Augmenting Auto-context with Global Geometric Features for Spinal Cord Segmentation
Anatomical shape variations are typically difficult to model and parametric or hand-crafted models can lead to ill-fitting segmentations. This difficulty can be addressed with a framework like auto-context, that learns to jointly detect and regularize a segmentation. However, mis-segmentation can still occur when a desired structure, such as the spinal cord, has few locally distinct features. High-level knowledge at a global scale (e.g. an MRI contains a single connected spinal cord) is needed to regularize these candidate segmentations. To encode high-level knowledge, we propose to augment the auto-context framework with global geometric features extracted from the detected candidate shapes. Our classifier then learns these high-level rules and rejects falsely detected shapes. To validate our method we segment the spinal cords from 20 MRI volumes composed of patients with and without multiple sclerosis and demonstrate improvements in accuracy, speed, and manual effort required when compared to state-of-the-art methods.
KeywordsClass Label Principal Component Analysis Model Ground Truth Segmentation Decision Forest Candidate Segmentation
Unable to display preview. Download preview PDF.
- 1.Chen, M., Carass, A., Cuzzocreo, J., Bazin, P.L., Reich, D.S., Prince, J.L.: Topology preserving automatic segmentation of the spinal cord in magnetic resonance images. In: IEEE ISBI, pp. 1737–1740 (2011)Google Scholar
- 4.Kawahara, J., McIntosh, C., Tam, R., Hamarneh, G.: Globally optimal spinal cord segmentation using a minimal path in high dimensions. In: IEEE ISBI, pp. 836–839 (2013)Google Scholar
- 5.Kontschieder, P., Kohli, P., Shotton, J., Criminisi, A.: GeoF: Geodesic forests for learning coupled predictors. In: IEEE CVPR (2013)Google Scholar
- 7.McIntosh, C., Hamarneh, G., Toom, M., Tam, R.: Spinal cord segmentation for volume estimation in healthy and multiple sclerosis subjects using crawlers and minimal paths. In: IEEE HISB, pp. 25–31 (2011)Google Scholar