Saved in:
Bibliographic Details
Main Authors: She, Chaoyin, Lu, Ruifang, Chen, Lida, Wang, Wei, Huang, Qinghua
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.14977
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914480990978048
author She, Chaoyin
Lu, Ruifang
Chen, Lida
Wang, Wei
Huang, Qinghua
author_facet She, Chaoyin
Lu, Ruifang
Chen, Lida
Wang, Wei
Huang, Qinghua
contents Ultrasound imaging has become the preferred imaging modality for early cancer screening due to its advantages of non-ionizing radiation, low cost, and real-time imaging capabilities. However, conventional ultrasound diagnosis heavily relies on physician expertise, presenting challenges of high subjectivity and low diagnostic efficiency. Vision-language models (VLMs) offer promising solutions for this issue, but existing general-purpose models demonstrate limited knowledge in ultrasound medical tasks, with poor generalization in multi-organ lesion recognition and low efficiency across multi-task diagnostics. To address these limitations, we propose EchoVLM, a vision-language model specifically designed for ultrasound medical imaging. The model employs a Mixture of Experts (MoE) architecture trained on data spanning seven anatomical regions. This design enables the model to perform multiple tasks, including ultrasound report generation, diagnosis and visual question-answering (VQA). The experimental results demonstrated that EchoVLM achieved significant improvements of 10.15 and 4.77 points in BLEU-1 scores and ROUGE-1 scores respectively compared to Qwen2-VL on the ultrasound report generation task. These findings suggest that EchoVLM has substantial potential to enhance diagnostic accuracy in ultrasound imaging, thereby providing a viable technical solution for future clinical applications. Source code and model weights are available at https://github.com/Asunatan/EchoVLM.
format Preprint
id arxiv_https___arxiv_org_abs_2509_14977
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence
She, Chaoyin
Lu, Ruifang
Chen, Lida
Wang, Wei
Huang, Qinghua
Computer Vision and Pattern Recognition
Ultrasound imaging has become the preferred imaging modality for early cancer screening due to its advantages of non-ionizing radiation, low cost, and real-time imaging capabilities. However, conventional ultrasound diagnosis heavily relies on physician expertise, presenting challenges of high subjectivity and low diagnostic efficiency. Vision-language models (VLMs) offer promising solutions for this issue, but existing general-purpose models demonstrate limited knowledge in ultrasound medical tasks, with poor generalization in multi-organ lesion recognition and low efficiency across multi-task diagnostics. To address these limitations, we propose EchoVLM, a vision-language model specifically designed for ultrasound medical imaging. The model employs a Mixture of Experts (MoE) architecture trained on data spanning seven anatomical regions. This design enables the model to perform multiple tasks, including ultrasound report generation, diagnosis and visual question-answering (VQA). The experimental results demonstrated that EchoVLM achieved significant improvements of 10.15 and 4.77 points in BLEU-1 scores and ROUGE-1 scores respectively compared to Qwen2-VL on the ultrasound report generation task. These findings suggest that EchoVLM has substantial potential to enhance diagnostic accuracy in ultrasound imaging, thereby providing a viable technical solution for future clinical applications. Source code and model weights are available at https://github.com/Asunatan/EchoVLM.
title EchoVLM: Dynamic Mixture-of-Experts Vision-Language Model for Universal Ultrasound Intelligence
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.14977