Polarimentric differentiation of ex vivo colon samples complemented by machine-learning

Deyan Ivanov; Viktor Dremin; Tsanislava Genova; Alexander Bykov; Igor Meglinski; Tatiana Novikova; Razvigor Ossikovski

doi:10.1117/12.2615297

7 March 2022 Polarimentric differentiation of ex vivo colon samples complemented by machine-learning

Deyan Ivanov, Viktor Dremin, Tsanislava Genova, Alexander Bykov, Igor Meglinski, Tatiana Novikova, Razvigor Ossikovski

Author Affiliations +

Proceedings Volume PC11963, Polarized Light and Optical Angular Momentum for Biomedical Diagnostics 2022; PC1196307 (2022) https://doi.org/10.1117/12.2615297
Event: SPIE BiOS, 2022, San Francisco, California, United States

Abstract

We present a combination of Mueller matrix measurements (635 nm) of cancerous colon specimens and machine-learning approach. Physical realizability filtering and symmetric decomposition were used to extract polarimetric quantities, used as predictors in machine-learning algorithms. The results were visualized using various depolarization spaces. Principal component analysis was used to extract particular features from the model, logistic regression evaluated predictors with high likelihood for tumor detection, while random forest and support vector machines provided the best results for classification. Hence, polarimetry combined with machine-learning approach may increase the histopathology diagnostic accuracy.

Conference Presentation

Citation Download Citation

Deyan Ivanov, Viktor Dremin, Tsanislava Genova, Alexander Bykov, Igor Meglinski, Tatiana Novikova, and Razvigor Ossikovski "Polarimentric differentiation of ex vivo colon samples complemented by machine-learning", Proc. SPIE PC11963, Polarized Light and Optical Angular Momentum for Biomedical Diagnostics 2022, PC1196307 (7 March 2022); https://doi.org/10.1117/12.2615297

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