Automated bone and joint-region segmentation in volumetric ultrasound

Ultrasound (US) is being increasingly used in the assessment of joints for disorders such as rheumatoid arthritis (RA). Pathologies related to RA in joints, manifest themselves commonly as changes in the bone (e.g. erosions) and the region enclosed by the joint-capsule (e.g. synovitis). Automated tools for detecting and segmenting such structures would help significantly towards objective and quantitative assessment of RA in joints. In this paper we present a novel method for automatic extraction of the 3D bone surface and segmentation of the joint-capsule region from volumetric (3D) scans of commonly affected joints such as the metacar-pophalangeal (MCP) and metatarsophalangeal (MTP) joints. We improve and extend the cost function proposed in [1] to 3D such that it is more robust to loss of acoustic intensity due to the surface normals facing away from the incident acoustic beam. The extracted bone coupled with a simple anatomical model of the MCP joint provides a coarse localization of the joint-capsule region. A probabilistic speckle model is then used to iteratively refine the capsule segmentation. We illustrate the performance of proposed methods through quantitative comparisons with expert annotations as well as qualitative results on over 30 scans obtained from 11 subjects.