A Convolutional Approach to Vertebrae Detection and Labelling in Whole Spine MRI

TL;DR

This paper introduces a convolutional method for accurate vertebrae detection and labelling in whole spine MRI scans, enabling automated clinical assessments like scoliosis detection with high accuracy.

Contribution

A novel convolutional approach combining vector fields and image translation for versatile, high-accuracy vertebrae detection and labelling across various spine MRI sequences.

Findings

98.1% detection rate on clinical datasets

96.5% vertebral identification accuracy

Effective for scoliosis detection in clinical practice

Abstract

We propose a novel convolutional method for the detection and identification of vertebrae in whole spine MRIs. This involves using a learnt vector field to group detected vertebrae corners together into individual vertebral bodies and convolutional image-to-image translation followed by beam search to label vertebral levels in a self-consistent manner. The method can be applied without modification to lumbar, cervical and thoracic-only scans across a range of different MR sequences. The resulting system achieves 98.1% detection rate and 96.5% identification rate on a challenging clinical dataset of whole spine scans and matches or exceeds the performance of previous systems on lumbar-only scans. Finally, we demonstrate the clinical applicability of this method, using it for automated scoliosis detection in both lumbar and whole spine MR scans.