Mixture-Based Bone Segmentation and Its Application in Computer Aided Diagnosis and Treatment Planning

摘要

The developmental dysplasia of the hip (DDH) is a congenital malformation of the acetabulum with different degrees. Leaving it partially treated or untreated is a major cause of disability. In this paper, we implemented a computer-aided system for the diagnosis and treatment planning of DDH. Instead of labeling each voxel with a unique label or tissue type, the percentage of different tissues within each voxel, which we call a mixture, was considered in establishing a maximum a posterior probability (MAP) framework for more accurate segmentation. A graphical module displayed the segmented bone in a 3D view to show the spatial relationship between acetabulum and femurs. This virtual image, together with quantitative measurement indexes, helps physicians make diagnosis. The system also provides physicians a virtual treatment planning on screen for acetabular and femoral osteotomy. It is currently under clinical trial on patient datasets.