How to pick an optimal pre-processing technique to reduce non-tissue specific variations in hyperspectral imaging

Mark Witteveen; Maurice C. G. Aalders; Ton G. van Leeuwen; Henricus J. C. M. Sterenborg; Theo J. M. Ruers; Anouk L. Post

doi:10.1117/12.2608746

7 March 2022 How to pick an optimal pre-processing technique to reduce non-tissue specific variations in hyperspectral imaging

Mark Witteveen, Maurice C. G. Aalders, Ton G. van Leeuwen, Henricus J. C. M. Sterenborg, Theo J. M. Ruers, Anouk L. Post

Author Affiliations +

Proceedings Volume PC11944, Multiscale Imaging and Spectroscopy III; PC119440A (2022) https://doi.org/10.1117/12.2608746
Event: SPIE BiOS, 2022, San Francisco, California, United States

Abstract

In hyperspectral imaging, surface reflections and height differences within tissue samples add variations to spectra which are not related to tissue composition. To improve diagnostic accuracy, several pre-processing techniques are used to reduce these variations. However, currently a framework is lacking to choose an optimal pre-processing algorithm technique for a clinical application. We identified 8 pre-processing algorithms and investigated on synthetic data how well each algorithm reduces variations related to surface reflections and height differences and keeps variations between spectra related to differences in tissue optical properties. We demonstrate the use of our framework on colon and breast cancer tissue.

Conference Presentation

Citation Download Citation

Mark Witteveen, Maurice C. G. Aalders, Ton G. van Leeuwen, Henricus J. C. M. Sterenborg, Theo J. M. Ruers, and Anouk L. Post "How to pick an optimal pre-processing technique to reduce non-tissue specific variations in hyperspectral imaging", Proc. SPIE PC11944, Multiscale Imaging and Spectroscopy III, PC119440A (7 March 2022); https://doi.org/10.1117/12.2608746

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