Top

International Journal of Computer Assisted Radiology and Surgery

Published in:

01-01-2015 | Original Article

A 3D active model framework for segmentation of proximal femur in MR images

Authors: Sadaf Arezoomand, Won-Sook Lee, Kawan S. Rakhra, Paul E. Beaulé

Published in: International Journal of Computer Assisted Radiology and Surgery | Issue 1/2015

Abstract

Purpose

Segmentation of osseous structures from clinical MR images is difficult due to acquisition artifacts and variable signal intensity of bones. Segmentation of femoral head is required for evaluation of hip joint abnormalities such as cam- type femoroacetabular impingement. A parametric deformable model (PDM) framework was developed for segmentation of 3D magnetic resonance (MR) images of the hip.

Method

A two-phase segmentation scheme was implemented: (i) Radial basis function interpolation was performed for semi-automatic piecewise registration of a proximal femur atlas model to an MRI scan region of interest. User-defined control points on the mesh model were registered to the corresponding landmarks on the image. (ii) An active PDM was then used for coarse-to-fine level segmentation. The segmentation technique was tested using 3D synthetic image data and clinical MR scans of the hip with varying resolution.

Results

The segmentation method provided a mean target overlap of 0.95 and misclassification error of 0.035 for the synthetic data. The average target overlap was 0.88, and misclassification error rate was 0.12 for the clinical MRI data sets.

Conclusion

A framework for segmentation of proximal femur in hip MRI scans was developed and tested. This method is robust to artifacts and intensity inhomogeneity and resistant to leakage into adjacent tissues. In comparison with slicewise segmentation techniques, this method features inter-slice consistency, which results in a smooth model of the proximal femur in hip MRI scans.

Rubin D (2013) Femoroacetabular impingement: fact, fiction, or fantasy? Am J Roentgenol 201(3):526–534CrossRef

Dimmick S, Stevens K, Brazier D, Anderson S (2013) Femoroacetabular impingement. Radiol Clinics N Am 51(3):337–352CrossRef

Sankar W, Matheney T, Zaltz I (2013) Femoroacetabular impingement: current concepts and controversies. Orthop Clinics N Am 44(4):575–589CrossRef

Genovese E, Spiga S, Vinci V, Aliprandi A, Di Pietto F, Coppolino F, Scialpi M, Giganti M (2013) Femoroacetabular impingement: role of imaging. Musculoskelet Surg 97:117–126CrossRef

Rakhra K (2012) ”MRI/CT in FAI”. In: Femoroacetabular impingement. Springer, Berlin, pp 41–55

Pham D, Xu C, Prince J (2000) Current methods in medical image segmentation. Annu Rev Biomed Eng 2:315–337PubMedCrossRef

Ababneh S, Prescott J, Gurcan M (2011) Automatic graph-cut based segmentation of bones from knee magnetic resonance images for osteoarthritis research. Med Image Anal 15(4):438–448PubMedCentralPubMedCrossRef

Hata Y, Kobashi S (2009) Fuzzy segmentation of endorrhachis in magnetic resonance images and its fuzzy maximum intensity projection. Appl Soft Comput 9(3):1156–1169CrossRef

Lorigo L, Faugeras O, Grimson W, Keriven R, Kikinis R (1998) Segmentation of bone in clinical knee MRI using texture-based geodesic active contours. Int Conf Med Image Comput Comput Assist Interv 1496:1195–1204

10.

Fripp J, Bourgeat P, Crozier S, Ourselin S (2007) Segmentation of the bones in MRIs of the knee using phase, magnitude, and shape information. Acad Radiol 14(10):1201–1208PubMedCrossRef

11.

Schmid J, Magnenat-Thalmann N (2008) MRI bone segmentation using deformable models and shape priors. Int Conf Med Image Comput Comput Assist Interv 11(1):119–126

12.

Seim H, Kainmueller D, Lamecker H, Bindernagel M, Malinowski J, Zachow S (2010) Model-based auto-segmentation of knee bones and cartilage in MRI data. In: MICCAI workshop medical image analysis for the clinic

13.

Carballido-Gamio J, Belongie S, Majumdar S (2004) Normalized cuts in 3-D for spinal MRI segmentation. IEEE Trans Med Imaging 23(1):36–44PubMedCrossRef

14.

Frangia A, Egmont-Petersenb M, Niessena W, Reiberb J, Viergever M (2001) Bone tumor segmentation from MR perfusion images with neural networks using multi-scale pharmacokinetic features. Image Vis Comput 19(9–10):679–690CrossRef

15.

Radeva P, Serrat J, Marti E (1995) A snake for model-based segmentation. In: International conference on computer vision

16.

Pardoa J, Cabelloa D, Herasb J (1997) A snake for model-based segmentation of biomedical images. Pattern Recognit Lett 18(14):1529–1538CrossRef

17.

Chesnaud C, Refregier P, Boulet V (1999) Statistical region snake-based segmentation adapted to different physical noise models. IEEE Trans Pattern Anal Mach Intell 21(11):1145–1157CrossRef

18.

Ji L, Yan H (2002) Robust topology-adaptive snakes for image segmentation. Image Vis Comput 20(2):147–164CrossRef

19.

Colliot O, Camara O, Bloch I (2006) Integration of fuzzy spatial relations in deformable models-application to brain MRI segmentation. Pattern Recognit 39(8):1401–1414CrossRef

20.

Kass M, Witkin A, Terzopoulos D (1998) Snakes: active contour models. Int J Comput Vis 1(4):321–331CrossRef

21.

Terzopoulos D, Platt J, Barr A, Fleischer K (1987) Elastically deformable models. In: Annual conference on computer graphics and interactive techniques

22.

Delingette H, Hebert M, Ikeuchi K (1991) ”Image segmentation and shape representation using deformable surfaces. In: IEEE computer society conference on computer vision and pattern recognition

23.

Cohen I, Ayache N, Cohen L (1991) Segmenting, visualizing and characterizing 3D anatomical structures with deformable surfaces. In: International conference of the IEEE engineering in medicine and biology society

24.

Cohen L, Cohen I (1993) Finite-element methods for active contour models and balloons for 2-D and 3-D images. IEEE Trans Pattern Anal Mach Intell 15(11):1131–1147

25.

McInerney T, Terzopoulos D (1995) Medical image segmentation using topologically adaptable surfaces. In: International conference on computer vision, virtual reality and robotics in medicine

26.

McInerney T, Terzopoulos D (1999) Topology adaptive deformable surfaces for medical image volume segmentation. IEEE Trans Med Imaging 18(10):840–850PubMedCrossRef

27.

Alfiansyah A, Ng K, Lamsudin R (2009) ”Deformable model for serial ultrasound images segmentation: application to computer assisted hip arthroplasty. In: International conference on biomedical engineering (IFMBE)

28.

Cohen L (1991) On active contour models and balloons. CVGIP Image Underst 53(2):211–218CrossRef

29.

Bakos M, Karch P, Dulova O (2012) Advanced initialization possibilities of active contours. In: IEEE international symposium on applied machine intelligence and informatics (SAMI)

30.

Rahnamayan S, Tizhoosh H, Salama M (2005) Automated snake initialization for the segmentation of the prostate in ultrasound images. Image Anal Recognit 3656:930–937

31.

Dalvi R, Abugharibeh R, Wilson D, Wilson D (2006) Highly-automated 3D segmentation of femoral bone from hip MRI. In: International society for magnetic resonance in medicine scientific meeting (ISMRM), Berlin

32.

Xu L, Lu C, Xu Y, Jia J (2011) Image smoothing via L0 gradient minimization. ACM Trans Graph (TOG) 30(6):174

33.

Delingette H (1999) General object reconstruction based on simplex meshes. Int J Comput Vis 32(2):111–146CrossRef

34.

Tohka J (2002) Surface extraction from volumetric images using deformable meshes: a comparative study. In: European conference on computer vision (ECCV)

35.

Banerjee P, Mclean C (2011) Femoroacetabular impingement: a review of diagnosis and management. Curr Rev Musculoskelet Med 4(1):23–32PubMedCentralPubMedCrossRef

36.

Nötzli H, Wyss T, Stoecklin C, Schmid M, Treiber K, Hodler J (2002) The contour of the femoral head-neck junction as a predictor for the risk of anterior impingement. J Bone Joint Surg 84(4):556–560CrossRef

37.

Torsney-Weir T, Saad A, Moller T, Hege H, Weber B, Verbavatz J, Bergner S (2011) Tuner: principled parameter finding for image segmentation algorithms using visual response surface exploration. IEEE Trans Vis Comput Graph 17(12):1892–1901PubMedCrossRef

Title: A 3D active model framework for segmentation of proximal femur in MR images
Authors: Sadaf Arezoomand
Won-Sook Lee
Kawan S. Rakhra
Paul E. Beaulé
Publication date: 01-01-2015
Publisher: Springer Berlin Heidelberg
Published in: International Journal of Computer Assisted Radiology and Surgery / Issue 1/2015
Print ISSN: 1861-6410
Electronic ISSN: 1861-6429
DOI: https://doi.org/10.1007/s11548-014-1125-6

At a glance: The ONWARDS insulin icodec trials

Springer Medicine

A 3D active model framework for segmentation of proximal femur in MR images

Abstract

Purpose

Method

Results

Conclusion

At a glance: The ONWARDS insulin icodec trials

Springer Medicine

Abstract

Purpose

Method

Results

Conclusion

Please log in to get access to this content

Other articles of this Issue 1/2015

3D lumbar spine intervertebral disc segmentation and compression simulation from MRI using shape-aware models

Wavelet denoising for quantum noise removal in chest digital tomosynthesis

Bivariate optimization of orthodontic mini-implant thread height and pitch

Precision of volumetric assessment of proximal femur microarchitecture from high-resolution 3T MRI

Fusion of coronary angiography and stress echocardiography for myocardial viability evaluation

Ameliorating slice gaps in multislice magnetic resonance images: an interpolation scheme