Challenge Description
In clinical practice, spine MRI is the preferred modality in diagnosis and treatment planning of various spinal pathologies such as disc herniation, slipped vertebra and so on. Automatic image analysis and quantification for the diagnosis of MR images of spine have drawn more and more attentions. Here the term image analysis refers to localization and segmentation of IVDs from MR images, which is a step prior to the quantification process. Localization means identifying the location of each IVD center, and segmentation produces the binary labeling of the image into disc/non-disc regions (from which a 3D surface of the disc boundary can be extracted if needed).
In this challenge, there are 7 IVDs to be localized and segmented from each image. Each team needs to submit both localization and segmentation results (see the image below for a schematic example). The final ranking will be calculated on both results.
In this challenge, there are 7 IVDs to be localized and segmented from each image. Each team needs to submit both localization and segmentation results (see the image below for a schematic example). The final ranking will be calculated on both results.
Reference
[1] Chen C, Belavy D, Yu W, Chu C, Armbrecht G, Bansmann M, Felsenberg D, Zheng G, "Localization and Segmentation of 3D Intervertebral Discs in MR Images by Data Driven Estimation", IEEE Trans Med Imaging, 2015 Aug;34(8):1719-29, DOI: 10.1109/TMI.2015.2403285. .
[2] Stern D, Likar B, Pernus F, Vrtovec T., "Automated detection of spinal centrelines, vertebral bodies and intervertebral discs in CT and MR images of lumbar spine". Phys Med Biol. 2010 Jan 7;55(1):247-64.
[3] Ben Ayed I, Punithakumar K, Garvin G, Romano W, Li S. "Graph cuts with invariant object-interaction priors: application to intervertebral disc segmentation". Inf Process Med Imaging. 2011;22:221-32.
[4] Neubert A, Fripp J, Engstrom C, Walker D, Weber MA, Schwarz R, Crozier S. "Three-dimensional morphological and signal intensity features for detection of intervertebral disc degeneration from magnetic resonance images". J Am Med Inform Assoc. 2013 Nov-Dec;20(6):1082-90.
[1] Chen C, Belavy D, Yu W, Chu C, Armbrecht G, Bansmann M, Felsenberg D, Zheng G, "Localization and Segmentation of 3D Intervertebral Discs in MR Images by Data Driven Estimation", IEEE Trans Med Imaging, 2015 Aug;34(8):1719-29, DOI: 10.1109/TMI.2015.2403285. .
[2] Stern D, Likar B, Pernus F, Vrtovec T., "Automated detection of spinal centrelines, vertebral bodies and intervertebral discs in CT and MR images of lumbar spine". Phys Med Biol. 2010 Jan 7;55(1):247-64.
[3] Ben Ayed I, Punithakumar K, Garvin G, Romano W, Li S. "Graph cuts with invariant object-interaction priors: application to intervertebral disc segmentation". Inf Process Med Imaging. 2011;22:221-32.
[4] Neubert A, Fripp J, Engstrom C, Walker D, Weber MA, Schwarz R, Crozier S. "Three-dimensional morphological and signal intensity features for detection of intervertebral disc degeneration from magnetic resonance images". J Am Med Inform Assoc. 2013 Nov-Dec;20(6):1082-90.
