Thyroid-Specialized Version
This repository provides a thyroid-specialized version of EchoVLM, designed for thyroid ultrasound image understanding and thyroid-specific vision-language tasks. It is built on the Qwen framework and trained with the chaoyinshe/EchoVLM-Thyroid dataset.
Please note that the chaoyinshe/EchoVLM-Thyroid dataset is currently private. It will be open-sourced upon acceptance of the paper, together with the corresponding benchmark.
Relevant technical reports and comprehensive technical documentation for this thyroid-specific variant are coming soon.
The desensitization tool is available at Ultrasonic_image_desensitization.
For usage, please refer to: Qwen3.5-9B
Citation
If you use this tool in your research or project, please cite our EchoVLM paper:
@misc{she2026echovlmdynamicmixtureofexpertsvisionlanguage,
title={EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence},
author={Chaoyin She and Ruifang Lu and Lida Chen and Wei Wang and Qinghua Huang},
year={2026},
eprint={2509.14977},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2509.14977},
}