Issue |
BIO Web Conf.
Volume 174, 2025
2025 7th International Conference on Biotechnology and Biomedicine (ICBB 2025)
|
|
---|---|---|
Article Number | 03010 | |
Number of page(s) | 7 | |
Section | Technologies and Methodologies in Biomedical Research | |
DOI | https://doi.org/10.1051/bioconf/202517403010 | |
Published online | 12 May 2025 |
A Benchmark for Multi-Task Evaluation of Pretrained Models in Medical Report Generation
1 School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China
2 School of Foreign Languages, Guangdong Polytechnic Normal University
* Corresponding author: a wangruix5@mail.sysu.edu.cn b lcx@gpnu.edu.cn
MRG for medical images has become increasingly important due to the growing workload of radiologists in hospitals. However, current studies in the MRG field predominantly focus on specific modal- ities or training foundation models with a notable lack of research evaluating the impact of pre-trained models on performance across different tasks, particularly their cross-task capabilities. This study introduces a novel benchmark for medical multi-task learning that encompasses four medical modalities: CT, X-ray, ultrasound, and pathology. We believe this benchmark can provide a robust comparative basis for future research in this field. More importantly, we conduct an in-depth analysis comparing modality-specific pre-trained models, natural domain pre-trained models, and medical foundation pre-trained models. Our findings indicate that medical foundation pre-trained models generally outperform other pre-trained models across all tasks, while natural domain pre-trained models exhibit superior performance in cross-modality tasks. Our source code is available at https://github.com/Reckless0/MT-Med.git.
© 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.