A computer-aided approach was proposed to reduce the variability in the Lenke classification. At the first step, endplate inclination of each vertebra on both the coronal and sagittal radiographs was measured by a computerized system. The Cobb angles of the proximal thoracic, the main thoracic, and the thoracolumbar/lumbar curves were then automatically calculated in the standing and side-bending coronal planes and the standing sagittal plane. A computerized algorithm automatically classified the spinal type. The classification results of 37 scoliotic patients by five observers showed that with the computer aid, the average interobserver and intraobserver kappa values were improved from 0.77 to 0.88 and from 0.68 to 0.83, respectively. This computerized tool can assist in the Lenke classification of scoliosis.

Download full-text PDF

Source
http://dx.doi.org/10.1109/EMBC.2013.6609658DOI Listing

Publication Analysis

Top Keywords

lenke classification
12
classification scoliotic
8
computerized
4
computerized lenke
4
classification
4
scoliotic spine
4
spine computer-aided
4
computer-aided approach
4
approach proposed
4
proposed reduce
4

Similar Publications

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!