Saved in:
Bibliographic Details
Main Authors: Lin, Zehui, Zhang, Zhuoneng, Hu, Xindi, Gao, Zhifan, Yang, Xin, Sun, Yue, Ni, Dong, Tan, Tao
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2406.01154
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929480606416896
author Lin, Zehui
Zhang, Zhuoneng
Hu, Xindi
Gao, Zhifan
Yang, Xin
Sun, Yue
Ni, Dong
Tan, Tao
author_facet Lin, Zehui
Zhang, Zhuoneng
Hu, Xindi
Gao, Zhifan
Yang, Xin
Sun, Yue
Ni, Dong
Tan, Tao
contents 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).
format Preprint
id arxiv_https___arxiv_org_abs_2406_01154
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle UniUSNet: A Promptable Framework for Universal Ultrasound Disease Prediction and Tissue Segmentation
Lin, Zehui
Zhang, Zhuoneng
Hu, Xindi
Gao, Zhifan
Yang, Xin
Sun, Yue
Ni, Dong
Tan, Tao
Computer Vision and Pattern Recognition
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).
title UniUSNet: A Promptable Framework for Universal Ultrasound Disease Prediction and Tissue Segmentation
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2406.01154