Rethinking Ultrasound Augmentation: A Physics-Inspired Approach

TL;DR

This paper introduces physics-inspired data augmentation techniques for ultrasound images to improve deep learning models in medical imaging, addressing artifacts and operator dependency issues.

Contribution

The authors propose novel physics-based transformations for ultrasound data augmentation, aligning with ultrasound physics to enhance model training.

Findings

Improved bone segmentation accuracy on spine ultrasound dataset.

Enhanced classification performance with physics-inspired augmentation.

Demonstrated effectiveness over traditional augmentation methods.

Abstract

Medical Ultrasound (US), despite its wide use, is characterized by artifacts and operator dependency. Those attributes hinder the gathering and utilization of US datasets for the training of Deep Neural Networks used for Computer-Assisted Intervention Systems. Data augmentation is commonly used to enhance model generalization and performance. However, common data augmentation techniques, such as affine transformations do not align with the physics of US and, when used carelessly can lead to unrealistic US images. To this end, we propose a set of physics-inspired transformations, including deformation, reverb and Signal-to-Noise Ratio, that we apply on US B-mode images for data augmentation. We evaluate our method on a new spine US dataset for the tasks of bone segmentation and classification.