MASCG: Multi-Atlas Segmentation Constrained Graph method for accurate segmentation of hip CT images

• Published in: Medical image analysis Vol. 26; no. 1; pp. 173 - 184
• Main Authors: Chu, Chengwen, Bai, Junjie, Wu, Xiaodong, Zheng, Guoyan
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 01.12.2015
• Subjects: Algorithms; Arthrography - methods; Graph cut; Graph search; Hip Joint - diagnostic imaging; Humans; Multi-atlas; Pattern Recognition, Automated - methods; Radiographic Image Enhancement - methods; Radiographic Image Interpretation, Computer-Assisted - methods; Reproducibility of Results; Segmentation; Sensitivity and Specificity; Subtraction Technique; Tomography, X-Ray Computed - methods; Multi-atlas; CT; Segmentation; Graph cut; Graph search
• ISSN: 1361-8415; 1361-8423; 1361-8423
• DOI: 10.1016/j.media.2015.08.011

•A Multi-Atlas Segmentation Constrained Graph (MASCG) method combining a multi-atlas mesh fusion algorithm, a bone sheetness based multi-label graph cut algorithm with a graph cut constrained graph search algorithm for fully automatic segmentation of hip CT images.•Overall hip CT segmentation with average accuracy of about 0.30 mm, comparable with the state of the art.•Hip joint region segmentation with average accuracy of 0.16–0.21 mm, better than the state of the art.•Preservation of hip joint space as demonstrated on 30 hip CT data (60 joints). [Display omitted] This paper addresses the issue of fully automatic segmentation of a hip CT image with the goal to preserve the joint structure for clinical applications in hip disease diagnosis and treatment. For this purpose, we propose a Multi-Atlas Segmentation Constrained Graph (MASCG) method. The MASCG method uses multi-atlas based mesh fusion results to initialize a bone sheetness based multi-label graph cut for an accurate hip CT segmentation which has the inherent advantage of automatic separation of the pelvic region from the bilateral proximal femoral regions. We then introduce a graph cut constrained graph search algorithm to further improve the segmentation accuracy around the bilateral hip joint regions. Taking manual segmentation as the ground truth, we evaluated the present approach on 30 hip CT images (60 hips) with a 15-fold cross validation. When the present approach was compared to manual segmentation, an average surface distance error of 0.30 mm, 0.29 mm, and 0.30 mm was found for the pelvis, the left proximal femur, and the right proximal femur, respectively. A further look at the bilateral hip joint regions demonstrated an average surface distance error of 0.16 mm, 0.21 mm and 0.20 mm for the acetabulum, the left femoral head, and the right femoral head, respectively.