Branched Convolutional Neural Networks for Receiver Channel Recovery in High-Frame-Rate Sparse-Array Ultrasound Imaging
Open Access
- 2 April 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
- Vol. 71 (5) , 558-571
Abstract
For high-frame-rate ultrasound imaging, it remains challenging to implement on compact systems as a sparse imaging configuration with limited array channels. One key issue is that the resulting image quality is known to be mediocre not only because unfocused plane-wave excitations are used, but also because grating lobes would emerge in sparse array configurations. In this paper, we present the design and use of a new channel recovery framework to infer full-array plane-wave channel datasets for periodically sparse arrays that operate with as few as one-quarter of the full-array aperture. This framework is based on a branched encoder-decoder convolutional neural network (CNN) architecture, which was trained using full-array plane-wave channel data collected from human carotid arteries (59,864 training acquisitions; 5 MHz imaging frequency; 20 MHz sampling rate; plane-wave steering angles between -15° and 15° in 1° increments). Three branched encoder-decoder CNNs were separately trained to recover missing channels after differing degrees of channel-wise downsampling (2, 3, and 4-times). The framework’s performance was tested on full-array and downsampled plane-wave channel data acquired from an in vitro point target, human carotid arteries, and human brachioradialis muscle. Results show that, when inferred full-array plane-wave channel data was used for beamforming, spatial aliasing artifacts in the B-mode images were suppressed for all degrees of channel downsampling. Also, the image contrast was enhanced comparing to B-mode images obtained from beamforming with downsampled channel data. When the recovery framework was implemented on an RTX-2080 GPU, the three investigated degrees of downsampling all achieved the same inference time of 4 ms. Overall, the proposed framework shows promise in enhancing the quality of high-frame-rate ultrasound images generated using a sparse-array imaging setup.Keywords
Funding Information
- Natural Sciences and Engineering Council of Canada (CREATE-528202-2019, RGPIN-2022-04157)
- Canadian Space Agency (21FAWATA08)
- E.W.R. Steacie Memorial Fellowship (SMFSU-556263-2021)
This publication has 33 references indexed in Scilit:
- Towards practical implementation of the compressed sensing framework for multi-element synthetic transmit aperture imagingUltrasonics, 2021
- Ultrasound ImagingInvestigative Radiology, 2020
- Gap-Filling Method for Suppressing Grating Lobes in Ultrasound Imaging: Experimental Study With Deep-Learning ApproachIEEE Access, 2020
- A Survey on optimized implementation of deep learning models on the NVIDIA Jetson platformJournal of Systems Architecture, 2019
- Experimental 3-D Ultrasound Imaging with 2-D Sparse Arrays using Focused and Diverging WavesScientific Reports, 2018
- Compressed delay-and-sum beamforming for ultrafast ultrasound imaging2016
- Out of hospital point of care ultrasound: current use models and future directionsEuropean Journal of Trauma and Emergency Surgery, 2015
- Pre-beamformed RF signal reconstruction in medical ultrasound using compressive sensingUltrasonics, 2013
- Synthetic aperture ultrasound imagingUltrasonics, 2006
- Optimizing the radiation pattern of sparse periodic linear arraysIEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control, 1996