UltraUPConvNet: A UPerNet- and ConvNeXt-Based Multi-Task Network for Ultrasound Tissue Segmentation and Disease Prediction
This addresses the need for efficient AI tools in clinical ultrasound imaging by combining tasks, but it is incremental as it builds on existing UPerNet and ConvNeXt architectures.
The authors tackled the problem of separate AI models for ultrasound disease prediction and tissue segmentation by introducing UltraUPConvNet, a computationally efficient multi-task framework that achieves state-of-the-art performance on certain datasets with lower computational overhead, trained on over 9,700 annotations across seven anatomical regions.
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