UniUSNet: A Promptable Framework for Universal Ultrasound Disease Prediction and Tissue Segmentation
This addresses the need for versatile AI tools in clinical ultrasound practice, though it appears incremental by building on existing methods for a specific domain.
The authors tackled the problem of combined disease prediction and tissue segmentation in ultrasound imaging by proposing UniUSNet, a universal framework that matches state-of-the-art performance and surpasses single-dataset models, as demonstrated on a dataset with over 9.7K annotations from 7 anatomical positions.
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).