Advertisement

Medical & Biological Engineering & Computing

, Volume 49, Issue 12, pp 1413–1424 | Cite as

A fully automated human knee 3D MRI bone segmentation using the ray casting technique

  • Pierre Dodin
  • Johanne Martel-Pelletier
  • Jean-Pierre Pelletier
  • François Abram
Original Article

Abstract

This study aimed at developing a fully automated bone segmentation method for the human knee (femur and tibia) from magnetic resonance (MR) images. MR imaging was acquired on a whole body 1.5T scanner with a gradient echo fat suppressed sequence using an extremity coil. The method was based on the Ray Casting technique which relies on the decomposition of the MR images into multiple surface layers to localize the boundaries of the bones and several partial segmentation objects being automatically merged to obtain the final complete segmentation of the bones. Validation analyses were performed on 161 MR images from knee osteoarthritis patients, comparing the developed fully automated to a validated semi-automated segmentation method, using the average surface distance (ASD), volume correlation coefficient, and Dice similarity coefficient (DSC). For both femur and tibia, respectively, data showed excellent bone surface ASD (0.50 ± 0.12 mm; 0.37 ± 0.09 mm), average oriented distance between bone surfaces within the cartilage domain (0.02 ± 0.07 mm; −0.05 ± 0.10 mm), and bone volume DSC (0.94 ± 0.05; 0.92 ± 0.07). This newly developed fully automated bone segmentation method will enable large scale studies to be conducted within shorter time durations, as well as increase stability in the reading of pathological bone.

Keywords

Ray casting MRI 3D knee segmentation 

Notes

Acknowledgments

The authors would like to thank Yvan Ross for his involvement in the execution of the computation needed for the validation protocol, Françoys Labonté, PhD and François Guéritaud, PhD for their critical review and comments, and Virginia Wallis for her assistance with the manuscript preparation.

References

  1. 1.
    Berthiaume MJ, Raynauld JP, Martel-Pelletier J, Labonté F, Beaudoin G, Bloch DA, Choquette D, Haraoui B, Altman RD, Hochberg M, Meyer JM, Cline GA, Pelletier JP (2005) Meniscal tear and extrusion are strongly associated with the progression of knee osteoarthritis as assessed by quantitative magnetic resonance imaging. Ann Rheum Dis 64:556–563PubMedCrossRefGoogle Scholar
  2. 2.
    Dalvi R, Abugharbieh R, Wilson DC, Wilson D (2007) Multi-contrast MR for enhanced bone imaging and segmentation. Conf Proc IEEE Eng Med Biol Soc 2007:5620–5623PubMedGoogle Scholar
  3. 3.
    Ding C, Cicuttini F, Jones G (2007) Tibial subchondral bone size and knee cartilage defects: relevance to knee osteoarthritis. Osteoarthr Cartil 15:479–486PubMedCrossRefGoogle Scholar
  4. 4.
    Dogdas B, Shattuck D, Leahy RM (2002) Segmentation of the skull in 3D human MR images using mathematical morphology. Proceedings of the SPIE. Med Imaging 4684:1553–1562Google Scholar
  5. 5.
    Felson DT, Niu J, Guermazi A, Roemer F, Aliabadi P, Clancy M, Torner J, Lewis CE, Nevitt MC (2007) Correlation of the development of knee pain with enlarging bone marrow lesions on magnetic resonance imaging. Arthritis Rheum 56:2986–2992PubMedCrossRefGoogle Scholar
  6. 6.
    Folkesson J, Dam E, Olsen OF, Pettersen P, Christiansen C (2005) Automatic segmentation of the articular cartilage in knee MRI using a hierarchical multi-class classification scheme. Med Image Comput Comput Assist Interv 8:327–334PubMedGoogle Scholar
  7. 7.
    Folkesson J, Olsen OF, Pettersen P, Dam E, Christiansen C (2005) Combining binary classifiers for automatic cartilage segmentation in knee MRI. In: Liu Y, Jiang T, Zhang C (eds) Lecture notes in computer science. Springer-Verlag, Berlin, pp 230–239Google Scholar
  8. 8.
    Fripp J, Bourgeat P, Crozier S, Ourselin S (2007) Segmentation of the bones in MRI of the knee using phase, magnitude and shape information. Acad Radiol 10:1201–1208CrossRefGoogle Scholar
  9. 9.
    Fripp J, Crozier S, Warfield SK, Ourselin S (2007) Automatic segmentation of the bone and extraction of the bone-cartilage interface from magnetic resonance images of the knee. Phys Med Biol 52:1617–1631PubMedCrossRefGoogle Scholar
  10. 10.
    Fripp J, Warfield SK, Crozier S and Ourselin S. (2007) Automatic segmentation of articular cartilage in magnetic resonance images of the knee. Lecture notes in computer science, medical image computing and computer-assisted intervention 10:186–194Google Scholar
  11. 11.
    Fripp J, Crozier S, Warfield SK, Ourselin S (2010) Automatic segmentation and quantitative analysis of the articular cartilages from magnetic resonance images of the knee. IEEE Trans Med Imaging 29:55–64PubMedCrossRefGoogle Scholar
  12. 12.
    Gambini J, Mejail M, Jacobo J and Delrieux C. (2004) SAR image segmentation through B-spline deformable contours and fractal dimension. Proceedings of the international society for photogrammetry and remote sensing (ISPRS) July 15–23, Istanbul, TurkeyGoogle Scholar
  13. 13.
    Gerig G, Jomier M and Chakos M. (2001) VALMET: A new validation tool for assessing and improving 3D object segmentation. Proceedings of the international society and conference series on medical image computing and computer-assisted intervention 2208:516–523Google Scholar
  14. 14.
    Grau V, Mewes AUJ, Alcaniz M, Kikinis R, Warfield SK (2004) Improved watershed transform for medical image segmentation using prior information. IEEE Trans Med Imaging 23:447–457PubMedCrossRefGoogle Scholar
  15. 15.
    Hamarneh G, Li X (2009) Watershed segmentation using prior shape and appearance knowledge. Image Vis Comput 27:59–68CrossRefGoogle Scholar
  16. 16.
    Heinze P, Meister D, Kober R, Raczkowsky J, Worn H (2002) Atlas-based segmentation of pathological knee joints. Stud Health Technol Inform 85:198–203PubMedGoogle Scholar
  17. 17.
    Kapur T, Beardsley PA, Gibson SF, Grimson WEL and Wells WM. (1998) Model based segmentation of clinical knee MRI. Proceedings of the IEEE international workshop on model-based 3D image analysis, Bombay, India:97–106Google Scholar
  18. 18.
    Kauffmann C, Gravel P, Godbout B, Gravel A, Beaudoin G, Raynauld J-P, Martel-Pelletier J, Pelletier J-P, DeGuise JA (2003) Computer-aided method for quantification of cartilage thickness and volume changes using MRI: validation study using a synthetic model. IEEE Trans Biomed Eng 50:978–988PubMedCrossRefGoogle Scholar
  19. 19.
    Kubassova O, Boyle RD and Pyatnizkiy M. (2005) Bone segmentation in metacarpophalangeal MR data. Proceedings of the third international conference on advances in pattern recognition (ICAPR):726–735Google Scholar
  20. 20.
    Levoy M (1990) Efficient ray tracing of volume data. ACM Trans Gr 9:245–261CrossRefGoogle Scholar
  21. 21.
    Loeuille D, Chary-Valckenaere I, Champigneulle J, Rat AC, Toussaint F, Pinzano-Watrin A, Goebel JC, Mainard D, Blum A, Pourel J, Netter P, Gillet P (2005) Macroscopic and microscopic features of synovial membrane inflammation in the osteoarthritic knee: correlating magnetic resonance imaging findings with disease severity. Arthritis Rheum 52:3492–3501PubMedCrossRefGoogle Scholar
  22. 22.
    Lorenz C, von Berg J (2005) Fast automated object detection by recursive casting of search rays. Int Congr Ser 1281:230–235CrossRefGoogle Scholar
  23. 23.
    Lorigo LM, Faugeras O, Grimson WEL, Keriven R and Kikinis R. (1998) Segmentation of bone in clinical knee MRI using texture-based geodesic active contours. Lecture notes in computer science, proceedings of the first international conference on medical image computing and computer-assisted intervention 1496:1195–1204Google Scholar
  24. 24.
    Mayunga SD, Coleman DJ, Zhang Y (2007) A semi-automated approach for extracting buildings from QuickBird imagery applied to informal settlement mapping. Int J Remote Sens 28:2343–2357CrossRefGoogle Scholar
  25. 25.
    Otsu N (1979) A threshold selection method from gray-level histograms. IEEE Trans Syst Man Cybern 9:62–66CrossRefGoogle Scholar
  26. 26.
    Pelletier JP, Raynauld JP, Abram F, Haraoui B, Choquette D, Martel-Pelletier J (2008) A new non-invasive method to assess synovitis severity in relation to symptoms and cartilage volume loss in knee osteoarthritis patients using MRI. Osteoarthr Cartil 16(Suppl 3):S8–S13Google Scholar
  27. 27.
    Raynauld JP, Kauffmann C, Beaudoin G, Berthiaume MJ, de Guise JA, Bloch DA, Camacho F, Godbout B, Altman RD, Hochberg M, Meyer JM, Cline G, Pelletier JP, Martel-Pelletier J (2003) Reliability of a quantification imaging system using magnetic resonance images to measure cartilage thickness and volume in human normal and osteoarthritic knees. Osteoarthr Cartil 11:351–360PubMedCrossRefGoogle Scholar
  28. 28.
    Raynauld JP, Martel-Pelletier J, Berthiaume MJ, Labonté F, Beaudoin G, de Guise JA, Bloch DA, Choquette D, Haraoui B, Altman RD, Hochberg M, Meyer JM, Cline G, Pelletier JP (2004) Quantitative magnetic resonance imaging evaluation of knee osteoarthritis progression over two years and correlation with clinical symptoms and radiologic changes. Arthritis Rheum 50:476–487PubMedCrossRefGoogle Scholar
  29. 29.
    Raynauld JP, Martel-Pelletier J, Bias P, Laufer S, Haraoui B, Choquette D, Beaulieu AD, Abram F, Dorais M, Vignon E, Pelletier JP (2009) Protective effects of licofelone, a 5-lipoxygenase and cyclo-oxygenase inhibitor, versus naproxen on cartilage loss in knee osteoarthritis: a first multicentre clinical trial using quantitative MRI. Ann Rheum Dis 68:938–947PubMedCrossRefGoogle Scholar
  30. 30.
    Roemer FW, Frobell R, Hunter DJ, Crema MD, Fischer W, Bohndorf K, Guermazi A (2009) MRI-detected subchondral bone marrow signal alterations of the knee joint: terminology, imaging appearance, relevance and radiological differential diagnosis. Osteoarthr Cartil 17:1115–1131PubMedCrossRefGoogle Scholar
  31. 31.
    Wolf M, Welerich P, Niemann H (1997) Automatic segmentation and 3D-registration of a femoral bone in MR images of the knee. Pattern Recognit Image Anal 7:152–165Google Scholar
  32. 32.
    Yuille AL, Poggio TA (1986) Scaling theorems for zero crossings. IEEE Trans Pattern Anal Mach Intell 8:15–25PubMedCrossRefGoogle Scholar

Copyright information

© International Federation for Medical and Biological Engineering 2011

Authors and Affiliations

  • Pierre Dodin
    • 1
  • Johanne Martel-Pelletier
    • 2
  • Jean-Pierre Pelletier
    • 2
  • François Abram
    • 1
  1. 1.ArthroVisionMontrealCanada
  2. 2.Osteoarthritis Research UnitUniversity of Montreal Hospital Research Centre (CRCHUM), Notre-Dame HospitalMontrealCanada

Personalised recommendations