A Review on Few-shot Learning for Medical Image Segmentation
- Authors
- Kim, Y.; Kang, D.; Mok, Y.; Kwon, S.; Paik, Joon Ki
- Issue Date
- 2023
- Publisher
- Institute of Electrical and Electronics Engineers Inc.
- Keywords
- few-shot learning; medical image; Meta-learning; MRI; semantic segmentation
- Citation
- 2023 International Conference on Electronics, Information, and Communication, ICEIC 2023
- Journal Title
- 2023 International Conference on Electronics, Information, and Communication, ICEIC 2023
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/67638
- DOI
- 10.1109/ICEIC57457.2023.10049899
- ISSN
- 0000-0000
- Abstract
- Deep-learning based approach has solved various medical imaging problems successfully. Since the lack of training data issues caused by patient privacy, the few-shot learning method has been studied widely. However, this issue still afflicts model performance even in few-shot learning methods. To solve this issue, it is important to quickly optimize the initial parameter values using a small amount of data. In addition, to utilize small data effectively, it is important to design the objective function for segmentation suitable for GT (Ground Truth) with few-shots. In this paper, we experiment with various algorithms using the MAML (Model Agnostic Meta-Learning) method. And we propose an optimal few-shot semantic segmentation network. The proposed method uses a gradient descent algorithm and optimizer parameter decomposition method to ensure fast convergence with fewer data. Experimental results show high performance and fast convergence using fewer datasets than conventional methods. © 2023 IEEE.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - Graduate School of Advanced Imaging Sciences, Multimedia and Film > Department of Imaging Science and Arts > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/67638)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.