A fully automated method of associating axial slices with a disc based on labeling of multi-protocol lumbar MRI

Abstract

In a clinical setting, sagittal magnetic resonance imaging (MRI) slices along with axial MRI slices are commonly examined to diagnose lower lumbar disorders. Alongside, scan lines by projecting axial slices onto sagittal slices are provided to show the relationship about which axial slice is associated with a particular disc, resulting in better diagnosing disc-related disorders by a radiologist. In this paper, we propose a method to accurately associate an axial MRI with the particular intervertebral disc in a pre-labeled sagittal lumbar region MRI. A statistical distance prior from multi-protocol MR images of 68 patients is used in labeling process to accommodate the variability of the distance among patients of different ages and gender. Experiments with 93 patient data including 465 lumbar discs show that our method can assign the class membership to scan lines with over 92% accuracy.