Intensity-invariant scatterer density estimation for optical coherence tomography using deep convolutional neural network

Thitiya Seesan; Daisuke Oida; Kensuke Oikawa; Prathan Buranasiri; Yoshiaki Yasuno

doi:10.1117/12.2573236

15 June 2020 Intensity-invariant scatterer density estimation for optical coherence tomography using deep convolutional neural network

Thitiya Seesan, Daisuke Oida, Kensuke Oikawa, Prathan Buranasiri, Yoshiaki Yasuno

Author Affiliations +

Proceedings Volume 11521, Biomedical Imaging and Sensing Conference 2020; 115210Q (2020) https://doi.org/10.1117/12.2573236
Event: SPIE Technologies and Applications of Structured Light, 2020, Yokohama, Japan

Abstract

A convolutional neural networks (CNN) based scatterer density estimator for optical coherence tomography (OCT) is presented. In order to train the OCT, small patches of OCT speckle image were numerically generated. In this numerical image generation, the imaging parameters including the resolutions, probe power, signal-to-noise ratio, and scatterer density were randomly defined. So, the CNN was trained to estimate the imaging parameters from the generated OCT image patch. The results showed that our CNN estimator can estimate the parameters from the OCT speckle images.

Citation Download Citation

Thitiya Seesan, Daisuke Oida, Kensuke Oikawa, Prathan Buranasiri, and Yoshiaki Yasuno "Intensity-invariant scatterer density estimation for optical coherence tomography using deep convolutional neural network", Proc. SPIE 11521, Biomedical Imaging and Sensing Conference 2020, 115210Q (15 June 2020); https://doi.org/10.1117/12.2573236

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available