UniUSNet: A Promptable Framework for Universal Ultrasound Disease Prediction and Tissue Segmentation
Lists
Only you see this
Abstract
Ultrasound is widely used in clinical practice due to its affordability, portability, and safety. However, current AI research often overlooks combined disease prediction and tissue segmentation. We propose UniUSNet, a universal framework for ultrasound image classification and segmentation. This model handles various ultrasound types, anatomical positions, and input formats, excelling in both segmentation and classification tasks. Trained on a comprehensive dataset with over 9.7K annotations from 7 distinct anatomical positions, our model matches state-of-the-art performance and surpasses single-dataset and ablated models. Zero-shot and fine-tuning experiments show strong generalization and adaptability with minimal fine-tuning. We plan to expand our dataset and refine the prompting mechanism, with model weights and code available at (https://github.com/Zehui-Lin/UniUSNet).
BibTeX
@inproceedings{lin2024uniusnet,
author = {Zehui Lin and Zhuoneng Zhang and Xindi Hu and Zhifan Gao and Xin Yang and Yue Sun and Dong Ni and Tao Tan},
title = {{UniUSNet: A Promptable Framework for Universal Ultrasound Disease Prediction and Tissue Segmentation}},
booktitle = {BIBM},
year = {2024},
doi = {10.1109/bibm62325.2024.10822429},
}Loading related content...