3D dense micro-block difference descriptor for gastrointestinal disease detection

M. Zhdanova; V. Voronin; O. Tokareva; E. Semenishchev; A. Zelensky; N. Gapon

doi:10.1117/12.2691162

27 November 2023 3D dense micro-block difference descriptor for gastrointestinal disease detection

M. Zhdanova, V. Voronin, O. Tokareva, E. Semenishchev, A. Zelensky, N. Gapon

Author Affiliations +

Proceedings Volume 12770, Optics in Health Care and Biomedical Optics XIII; 127703S (2023) https://doi.org/10.1117/12.2691162
Event: SPIE/COS Photonics Asia, 2023, Beijing, China

Conference Poster

Abstract

At present, medical endoscopy is the main procedure for exploring the internal cavities of the human body. Developing methods for integrating image processing and endoscopic visualization improves image quality and accurately identifies cancerous abnormalities. This paper aims to improve the efficiency detection of gastrointestinal disease detection in the endoscopic video. A recognition method is proposed, which is based on a 3-D binary difference of micro blocks and consists of the following steps: 1) a sequence of frames is divided into 3-D cuboids; 2) inside each cuboid, patches of different sizes are built, which are used to obtain volumetric local binary templates; 3) the Hamming distance is calculated between a randomly selected pair of cuboids within each patch of the video clip, which is sequentially written to a separate vector descriptor; 4) for recognition, the method of machine learning is used. Experimental studies show that disease detection is performed accurately on the test dataset (Kvasir).

(2023) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

M. Zhdanova, V. Voronin, O. Tokareva, E. Semenishchev, A. Zelensky, and N. Gapon "3D dense micro-block difference descriptor for gastrointestinal disease detection", Proc. SPIE 12770, Optics in Health Care and Biomedical Optics XIII, 127703S (27 November 2023); https://doi.org/10.1117/12.2691162

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