Combining convolutional neural networks and star convex cuts for fast whole spine vertebra segmentation in MRI. (August 2019)

• Record Type: Journal Article
• Authors: Rak, Marko; Steffen, Johannes; Meyer, Anneke; Hansen, Christian; Tönnies, Klaus–Dietz
• Is Part Of: Computer methods and programs in biomedicine. Volume 177(2019)
• Page Start: 47
• Page End: 56
• Publication Date: 2019-08
• Subjects: Magnetic resonance -- Spine analysis -- Vertebra segmentation -- Graph cuts -- Neural networks; Medicine -- Computer programs -- Periodicals; Biology -- Computer programs -- Periodicals; Computers -- Periodicals; Medicine -- Periodicals; Médecine -- Logiciels -- Périodiques; Biologie -- Logiciels -- Périodiques; Biology -- Computer programs; Medicine -- Computer programs; Periodicals; Electronic journals; 610.28
• DOI: 10.1016/j.cmpb.2019.05.003
• Languages: English
• ISSNs: 0169-2607

Abstract

Highlights: Average whole-spine Dice coefficients of 93.8%. Average lumbar Dice coefficients of 96.0%. Average run time per whole-spine image of 32.4 sec. Average run time per lumbar image of 6.3 sec. Performs equally well on T1- and T2-weighted sequences. Abstract: 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.