USFM: A Universal Ultrasound Foundation Model Generalized to Tasks and Organs towards Label Efficient Image Analysis

TL;DR

USFM is a universal ultrasound foundation model trained on a large, diverse dataset, capable of performing multiple tasks across organs with high label efficiency, addressing generality and data quality challenges in US image analysis.

Contribution

The paper introduces USFM, a large-scale multi-organ, multi-center ultrasound foundation model with novel spatial-frequency masked modeling and label-efficient training, advancing universal US image analysis.

Findings

USFM achieves robust performance with only 20% labeled data.

Extensive experiments validate USFM's universality across tasks and organs.

The model outperforms existing US analysis models in various benchmarks.

Abstract

Inadequate generality across different organs and tasks constrains the application of ultrasound (US) image analysis methods in smart healthcare. Building a universal US foundation model holds the potential to address these issues. Nevertheless, the development of such foundational models encounters intrinsic challenges in US analysis, i.e., insufficient databases, low quality, and ineffective features. In this paper, we present a universal US foundation model, named USFM, generalized to diverse tasks and organs towards label efficient US image analysis. First, a large-scale Multi-organ, Multi-center, and Multi-device US database was built, comprehensively containing over two million US images. Organ-balanced sampling was employed for unbiased learning. Then, USFM is self-supervised pre-trained on the sufficient US database. To extract the effective features from low-quality US images, we proposed a spatial-frequency dual masked image modeling method. A productive spatial noise addition-recovery approach was designed to learn meaningful US information robustly, while a novel frequency band-stop masking learning approach was also employed to extract complex, implicit grayscale distribution and textural variations. Extensive experiments were conducted on the various tasks of segmentation, classification, and image enhancement from diverse organs and diseases. Comparisons with representative US image analysis models illustrate the universality and effectiveness of USFM. The label efficiency experiments suggest the USFM obtains robust performance with only 20% annotation, laying the groundwork for the rapid development of US models in clinical practices.