Reslicing Ultrasound Images for Data Augmentation and Vessel Reconstruction

TL;DR

This paper presents RESUS, a novel data augmentation method for ultrasound image segmentation that leverages 3D volume slicing to improve vessel reconstruction and segmentation accuracy.

Contribution

RESUS introduces a weak supervision augmentation technique using 3D volume slicing to enhance ultrasound image segmentation models.

Findings

Significant improvement in segmentation accuracy with RESUS

Qualitative enhancement in vessel reconstruction

Effective augmentation of ultrasound views constrained by physical limitations

Abstract

Robot-guided catheter insertion has the potential to deliver urgent medical care in situations where medical personnel are unavailable. However, this technique requires accurate and reliable segmentation of anatomical landmarks in the body. For the ultrasound imaging modality, obtaining large amounts of training data for a segmentation model is time-consuming and expensive. This paper introduces RESUS (RESlicing of UltraSound Images), a weak supervision data augmentation technique for ultrasound images based on slicing reconstructed 3D volumes from tracked 2D images. This technique allows us to generate views which cannot be easily obtained in vivo due to physical constraints of ultrasound imaging, and use these augmented ultrasound images to train a semantic segmentation model. We demonstrate that RESUS achieves statistically significant improvement over training with non-augmented images and highlight qualitative improvements through vessel reconstruction.