UniUSNet: A Promptable Framework for Universal Ultrasound Disease Prediction and Tissue Segmentation

TL;DR

UniUSNet is a versatile ultrasound AI framework capable of disease prediction and tissue segmentation across various types and positions, demonstrating strong generalization and state-of-the-art performance.

Contribution

The paper introduces UniUSNet, a universal, promptable framework for ultrasound image classification and segmentation that handles diverse data and tasks with high accuracy.

Findings

Matches state-of-the-art performance on comprehensive dataset

Shows strong zero-shot and fine-tuning generalization

Outperforms single-dataset and ablated models

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).