Segmentation of bones in magnetic resonance images of the wrist

Abstract

Purpose Rheumatoid arthritis (RA) is a disease characterized by progressive and irreversible destruction of bones and joints. According to current recommendations, magnetic resonance imaging (MRI) is used to asses three main signs of RA based on manual evaluation of MR images: synovitis, bone edema and bone erosions. The key feature of a future computer-assisted diagnostic system for evaluation RA lesions is accurate segmentation of 15 wrist bones. In the present paper, we focus on developing a wrist bones segmentation framework.Method The segmentation procedure consisted of three stages: segmentation of the distal parts of ulna and radius, segmentation of the proximal parts of metacarpal bones and segmentation of carpal bones. At every stage, markers of bones were determined first, using an atlas-based approach. Then, given markers of bones and a marker of background, a watershed from markers algorithm was applied to find the final segmentation.Results The MR data for 37 cases were analyzed. The automated segmentation results were compared with gold-standard manual segmentations using a few well-established metrics: area under ROC curve AUC, mean similarity MS and mean absolute distance MAD. The mean (standard deviation) values of AUC, MS and MAD were 0.97 (0.04), 0.93 (0.09) and 1.23 (0.28), respectively.Conclusion The results of the present study demonstrate that automated segmentation of wrist bones is feasible. The proposed algorithm can be the first stage for the detection of early lesions like bone edema or synovitis.

Fast automated segmentation of wrist bones in magnetic resonance images

“…There are a few studies focused on segmentation of eight carpal bones in CT [11,12] or high-field MR images [13], while RA diagnosis requires evaluating 15 wrist bones. Moreover, apart from our previous study [10], there is no wrist segmentation framework designed for low resolution low-field MR images. Low-field (0.2 T) extremity scanners are more popular primarily because they are less expensive, more comfortable for patients, and better accessible than high-field scanners.…”

“…Apart from our algorithm presented in [10] there is no comprehensive framework for automated segmentation of wrist bones in MR images designed for low resolution low-field MR images. There are a few studies focused on segmentation of eight carpal bones in CT [11,12] or high-field MR images [13], while RA diagnosis requires evaluating 15 wrist bones.…”

“…The algorithm presented in [10] was essentially based on registering atlas images to actual images. On the output of the algorithm described in [10] there were markers of all 15 wrist bones.…”

“…On the output of the algorithm described in [10] there were markers of all 15 wrist bones. The markers were then used by the watershed from markers algorithm to produce the final segmentation of bones.…”

“…A substantial part of the processing was performed in 3D space, resulting in a long computation time. In the present paper we present improved and faster segmentation framework for lowfield MR images as compared with [10]. The main effort of the present study was to improve the method of calculating markers used in watershed from markers algorithm.…”