatomical correspondences are propagated during segmentation, the method can directly provide anatomical measurements, define personalized cutting guides, or determine the bone regions to be used to contour patient-specific implants.