Multi-task learning for predicting pulmonary nodule growth and follow-up volume
This study establishes that multi-task learning model of deformation-texture features significantly enhances pulmonary nodule growth prediction accuracy while providing radiologists with interpretable visualizations of progression patterns, demonstrating substantial potential for optimizing clinical surveillance protocols.
Authors
- Wenjuan Zhao (ORCID: https://orcid.org/0000-0003-2529-3404)
- Xiujuan Li
- Baosan Han
- Shengdong Nie
- Yang Chen
- Yue Jiang
- Yuangzhong Xie
Institutions
- Qingdao University (CN)
- University of Shanghai for Science and Technology (CN)
- XinHua Hospital (CN)
- The First People's Hospital of Shunde (CN)
- Affiliated Hospital of Qingdao University (CN)
- Taian City Central Hospital (CN)
Publication Details
- Journal
- Frontiers in Oncology
- Published
- 2026-02-03
- DOI
- https://doi.org/10.3389/fonc.2026.1677521
- Primary Topic
- Lung Cancer Diagnosis and Treatment
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China
- Shanghai Key Laboratory of Molecular Imaging