Title | ||
---|---|---|
Shared-boundary fusion for estimation of noisy multi-modality atherosclerotic plaque imagery |
Abstract | ||
---|---|---|
Our work focuses on applying boundary-preserving smoothing techniques to the fusion of multiple image modal- ities in an effort to improve image-based classification of atherosclerotic lesions. No single imaging modality has yet demonstrated the ability to reliably detect "vulnerable" le- sions. We present an approach for estimating multi-modality biomedical imagery when tissue classes are sharply delim- ited by boundaries. Our approach is based on the Mumford- Shah framework for edge-preserving smoothing. We ex- ploit this framework to fuse heterogeneous sensing modal- ities that image unrelated physicochemical parameters of a piecewise-homogeneous tissue field. We demonstrate this approach by fusing boundary field estimates from MR and CT atherosclerotic lesion imagery into a single estimated underlying tissue boundary field, while simultaneously es- timating the original imagery to better estimate tissue char- acteristics and structure. |
Year | DOI | Venue |
---|---|---|
2002 | 10.1109/ICIP.2002.1038929 | Image Processing. 2002. Proceedings. 2002 International Conference |
Keywords | Field | DocType |
biomedical MRI,cardiovascular system,computerised tomography,medical image processing,sensor fusion,smoothing methods,CT imagery,MR imagery,Mumford-Shah framework,atherosclerotic lesions,biomedical imagery,boundary-preserving smoothing techniques,edge-preserving smoothing,fusion,heterogeneous sensing modalities,image-based classification,multiple image modalities,noisy multi-modality atherosclerotic plaque imagery,physicochemical parameters,piecewise-homogeneous tissue field,shared-boundary fusion,tissue classes | Modalities,Computer vision,Pattern recognition,Computer science,Fusion,Sensor fusion,Smoothing,Artificial intelligence,Fuse (electrical) | Conference |
Volume | ISSN | Citations |
3 | 1522-4880 | 0 |
PageRank | References | Authors |
0.34 | 1 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Robert A. Weisenseel | 1 | 0 | 0.68 |
William Clement Karl | 2 | 79 | 13.41 |
Raymond C Chan | 3 | 52 | 7.35 |