Real-time deep-learning NICE classification and withdrawal-speed monitoring for colorectal endoscopy
This study is the first to integrate high-accuracy EfficientNet-based NICE classification, comprehensive explainability, and real-time withdrawal-speed monitoring into an ONNX-based multi-terminal system. The tool shows strong potential to improve optical diagnosis consistency for early colorectal cancer and to accelerate training of novice endoscopists.
Authors
- Zhijia Shen (ORCID: https://orcid.org/0000-0003-3148-3597)
- Kaijian Xia (ORCID: https://orcid.org/0000-0002-1650-9982)
- Limei Yin
- Ganhong Wang
- Xiaodan Xu (ORCID: https://orcid.org/0009-0005-1947-3339)
- Jian Chen (ORCID: https://orcid.org/0009-0001-9930-878X)
Institutions
- Nanjing University of Chinese Medicine (CN)
- Soochow University (TW)
- Soochow University (CN)
Publication Details
- Journal
- Digital Health
- Published
- 2025-05-01
- DOI
- https://doi.org/10.1177/20552076251393296
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 0.00