Title: Automated lumbar-lordosis angle computation from digital X-ray image based on unsupervised learning
Authors: Raka Kundu; Amlan Chakrabarti; Prasanna Lenka
Addresses: A.K. Choudhury School of Information Technology, University of Calcutta, JD-3, JD Block, Sector-3, Salt Lake City, Kolkata-700098, West Bengal, India ' A.K. Choudhury School of Information Technology, University of Calcutta, JD-3, JD Block, Sector-3, Salt Lake City, Kolkata-700098, West Bengal, India ' Rehab. Engineering, Research and Development, National Institute for the Orthopaedically Handicapped, B.T. Road, Bonhoogly, Kolkata-700090, West Bengal, India
Abstract: Computation of lumbar-lordosis angle (LLA) of spine is a common measure for patients suffering from lower back pain (LBP). The angle formed between the extreme superior lumbar vertebra (L1) and the superior sacrum vertebra (S1) is the LLA. Based on Gaussian mixture model (GMM), an unsupervised automated image processing technique was developed for computation of LLA from spine sagittal X-ray image where lumbar-sacral curvature was identified and the curvature angle (Cobb's method) was measured to get the LLA. The objective of our proposed automated technique is to ease real-life issues in medical treatment. To the extent of our knowledge, the proposed technique for automated LLA angle computation from digital X-ray is the first of its kind. Validation of the technique was done on 22 X-ray images and promising results were achieved from the performed experiments.
Keywords: automated computer-aided detection and diagnosis; digital X-ray image; lumbar-lordosis Cobb's angle; lumbar-lordosis angle; Gaussian mixture model; GMM; expectation maximisation; lumbar-lordosis.
International Journal of Advanced Intelligence Paradigms, 2018 Vol.11 No.3/4, pp.235 - 255
Received: 03 Sep 2015
Accepted: 04 Jan 2016
Published online: 08 Oct 2018 *