Automated radiological grading of spinal MRI

Abstract

This paper describes a fully automatic system for obtaining the standard Pfirrmann degeneration grading of individual intervertebral spinal discs in T2 MRI scans. It involves detecting and labeling all the vertebrae in the scan and then learning a regression from the disc region to the grading. In developing the regression function we investigate a spectrum of support regions which involve differing degrees of segmentation of the scan: our intention is to ascertain to what extent segmentation is necessary or detrimental in obtaining robust and accurate measurements. The methods are assessed on a heterogeneous clinical dataset containing 1,710 Pfirrmanngraded discs, from 285 symptomatic back pain patients. We are able to predict the grade to±1 precision at 85.8%accuracy. Our novelmethod proposes newimage features that outperform previous features and utilizes techniques to improve robustness to MR imaging variations.