Multiscale distribution preserving autoencoders for plaque detection in intravascular optical coherence tomography
Roy AG, Conjeti S, Carlier SG, Houissa K, Koenig A, Dutta PK, Laine AF, Navab N, Katouzian A, Sheet D (2016)
Publication Type: Conference contribution
Publication year: 2016
Journal
Publisher: IEEE Computer Society
Book Volume: 2016-June
Pages Range: 1359-1362
Conference Proceedings Title: Proceedings - International Symposium on Biomedical Imaging
Event location: Prague, CZE
ISBN: 9781479923502
DOI: 10.1109/ISBI.2016.7493519
Abstract
Interventional cardiologists use intravascular imaging techniques like optical coherence tomography (OCT) as adjunct to angiography for detailed diagnosis of atherosclerosis. Each tissue type is associated with characteristic speckle intensity distribution, which forms the basis for tissue characterization (TC). Classical approaches follow statistical machine learning using apriori assumed speckle models, and are challenged by inability to discriminate high tissue heterogeneity. As a first of its kind approach, we solve this problem in absence of a well studied distribution, by learning the multiscale statistical distribution model of the data using our proposed distribution preserving (DP) autoencoder (AE) based neural network (NN). The learning rule introduces a scale importance parameter associated with error backpropagation. We have evaluated performance of DPAE vs. prior-art and AE (with L2 norm and cross-entropy cost function) to obtain LogLoss of 0.16, 0.28, 0.22, 0.53 respectively, and 93.6% average classification accuracy with DPAE predictions were judged to be clinically acceptable.
Involved external institutions
Hôpital Ambroise-Paré
France (FR)
Technische Universität München (TUM)
Germany (DE)
Indian Institute of Technology Kharagpur
India (IN)
Columbia University
United States (USA) (US)
France (FR)
Technische Universität München (TUM)
Germany (DE)
Indian Institute of Technology Kharagpur
India (IN)
Columbia University
United States (USA) (US)
How to cite
APA:
Roy, A.G., Conjeti, S., Carlier, S.G., Houissa, K., Koenig, A., Dutta, P.K.,... Sheet, D. (2016). Multiscale distribution preserving autoencoders for plaque detection in intravascular optical coherence tomography. In Proceedings - International Symposium on Biomedical Imaging (pp. 1359-1362). Prague, CZE: IEEE Computer Society.
MLA:
Roy, Abhijit Guha, et al. "Multiscale distribution preserving autoencoders for plaque detection in intravascular optical coherence tomography." Proceedings of the 2016 IEEE 13th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2016, Prague, CZE IEEE Computer Society, 2016. 1359-1362.
BibTeX: Download