Title | Multi-Learner Based Deep Meta-Learning for Few-Shot Medical Image Classification |
Author | |
Publication Years | 2023-01
|
DOI | |
Source Title | |
ISSN | 2168-2194
|
EISSN | 2168-2208
|
Volume | PPIssue:99Pages:1-11 |
Abstract | Few-shot learning (FSL) is promising in the field of medical image analysis due to high cost of establishing high-quality medical datasets. Many FSL approaches have been proposed in natural image scenes. However, present FSL methods are rarely evaluated on medical images and the FSL technology applicable to medical scenarios need to be further developed. Meta-learning has supplied an optional framework to address the challenging FSL setting. In this paper, we propose a novel multi-learner based FSL method for multiple medical image classification tasks, combining meta-learning with transfer-learning and metric-learning. Our designed model is composed of three learners, including auto-encoder, metric-learner and task-learner. In transfer-learning, all the learners are trained on the base classes. In the ensuing meta-learning, we leverage multiple novel tasks to fine-tune the metric-learner and task-learner in order to fast adapt to unseen tasks. Moreover, to further boost the learning efficiency of our model, we devised real-time data augmentation and dynamic Gaussian disturbance soft label (GDSL) scheme as effective generalization strategies of few-shot classification tasks. We have conducted experiments for three-class few-shot classification tasks on three newly-built challenging medical benchmarks, BLOOD, PATH and CHEST. Extensive comparisons to related works validated that our method achieved top performance both on homogeneous medical datasets and cross-domain datasets. |
Keywords | |
URL | [Source Record] |
Indexed By | |
Language | English
|
SUSTech Authorship | First
|
Scopus EID | 2-s2.0-85140750687
|
Data Source | Scopus
|
PDF url | https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9921265 |
Citation statistics |
Cited Times [WOS]:2
|
Document Type | Journal Article |
Identifier | http://kc.sustech.edu.cn/handle/2SGJ60CL/407147 |
Department | Department of Computer Science and Engineering |
Affiliation | 1.Department of Computer Science and Engineering, Southern University of Science and Technology, Shenzhen, China 2.Department of Biomedical Engineering, College of Future Technology, Peking University, Beijing, China |
First Author Affilication | Department of Computer Science and Engineering |
First Author's First Affilication | Department of Computer Science and Engineering |
Recommended Citation GB/T 7714 |
Jiang,Hongyang,Gao,Mengdi,Li,Heng,et al. Multi-Learner Based Deep Meta-Learning for Few-Shot Medical Image Classification[J]. IEEE Journal of Biomedical and Health Informatics,2023,PP(99):1-11.
|
APA |
Jiang,Hongyang,Gao,Mengdi,Li,Heng,Jin,Richu,Miao,Hanpei,&Liu,Jiang.(2023).Multi-Learner Based Deep Meta-Learning for Few-Shot Medical Image Classification.IEEE Journal of Biomedical and Health Informatics,PP(99),1-11.
|
MLA |
Jiang,Hongyang,et al."Multi-Learner Based Deep Meta-Learning for Few-Shot Medical Image Classification".IEEE Journal of Biomedical and Health Informatics PP.99(2023):1-11.
|
Files in This Item: | There are no files associated with this item. |
|
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment