Combined surface and volume processing for fused joint segmentation
- 92 Downloads
Segmentation of rheumatoid joints from CT images is a complicated task. The pathological state of the joint results in a non-uniform density of the bone tissue, with holes and irregularities complicating the segmentation process. For the specific case of the shoulder joint, existing segmentation techniques often fail and lead to poor results. This paper describes a novel method for the segmentation of these joints.
Given a rough surface model of the shoulder, a loop that encircles the joint is extracted by calculating the minimum curvature of the surface model. The intersection points of this loop with the separate CT-slices are connected by means of a path search algorithm. Inaccurate sections are corrected by iteratively applying a Hough transform to the segmentation result.
As a qualitative measure we calculated the Dice coefficient and Hausdorff distances of the automatic segmentations and expert manual segmentations of CT-scans of ten severely deteriorated shoulder joints. For the humerus and scapula the median Dice coefficient was 98.9% with an interquartile range (IQR) of 95.8–99.4 and 98.5% (IQR 98.3–99.2%), respectively. The median Hausdorff distances were 3.06 mm (IQR 2.30–4.14) and 3.92 mm (IQR 1.96 –5.92 mm), respectively.
The routine satisfies the criterion of our particular application to accurately segment the shoulder joint in under 2 min. We conclude that combining surface curvature, limited user interaction and iterative refinement via a Hough transform forms a satisfactory approach for the segmentation of severely damaged arthritic shoulder joints.
KeywordsSegmentation Curvature Hough transform Rheumatoid joints Glenohumeral joint
Unable to display preview. Download preview PDF.
- 1.Aspert N, Santa-Cruz D, Ebrahimi T (2002) Mesh: measuring errors between surfaces using the hausdorff distance. In: Proceedings of the IEEE international conference on multimedia and expo I, pp 705–708Google Scholar
- 2.Botha CP (2005) Techniques and software architectures for medical visualisation and image processing. Ph.D. thesis, Delft University of Technology. URL: http://visualisation.tudelft.nl/People/CharlBotha/PhDThesis
- 4.Branzan-Albu A, Laurendeau D, Hèbert L, Moffet H, Dufour M, Moisan C (2004) Image-guided analysis of shoulder pathologies: modeling the 3d deformation of the subacromial space during arm flexion and abduction. In: Stephane Cotin DM (ed) International symposium on medical simulation (ISMS 2004). vol 1 of lecture notes in computer science. Springer, Cambridge, pp 193–202Google Scholar
- 6.Chambers EW, Èric Colin de Verdière, Erickson J, Lazarus F, Whittlesey K (2008) Splitting (complicated) surfaces is hard: computational geometry 41 (1–2), 94–110, special Issue on the 22nd European workshop on computational geometry (EuroCG), 22nd European workshop on computational geometryGoogle Scholar
- 7.Di Gioia III, MAM, Blendea S, Jaramaz B (2007) Surgical navigation for total hip arthroplasty. In: Callaghan JJ , Rosenberg AGHR (eds) The adult hip, 2nd edn. vol 2. Lippincott Williams & Wilkins, pp 1053–1059Google Scholar
- 10.Fleute M, Lavallee S (1998) Building a complete surface model from sparse data using statistical shape models: application to computer assisted knee surgery system. In: MICCAI. pp 879–887Google Scholar
- 12.Krekel P, Botha C, Valstar E, de Bruin P, Rozing P, Post F (2006) Interactive simulation and comparative visualisation of the bone-determined range of motion of the human shoulder. In: Schulze T, Horton G, Preim B, Schlechtweg S (eds) Proceedings of the simulation and visualization. SCS Publishing House, Erlangen, pp 275–288, best Paper AwardGoogle Scholar
- 16.Page DL, Sun Y, Koschan AF, Paik Paik J, Abidi MA (2002) Normal vector voting:crease detection and curvature estimation on large, noisy meshes. Graphical Models 64Google Scholar
- 17.Page DL, Koschan AF, Abidi MA (2003) Perception-based 3d triangle mesh segmentation using fast marching watersheds. cvpr 02, 27Google Scholar
- 21.Sato Y, Sasama T, Sugano N, Nakahodo K, Nishii T, Ozono K, Yonenobu K, Ochi T, Tamura S (2000) Intraoperative simulation and planning using a combined acetabular and femoral (caf) navigation system for total hip replacement. pp 1114–1125Google Scholar
- 23.Taubin G (1995) A signal processing approach to fair surface design. In: SIGGRAPH’95: Proceedings of the 22nd annual conference on Computer graphics and interactive techniques, ACM, New York, pp 351–358Google Scholar
- 24.Tremblay M-E, Branzan-Albu A, Laurendeau D, Hèbert L (2004) Integrating region and edge information for the automatic segmentation for interventional magnetic resonance images of the shoulder complex. In: 1st Canadian conference on computer and robot vision (CRV2004). vol 1. IEEE Computer Society, London, Ontario, pp 279–286Google Scholar
- 25.van der Glas M, Vos FM, Botha CP, Vossepoel AM (2002) Determination of position and radius of ball joints. In: Sonka M (ed) Proceedings of the SPIE international symposium on medical imaging. vol 4684—image processingGoogle Scholar