Adaptive segmentation of vertebral bodies from sagittal MR images based on local spatial information and Gaussian weighted chi-square distance

Combining convolutional neural networks and star convex cuts for fast whole spine vertebra segmentation in MRI

BACKGROUND AND OBJECTIVE

We propose an automatic approach for fast vertebral body segmentation in three-dimensional magnetic resonance images of the whole spine. Previous works are limited to the lower thoracolumbar section and often take minutes to compute, which is problematic in clinical routine, for study data sets with numerous subjects or when the cervical or upper thoracic spine is to be analyzed.

METHODS

We address these limitations by a novel graph cut formulation based on vertebra patches extracted along the spine. For each patch, our formulation incorporates appearance and shape information derived from a task-specific convolutional neural network as well as star-convexity constraints that ensure a topologically correct segmentation of each vertebra. When segmenting vertebrae individually, ambiguities will occur due to overlapping segmentations of adjacent vertebrae. We tackle this problem by novel non-overlap constraints between neighboring patches based on so-called encoding swaps. The latter allow us to obtain a globally optimal multi-label segmentation of all vertebrae in polynomial time.

RESULTS

We validated our approach on two data sets. The first contains T₁- and T₂-weighted whole spine images of 64 subjects with varying health conditions. The second comprises 23 T₂-weighted thoracolumbar images of young healthy adults and is publicly available. Our method yielded Dice coefficients of 93.8  ±  2.6% and 96.0  ±  1.0% for both data sets with a run time of 1.35  ±  0.08 s and 0.90  ±  0.03 s per vertebra on consumer hardware. A complete whole spine segmentation took 32.4 ± 1.92 s on average.

CONCLUSIONS

Our results are superior to those of previous works at a fraction of their run time, which illustrates the efficiency and effectiveness of our whole spine segmentation approach.

Quantitative magnetic resonance imaging of the lumbar intervertebral discs

Human lumbar spine is composed of multiple tissue components that serve to provide structural stability and proper nutrition. Conventional magnetic resonance (MR) imaging techniques have been useful for evaluation of IVD, but inadequate at imaging the discovertebral junction and ligamentous tissues due primarily to their short T2 nature. Ultrashort time to echo (UTE) MR techniques acquire sufficient MR signal from these short T2 tissues, thereby allowing direct and quantitative evaluation. This article discusses the anatomy of the lumbar spine, MR techniques available for morphologic and quantitative MR evaluation of long and short T2 tissues of the lumbar spine, considerations for T2 relaxation modeling and fitting, and existing and new techniques for spine image post-processing, focusing on segmentation. This article will be of interest to radiologic and orthopaedic researchers performing lumbar spine imaging.