Daniel Freedman

Google Research

Associated articles

TBME, Featured Articles
A Deep Learning Framework for Single-Sided Sound Speed Inversion in Medical Ultrasound
Abnormalities in the tissue’s mechanical properties and structure, as well as their spatial arrangement, are useful in disease diagnosis and monitoring of disease progression. To this end, ultrasound shear wave elastography is gaining traction as a useful diagnostic tool for... Read more
TBME,
A Deep Learning Framework for Single-Sided Sound Speed Inversion in Medical Ultrasound
Shear wave elastography constitutes the deployed state of the art for assessing mechanical properties of tissue, with numerous diagnostic applications. It is however limited to high-end hardware due to power requirements, is sensitive to sonographer and patient motion, and suffers from low frame rates. The longitudinal speed of sound maps enable an alternate approach for assessing the elastic properties of tissue. In this work, we present a single-sided speed of sound inversion solution using a fully convolutional deep neural network. We show that this presents a viable solution for inverting raw ultrasound channel data capable of interactive frame rates... Read more