UltraUPConvNet: A UPerNet- and ConvNeXt-Based Multi-Task Network for Ultrasound Tissue Segmentation and Disease Prediction

Zhi Chen, Le Zhang
9/14/2025
eess.IVcs.CV

Official code: yyxl123/UltraUPConvNet (4 stars, last commit 2025-12-30).

Abstract

Ultrasound imaging is widely used in clinical practice due to its cost-effectiveness, mobility, and safety. However, current AI research often treats disease prediction and tissue segmentation as two separate tasks and their model requires substantial computational overhead. In such a situation, we introduce UltraUPConvNet, a computationally efficient universal framework designed for both ultrasound image classification and segmentation. Trained on a large-scale dataset containing more than 9,700 annotations across seven different anatomical regions, our model achieves state-of-the-art performance on certain datasets with lower computational overhead. Our model weights and codes are available at https://github.com/yyxl123/UltraUPConvNet

View on arXivView PDF

Code Implementations(1)

41Shell, PythonJul 23, 20259 months ago

Similar Papers

Cite this paper

@article{chen2025ultraupconvnet,
  title  = {UltraUPConvNet: A UPerNet- and ConvNeXt-Based Multi-Task Network for Ultrasound Tissue Segmentation and Disease Prediction},
  author = {Zhi Chen and Le Zhang},
  year   = {2025},
  eprint = {2509.11108},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2509.11108v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2509.11108.svg)](https://codeofpaper.com/paper/2509.11108)

Discussion