Spinal cord gray matter segmentation using deep dilated convolutions

Christian S Perone,Evan Calabrese,Julien Cohen-Adad

doi:10.1038/s41598-018-24304-3

Abstract

Gray matter (GM) tissue changes have been associated with a wide range of neurological disorders and were recently found relevant as a biomarker for disability in amyotrophic lateral sclerosis. The ability to automatically segment the GM is, therefore, an important task for modern studies of the spinal cord. In this work, we devise a modern, simple and end-to-end fully-automated human spinal cord gray matter segmentation method using Deep Learning, that works both on in vivo and ex vivo MRI acquisitions. We evaluate our method against six independently developed methods on a GM segmentation challenge. We report state-of-the-art results in 8 out of 10 evaluation metrics as well as major network parameter reduction when compared to the traditional medical imaging architectures such as U-Nets.

Highlights

Gray matter (GM) and white matter (WM) tissue changes in the spinal cord (SC) have been linked to a large spectrum of neurological disorders[1]
We propose a new simple pipeline featuring an end-to-end learning approach for fully-automated spinal cord gray matter segmentation using a novel Deep Learning architecture based on the Atrous Spatial Pyramid Pooling (ASPP)[21,24], where we achieved state-of-the-art results on many metrics in an in vivo independent dataset evaluation
We can see that the Dice Loss is an excellent surrogate for the Dice Similarity Coefficient (DSC) and a surrogate for distance metrics, as we note that our model achieved state-of-the-art results on overlap metrics (i.e. DSC) and on distance and statistical metrics

Summary

Introduction

Gray matter (GM) and white matter (WM) tissue changes in the spinal cord (SC) have been linked to a large spectrum of neurological disorders[1]. Despite these difficulties, there have been major improvements in acquisition and analysis methods in recent years, making it possible to obtain reliable GM segmentations. The scientific community recently organized a collaboration effort called “Spinal Cord Gray Matter Segmentation Challenge” (SCGM Challenge)[6] to characterize the state-of-the-art and compare six independent developed methods[10,11,12,13,14,15] on a public available standard dataset created through the collaboration of four internationally recognized spinal cord imaging research groups (University College London, Polytechnique Montreal, University of Zurich and Vanderbilt University), providing a ground basis for method comparison that was previously unfeasible

Methods

Results

Conclusion