Purpose:To develop an automated pipeline based on convolutional neural networks to segment lumbar intervertebral discs and characterize their biochemical composition using voxel-based relaxometry, and establish local associations with clinical measures of disability, muscle changes, and other symptoms of lower back pain. Methods: This work proposes a new methodology using MRI (n = 31, across the spectrum of disc degeneration) that combines deep learning-based segmentation, atlas-based registration, and statistical parametric mapping for voxel-based analysis of T 1ρ and T 2 relaxation time maps to characterize disc degeneration and its associated disability. Results: Across degenerative grades, the segmentation algorithm produced accurate, high-confidence segmentations of the lumbar discs in two independent data sets.Manually and automatically extracted mean disc T 1ρ and T 2 relaxation times were in high agreement for all discs with minimal bias. On a voxel-by-voxel basis, imagingbased degenerative grades were strongly negatively correlated with T 1ρ and T 2 , particularly in the nucleus. Stratifying patients by disability grades revealed significant differences in the relaxation maps between minimal/moderate versus severe disability: The average T 1ρ relaxation maps from the minimal/moderate disability group showed clear annulus nucleus distinction with a visible midline, whereas the severe disability group had lower average T 1ρ values with a homogeneous distribution. Conclusion: This work presented a scalable pipeline for fast, automated assessment of disc relaxation times, and voxel-based relaxometry that overcomes limitations of current region of interest-based analysis methods and may enable greater insights and associations between disc degeneration, disability, and lower back pain.
K E Y W O R D Sdeep learning, registration, relaxometry, segmentation, spine