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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Zhi, Zhang, Le
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918379245273088
author Chen, Zhi
Zhang, Le
author_facet Chen, Zhi
Zhang, Le
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2509_11108
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle UltraUPConvNet: A UPerNet- and ConvNeXt-Based Multi-Task Network for Ultrasound Tissue Segmentation and Disease Prediction
Chen, Zhi
Zhang, Le
Image and Video Processing
Computer Vision and Pattern Recognition
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
title UltraUPConvNet: A UPerNet- and ConvNeXt-Based Multi-Task Network for Ultrasound Tissue Segmentation and Disease Prediction
topic Image and Video Processing
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.11108