Abstract | ||
---|---|---|
Recent developments in optical coherence tomography (OCT) have enabled wide-field and high-resolution angiographic imaging. However, generation of vascular contrast inherently requires long imaging times. In this work, we demonstrate a reconstruction technique based on sparse and redundant representations over trained dictionaries that can be used to reduce acquisition times and accurately reconstruct angiographic OCT projection images with full vascular detail from a smaller number of B-scans than conventionally required. Our technique for fast angiographic imaging through reconstruction (FAIR), shows excellent reconstruction quality while using only half of the number of B-scans and graceful quality degradation with further undersampling. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1109/ISBI.2011.5872454 | 2011 8TH IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING: FROM NANO TO MACRO |
Keywords | Field | DocType |
OCT, brain angiography, overcomplete dictionary learning, sparse representation | Iterative reconstruction,Computer vision,Optical coherence tomography,Pattern recognition,Computer science,Image representation,Sparse approximation,Undersampling,Coherence (physics),Pixel,Artificial intelligence,Optical tomography | Conference |
ISSN | Citations | PageRank |
1945-7928 | 0 | 0.34 |
References | Authors | |
2 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Ivana Stojanovic | 1 | 64 | 4.12 |
Nishant Mohan | 2 | 0 | 0.34 |
Benjamin J. Vakoc | 3 | 1 | 1.03 |
W. Clem Karl | 4 | 224 | 35.45 |