Share Email Print
cover

Proceedings Paper • new

Deep variational autoencoders for breast cancer tissue modeling and synthesis in SFDI
Author(s): Arturo Pardo; José M. López-Higuera; Brian W. Pogue; Olga M. Conde
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Extracting pathology information embedded within surface optical properties in Spatial Frequency Domain Imaging (SFDI) datasets is still a rather cumbersome nonlinear translation problem, mainly constrained by intrasample and interpatient variability, as well as dataset size. The β-variational autoencoder (β-VAE) is a rather novel dimensionality reduction technique where a tractable set of latent low-dimensional embeddings can be obtained from a given dataset. These embeddings can then be sampled to synthesize new data, providing further insight into pathology variability as well as differentiability in terms of optical properties. Its applications for data classification and breast margin delineation are also discussed.

Paper Details

Date Published: 11 July 2019
PDF: 3 pages
Proc. SPIE 11074, Diffuse Optical Spectroscopy and Imaging VII, 110741G (11 July 2019); doi: 10.1117/12.2527142
Show Author Affiliations
Arturo Pardo, Univ. de Cantabria (Spain)
Instituto de Investigacion Sanitaria Valdecilla (Spain)
José M. López-Higuera, Univ. de Cantabria (Spain)
Instituto de Investigacion Sanitaria Valdecilla (Spain)
Biomedical Research Networking Ctr. (Spain)
Brian W. Pogue, Thayer School of Engineering, Dartmouth College (United States)
Olga M. Conde, Univ. de Cantabria (Spain)
Instituto de Investigacion Sanitaria Valdecilla (Spain)
Biomedical Research Networking Ctr. (Spain)


Published in SPIE Proceedings Vol. 11074:
Diffuse Optical Spectroscopy and Imaging VII
Hamid Dehghani; Heidrun Wabnitz, Editor(s)

© SPIE. Terms of Use
Back to Top