Voon, Wingates and Hum, Yan Chai and Tee, Yee Kai and Yap, Wun-She and Lai, Khin Wee and Nisar, Humaira and Mokayed, Hamam (2024) IMAML-IDCG: Optimization-based meta-learning with ImageNet feature reusing for few-shot invasive ductal carcinoma grading. Expert Systems with Applications, 257. p. 124969. ISSN 0957-4174, DOI https://doi.org/10.1016/j.eswa.2024.124969.
Full text not available from this repository.Abstract
Model-Agnostic Meta-Learning (MAML) is a widely used few-shot learning (FSL) technique that reduces reliance on large, labeled datasets in deep learning for medical imaging analysis. However, MAML requires backpropagating through all feature layers for task adaptation, leading to suboptimal computational efficiency. We propose IMAML-IDCG (ImageNet Model-Agnostic Meta-Learning in Invasive Ductal Carcinoma Grading), which enhances computational efficiency for few-shot grading of Invasive Ductal Carcinoma (IDC) through three key techniques: (1) ImageNet feature reusing, (2) ImageNet partial freezing strategy, and (3) adaptive inner learning rate. IMAML-IDCG is initialized with ImageNet pre-trained weights. During the inner optimization loop, only the model's classifier head layer is optimized, leveraging prior ImageNet knowledge (ImageNet feature reusing) and employing an adaptive learning rate for improved task adaptation. In the outer optimization loop, IMAML-IDCG selectively fine-tunes the last few model layers to enhance efficiency and reduce overfitting (ImageNet partial freezing strategy). We evaluated IMAML-IDCG using the BreaKHis dataset (7,909 images) as the base dataset, and the BCHI (282 images) and PathoIDCG (3,744 images) datasets as the novel datasets. Our empirical results demonstrate that IMAML-IDCG outperforms MAML and other FSL methods in few-shot IDC grading tasks across various cross-magnification domain settings. Notably, IMAML-IDCG achieves a 14.64% improvement over MAML on the BCHI dataset and a 6.04% improvement on the PathoIDCG 40X dataset when meta-trained with the BreaKHis 40X dataset in the 3-way 5-shot scenario.
| Item Type: | Article |
|---|---|
| Funders: | Universiti Tunku Abdul Rahman Research Fund (IPSR/RMC/UTARRF/2022-C1/H01) |
| Uncontrolled Keywords: | Few-shot learning; Model-Agnostic Meta-Learning; ImageNet feature reusing; Medical imaging analysis; Invasive ductal carcinoma grading; Histopathological image classification |
| Subjects: | Q Science > QA Mathematics > QA75 Electronic computers. Computer science R Medicine > R Medicine (General) |
| Divisions: | Faculty of Engineering > Department of Biomedical Engineering |
| Depositing User: | Ms. Juhaida Abd Rahim |
| Date Deposited: | 10 Apr 2025 04:38 |
| Last Modified: | 10 Apr 2025 04:38 |
| URI: | http://eprints.um.edu.my/id/eprint/46673 |
Actions (login required)
 |
View Item |
