Time series prediction for lung disease diagnosis and treatment optimization
APIL dynamically adjusts the learning complexity by introducing prior-informed pseudo-labels, anatomical masks, and contrastive consistency losses across views. It effectively combines weak supervision, domain adaptation, and uncertainty modeling, making it particularly adept at learning from sparse, noisy, or imbalanced datasets commonly found in clinical environments. Ultimately, this integrated framework offers a clinically meaningful, anatomically coherent, and data-efficient solution for next-generation pulmonary disease modeling.
Authors
- Mengpei Liu
- Jiaqi Ge (ORCID: https://orcid.org/0000-0002-6172-4411)
- Pengfei Du (ORCID: https://orcid.org/0000-0002-1096-8125)
- Litao Guo (ORCID: https://orcid.org/0000-0002-6611-0902)
- Yong Zhang (ORCID: https://orcid.org/0000-0002-3522-0885)
Institutions
- Ningbo University (CN)
- Jiangnan University (CN)
- Ningbo University of Technology (CN)
- Wuxi Fourth People's Hospital (CN)
- Ningbo College of Health Sciences (CN)
- Obstetrics and Gynecology Hospital of Fudan University (CN)
Publication Details
- Journal
- Frontiers in Medicine
- Published
- 2025-11-25
- DOI
- https://doi.org/10.3389/fmed.2025.1620462
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 0.00