Monte Carlo investigation of deep learning tissue classification performance in OCT-based smart laser bone surgery (Conference Presentation)

Yakub Aqib Bayhaqi; Arsham Hamidi; Alexander Navarini; Philippe C. Cattin; Azhar Zam

doi:10.1117/12.2541604

9 March 2020 Monte Carlo investigation of deep learning tissue classification performance in OCT-based smart laser bone surgery (Conference Presentation)

Yakub Aqib Bayhaqi, Arsham Hamidi, Alexander Navarini, Philippe C. Cattin, Azhar Zam

Author Affiliations +

Proceedings Volume 11229, Advanced Biomedical and Clinical Diagnostic and Surgical Guidance Systems XVIII; 112290H (2020) https://doi.org/10.1117/12.2541604
Event: SPIE BiOS, 2020, San Francisco, California, United States

Abstract

Automatic tissue classification using optical coherence tomography (OCT) explores the possibility to control laser ablation in prevention for collateral damage of critical tissues. During ablation, tissue experience thermal dissipation which induces mechanical expansion and optical properties alteration. We reconstructed OCT images of bone, fat, and muscle tissues for pre and post ablation temperatures condition using Monte Carlo simulation. We trained a deep neural network to recognize tissue type based on reconstructed OCT images with pre-ablation temperature condition and tested it on post-ablation temprature condition. The reconstructed images show small changes in the tissue structure but do not significantly affect the performance of the classifier.

Conference Presentation

Citation Download Citation

Yakub Aqib Bayhaqi, Arsham Hamidi, Alexander Navarini, Philippe C. Cattin, and Azhar Zam "Monte Carlo investigation of deep learning tissue classification performance in OCT-based smart laser bone surgery (Conference Presentation)", Proc. SPIE 11229, Advanced Biomedical and Clinical Diagnostic and Surgical Guidance Systems XVIII, 112290H (9 March 2020); https://doi.org/10.1117/12.2541604

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