Vertebra localization and centroid detection from cervical radiographs

• DOI: 10.1109/c-code.2017.7918944
• Publication Date: 2017-05-04T20:31:38Z
• Authors: Anum Mehmood; M. Usman Akram; Anam Tariq
• Keywords: Centroid; Vertebra

Detection and localization of vertebra body plays a significant role in the diagnosis many spine disorders such as c-spine trauma their treatment including cervical surgeries. This requires great effort when one is dealing with poor contrast noisy set images like radiographs. paper aims to describe technique localize detect centroids c-spine. The presented takes radiograph enhance input image. Then edges enhanced image are detected. Next, modified generalized Hough Transform (GHT) applied on manually selected region interest (ROI) using mean model template As result voted points, localizing obtained fuzzy c means (FCM) clustering performed these points obtain five vertebrae (C <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sub> - C xmlns:xlink="http://www.w3.org/1999/xlink">7</sub> ). has been tested 150 cases publically available database `NHANES II' achieved 93.76% accuracy.