ColoSensus: A Spatiotemporal CNN-based Application for Gastrointestinal Disease Classification

DOI

10.2991/978-94-6463-684-0_21How to use a DOI?

Keywords

spatiotemporal convolutional neural network; gastrointestinal disease; hyperparameter tuning; colonoscopy; support decision tool

Abstract

The incidence cases of gastrointestinal diseases continue to rise in developing countries such as the Philippines. Some of these diseases such as colorectal cancer, ulcerative colitis, and colon polyps are a common sight during colonoscopy, a procedure used to detect abnormalities in the colon. Clinicians and medical students manually identifying gastrointestinal diseases may take time especially when lengthy videos are analyzed. Using models with spatiotemporal convolutional neural networks, colonoscopy videos instead of images can now be ingested by these models to predict gastrointestinal diseases. ColoSensus, an application that detects the gastrointestinal diseases mentioned, and uses one out of the 12 trained models from hyperparameter tuning, garnered a weighted average of 82% accuracy, 87% precision, 82% recall, and 79% F1 score. The performance of the current model could be further improved so that it could generalize better to new inputs and be finally used by clinicians as a support decision tool.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Seth Jared Saluta
AU  - Perlita Gasmen
PY  - 2025
DA  - 2025/04/30
TI  - ColoSensus: A Spatiotemporal CNN-based Application for Gastrointestinal Disease Classification
BT  - Proceedings of the  Workshop on Computation: Theory and Practice (WCTP 2024)
PB  - Atlantis Press
SP  - 332
EP  - 346
SN  - 2589-4900
UR  - https://doi.org/10.2991/978-94-6463-684-0_21
DO  - 10.2991/978-94-6463-684-0_21
ID  - Saluta2025
ER  -