Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group

Deep variational autoencoders for breast cancer tissue modeling and synthesis in SFDI

Not Accessible

Your library or personal account may give you access

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.

© 2019 SPIE/OSA

PDF Article
More Like This
Deep learning in photoacoustic tomography utilizing variational autoencoders

Teemu Sahlström and Tanja Tarvainen
1263108 European Conference on Biomedical Optics (ECBO) 2023

Ex Vivo Breast Cancer Tissue Classification Using Hyperspectral Endoscopy Imaging with Deep Learning

Shuyan Zhang, Shuwen Zeng, Ryan Ron Zee Tan, Wenjun Liao, and Malini Olivo
cl_p_3 The European Conference on Lasers and Electro-Optics (CLEO/Europe) 2023

Autoencoder Model for OFDM-based Optical Wireless Communication

Priti G. Pachpande, Monette H. Khadr, Hesham Hussien, Hany Elgala, and Dola Saha
SpT2E.3 Signal Processing in Photonic Communications (SPPCom) 2019

Select as filters


Select Topics Cancel
© Copyright 2024 | Optica Publishing Group. All Rights Reserved