Artificial Intelligence-Based Classification of Anatomical Sites in Esophagogastroduodenoscopy Images
Peng Yuan, Zhong-Hua Ma, Yan Yan, Shi-Jie Li, Jing Wang, Qi Wu · 2024
Read Artificial Intelligence-Based Classification of Anatomical Sites in Esophagogastroduodenoscopy Images by Peng Yuan, Zhong-Hua Ma, Yan Yan, Shi-Jie Li, Jing Wang, Qi Wu (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11649499.txt.
Description
Peng Yuan and five co-authors build an AI system to label anatomy in stomach scope images in a 2024 paper. A complete exam of the upper gut is needed to catch lesions, but doctors lack fast tools to confirm every region was viewed. The team trained a convolutional network on a large set of endoscopy images.
More than one hundred sixty thousand images across twenty seven anatomy classes were used. On a held out test set, the system reached accuracy above ninety nine percent, with high sensitivity and specificity. The authors say the tool could help operators check coverage during exams and standardize performance. That support could reduce missed spots in routine screening.
Catalog record
| CREATOR | Peng Yuan, Zhong-Hua Ma, Yan Yan, Shi-Jie Li, Jing Wang, Qi Wu |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 30 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |