Multiple Sclerosis Lesion Segmentation Using Joint Label Fusion
This paper adapts the joint label fusion (JLF) multi-atlas image segmentation algorithm to the problem of multiple sclerosis (MS) lesion segmentation in multi-modal MRI. Conventionally, JLF requires a set of atlas images to be co-registered to the target image using deformable registration. However, given the variable spatial distribution of lesions in the brain, whole-brain deformable registration is unlikely to line up lesions between atlases and the target image. As a solution, we propose to first pre-segment the target image using an intensity regression based technique, yielding a set of “candidate” lesions. Each “candidate” lesion is then matched to a set of similar lesions in the atlas based on location and size; and deformable registration and JLF are applied at the level of the “candidate” lesion. The approach is evaluated on a dataset of 74 subjects with MS and shown to improve Dice similarity coefficient with reference manual segmentation by 12% over intensity regression technique.
This work was supported, in part, by the NIH grants NIBIB R01EB017255, NINDS R01NS082347, NINDS R01NS085211, NINDS R21NS093349, NINDS R01NS094456.
- 9.Mechrez, R., Goldberger, J., Greenspan, H.: Patch-based segmentation with spatial consistency: application to ms lesions in brain MRI. J. Biomed. Imaging 2016, 3 (2016)Google Scholar
- 10.Roy, S., He, Q., Carass, A., Jog, A., Cuzzocreo, J.L., Reich, D.S., Prince, J., Pham, D.: Example based lesion segmentation. In: SPIE Medical Imaging, p. 90341Y. International Society for Optics and Photonics (2014)Google Scholar
- 13.Sweeney, E.M., Shinohara, R.T., Shiee, N., Mateen, F.J., Chudgar, A.A., Cuzzocreo, J.L., Calabresi, P.A., Pham, D.L., Reich, D.S., Crainiceanu, C.M.: OASIS is automated statistical inference for segmentation, with applications to multiple sclerosis lesion segmentation in MRI. NeuroImage: Clin. 2, 402–413 (2013)CrossRefGoogle Scholar