A Supervised Approach Towards Segmentation of Clinical MRI for Automatic Lumbar Diagnosis
Lower back pain (LBP) is widely prevalent in people all over the world. It is associated with chronic pain and change in posture which negatively affects our quality of life. Automatic segmentation of intervertebral discs and the dural sac along with labeling of the discs from clinical lumbar MRI is the first step towards computer-aided diagnosis of lower back ailments like desiccation, herniation and stenosis. In this paper we propose a supervised approach to simultaneously segment the vertebra, intervertebral discs and the dural sac of clinical sagittal MRI using the neighborhood information of each pixel. Experiments on 53 cases out of which 40 were used for training and the rest for testing, show encouraging Dice Similarity Indices of 0.8483 and 0.8160 for the dural sac and intervertebral discs respectively.
KeywordsLower Back Pain Intervertebral Disc Class Label Automatic Segmentation Manual Segmentation
This research was funded in part by NSF Grants DBI \(0959870\) and CNS \(0855220\) and NYSTAR grants \(60701\) and \(41702\).
- 3.Bhole, C., Kompalli, S., Chaudhary, V.: Context-sensitive labeling of spinal structures in MRI images. In: The Proceedings of SPIE Medical Imaging (2009)Google Scholar
- 5.Cherry, D.K., Hing, E., Woodwell, D.A., Rechtsteiner, E.A.: National ambulatory medical care survey: 2006 summary. Nati. Health Stat. Rep. 3, 1–39 (2008)Google Scholar
- 6.Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. Int. Conf. Comput. Vis. Pattern Recogn. 2, 886–893 (2005)Google Scholar
- 7.Ghosh, S., Alomari, R.S., Chaudhary, V., Dhillon, G.: Computer-aided diagnosis for lumbar mri using heterogeneous classifiers. In: Proceedings of the 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI, pp. 1179–1182 (2011)Google Scholar
- 8.Ghosh, S., Malgireddy, M.R., Chaudhary, V., Dhillon, G.: A new approach to automatic disc localization in clinical lumbar MRI: Combining machine learning with heuristics. In: Proceedings of the 9th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI, pp. 114–117 (2012)Google Scholar
- 9.Horsfield, M., Sala, S., Neema, M., Absinta, M., Bakshi, A., Sormani, M., Rocca, M., Bakshi, R., Filippi, M.: Rapid semi-automatic segmentation of the spinal cord from magnetic resonance images: Application in multiple sclerosis. Neuroimage (2010)Google Scholar
- 10.Koh, J., Kim, T., Chaudhary, V., Dhillon, G.: Automatic segmentation of the spinal cord and the dural sac in lumbar mr images using gradient vector flow field. In: Proceedings of the 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC, pp. 2117–2120 (2010)Google Scholar
- 11.Koh, J., Scott, P.D., Chaudhary, V., Dhillon, G.: An automatic segmentation method of the spinal canal from clinical mr images based on an attention model and an active contour model. In: Proceedings of the 8th IEEE International Symposium on Biomedical Imaging: From Nano to Macro, ISBI, pp. 1467–1471 (2011)Google Scholar
- 12.Kundel, H.L.: Measurement of observer agreement. In: RSNA, pp. 303–308 (2003)Google Scholar
- 13.Oktay, A.B., Akgul, Y.S.: Localization of the lumbar discs using machine learning and exact probabilistic inference. In: MICCAI (3) (2011)Google Scholar
- 14.Schmidt, S., Kappes, J., Bergtholdt, M., Pekar, V., Dries, S., Bystrov, D., Schnoerr, C.: Spine detection and labeling using a parts-based graphical model. In: Proceedings of the 20th International Conference on Information Processing in Medical Imaging, IPMI, vol. 4584, pp. 122–133 (2007)Google Scholar