Article
Learning from Limited phenotype-level annotations for promoting multiple instance learning in endoscopic helicobacter pylori infection diagnosis.
Medical image analysis - 1 Nov 2026
Yi Zhenyu, Xu Jianwei, Hu Yue, Huang Liang, Zheng Zhilin, Jin Haifeng, Ma Panpan, Chen Tanzhou, Pan Jie, Ding Xiaoyun, Zhang Fangfang, Liu Jiang, Wang Xiaoteng, Xia Yingda, Lv Bin, Zhang Ling
Abstract excerpt
Helicobacter pylori (H. pylori) infection is a major risk factor for gastric carcinogenesis, requiring holistic endoscopic assessment of distributed mucosal abnormalities. While patient-level diagnostic labels are accessible, obtaining large-scale fine-grained annotations is constrained due to high inter-observer variability and the labor-intensive nature of the process. This naturally formulates the task as a...
Read the complete abstract on PubMedTopics
- Humans
- Multiple-Instance Learning Algorithms
- Helicobacter Infections
- Phenotype
- Helicobacter pylori