Abstract | ||
---|---|---|
Automatic and accurate detection of white matter lesions is a significant step toward understanding the progression of many diseases, like Alzheimer's disease or multiple sclerosis. Multi-modal MR images are often used to segment T-2 white matter lesions that can represent regions of demyelination or ischemia, Sonic automated lesion segmentation methods describe the lesion intensities using generative models, and then classify the lesions with some combination of heuristics and cost minimization. in contrast, we propose a patch-based method, in which lesions are found using examples from an atlas containing multi-modal MR images and corresponding manual delineations of lesions. Patches from subject ME images are matched to patches from the atlas and lesion memberships are found based on patch similarity weights. We experiment on 43 subjects with MS, whose scans show various levels of lesion-load. We demonstrate significant improvement in Dice coefficient and total lesion volume compared to a state of the art model-based lesion segmentation method, indicating more accurate delineation of lesions. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1117/12.2043917 | Proceedings of SPIE |
Keywords | Field | DocType |
magnetic resonance imaging,MRI,lesion segmentation,MS,patches | Computer vision,Lesion,Segmentation,Sørensen–Dice coefficient,Multiple sclerosis,Artificial intelligence,Hyperintensity,Lesion segmentation,Magnetic resonance imaging,Physics | Conference |
Volume | ISSN | Citations |
9034 | 0277-786X | 12 |
PageRank | References | Authors |
0.58 | 13 | 8 |
Name | Order | Citations | PageRank |
---|---|---|---|
Snehashis Roy | 1 | 239 | 23.70 |
Qing He | 2 | 46 | 4.62 |
Aaron Carass | 3 | 383 | 43.15 |
Amod Jog | 4 | 174 | 13.09 |
Jennifer L Cuzzocreo | 5 | 103 | 5.03 |
Daniel S. Reich | 6 | 209 | 15.94 |
Jerry L. Prince | 7 | 4990 | 488.42 |
dzung pham | 8 | 12 | 0.58 |