论文信息 - 3D Intervertebral Disc Segmentation from MRI Using Supervoxel-Based CRFs

3D Intervertebral Disc Segmentation from MRI Using Supervoxel-Based CRFs

Segmentation of intervertebral discs from three-dimensional magnetic resonance images is a challenging problem with numerous medical applications. In this paper we describe a fully automated segmentation method based on a conditional random field operating on supervoxels. A mean Dice score of \(90\pm 3\) % was obtained on data provided for the intervertebral disc localisation and segmentation challenge in conjunction with the 3rd MICCAI Workshop & Challenge on Computational Methods and Clinical Applications for Spine Imaging - MICCAI–CSI2015.

Hugo Hutt | Richard Everson | Judith Meakin

[1] Pascal Fua,et al. SLIC Superpixels Compared to State-of-the-Art Superpixel Methods , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2] David J. Field,et al. Emergence of simple-cell receptive field properties by learning a sparse code for natural images , 1996, Nature.

[3] Richard M. Everson,et al. Segmentation of Lumbar Vertebrae Slices from CT Images , 2015 .

[4] Chengwen Chu,et al. Localization and Segmentation of 3D Intervertebral Discs in MR Images by Data Driven Estimation , 2015, IEEE Transactions on Medical Imaging.

[5] Kilian Q. Weinberger,et al. Distance Metric Learning for Large Margin Nearest Neighbor Classification , 2005, NIPS.