Issue |
BIO Web Conf.
Volume 152, 2025
International Conference on Health and Biological Science (ICHBS 2024)
|
|
---|---|---|
Article Number | 01036 | |
Number of page(s) | 14 | |
Section | Dense Matter | |
DOI | https://doi.org/10.1051/bioconf/202515201036 | |
Published online | 20 January 2025 |
A systematic review of lightweight transformer models for medical image segmentation
1 Faculty of Social Sciences, Universitas Harapan Bangsa, Indonesia
2 Faculty of Health Sciences, Universitas Harapan Bangsa, Indonesia
3 Faculty of Information and Communication Technology, Universitas Teknikal Malaysia Melaka, Malaysia
* Corresponding author: iissmn@uhb.ac.id
Finding, assessing, and synthesizing studies on lightweight transformer models for medical picture segmentation is the goal of this SLR. Accuracy and efficiency in medical image processing and analysis are becoming more and more crucial as the amount of medical data increases. It has been demonstrated that lightweight transformer models have a lot of promise for producing precise and quick outcomes while using fewer computer resources. Several lightweight transformer models for medical picture segmentation have been examined in this paper. The findings demonstrate that, in comparison to traditional techniques, these models offer notable gains in medical image segmentation accuracy and efficiency. The need for improved generalization and testing on a wider range of datasets are among the difficulties noted. To overcome these obstacles and broaden the use of lightweight transformer models in diverse medical settings, more investigation is required. As a result, this review offers significant insights for future research and helpful advice for researchers and practitioners in creating and deploying lightweight transformer models for medical image segmentation.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.