BROWSE
Detail
Journal Article
온디바이스 적용을 위한 다중 경량화 모델 기반 궤양성 대장염 중증도 예측 연구
- Authors
- 우동원, 김범휘, 정호영, 정성문
- Issue Date
- 2026-02
- Citation
- 한국정보통신학회논문지, v.30, no.2, pp.371-374
- ISSN
- 2234-4772
- Publisher
- 한국정보통신학회
- Language
- Korean
- Type
- Journal Article
- Abstract
- Ulcerative colitis (UC) severity is typically evaluated using the Ulcerative Colitis Endoscopic Index of Severity (UCEIS), but endoscopy is invasive and costly. To explore a non-invasive alternative, previous work proposed a Vision Transformer (ViT)-based model using stool images for binary classification of UCEIS scores. In this study, we extend this approach in two ways. First, to enable practical use in resource-limited and on-device settings, we implement lightweight models—MobileNetV2, EfficientNet-B0, ShuffleNetV2, and GhostNet—and compare their performance and efficiency against ViT. Second, we restructure UCEIS scores into three clinically relevant classes (0–1, 2–4, 5–8) for multi-class classification. This work demonstrates the feasibility and clinical value of stool image-based UC
- Keyword
- Ulcerative Colitis(UC), Deep learning, UCEIS, Light-weight model
- KSP Keywords
- Binary classification, Device settings, Image-based, Lightweight model, Non-invasive, Practical use, Ulcerative Colitis, deep learning(DL), multi-class classification
This work is distributed under the term of Creative Commons License (CCL)
(CC BY)
(CC BY)
