Koninklijke Philips Corporation N.V.

Anup Agarwal

David W Clark

David Hope Simpson

Earl M Canfield

Keith William Johnson

Liang Zhang

An ultrasound system with a deep learning neural network feature is used to eliminate haze artifacts in B mode images of the carotid artery by analysis of orthogonal information. In a described implementation the orthogonal information comprises the structural information of a B mode image and motion information of the same field of view as that of the B mode image. In another embodiment the neural network reduces haze artifacts by reducing TGC gain at the depth of artifacts.

Ultrasound system with deep learning network for image artifact identification and removal

An ultrasonic diagnostic imaging system produces audio Doppler from detected Doppler signals. The Doppler signals are detected in a band of frequencies which corresponds to the velocity of blood flow signals, and Doppler information is displayed based on the detected band of frequencies. The audio Doppler system produces Doppler audio in a frequency band which is shifted in pitch from the detected band of frequencies. The operator of the ultrasound system is provided with a user control by which the degree of pitch shifting can be controlled. The ultrasound system displays Doppler blood flow velocities referenced to a transmit Doppler frequency f, with the audio Doppler being shifted in pitch from the frequencies corresponding to the blood flow velocities.

Ultrasound blood flow Doppler audio with pitch shifting

Ultrasonic blood flow doppler audio with pitch shifting

Growing community of inventors

Mill Creek, WA, United States of America

Anup Agarwal