Paper Info
Title
Switchable and Tunable Deep Beamformer Using Adaptive Instance Normalization for Medical Ultrasound
Abstract
Recent proposals of deep learning-based beamformers for ultrasound imaging (US) have attracted significant attention as computational efficient alternatives to adaptive and compressive beamformers. Moreover, deep beamformers are versatile in that image post-processing algorithms can be readily combined. Unfortunately, with the existing technology, a large number of beamformers need to be trained and stored for different probes, organs, depth ranges, operating frequency, and desired target ‘styles’, demanding significant resources such as training data, etc. To address this problem, here we propose a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">switchable and tunable</i> deep beamformer that can switch between various types of outputs such as DAS, MVBF, DMAS, GCF, etc., and also adjust noise removal levels at the inference phase, by using a simple switch or tunable nozzle. This novel mechanism is implemented through Adaptive Instance Normalization (AdaIN) layers, so that distinct outputs can be generated using a single generator by merely changing the AdaIN codes. Experimental results using B-mode focused ultrasound confirm the flexibility and efficacy of the proposed method for various applications.
Year
DOI
Venue
2022
10.1109/TMI.2021.3110730
IEEE Transactions on Medical Imaging
Keywords
DocType
Volume
Deep beamformer,adaptive instance normalization,ultrasound imaging,B-mode,beamforming,adaptive beamformer
Journal
41
Issue
ISSN
Citations 
2
0278-0062
0
PageRank 
References 
Authors
0.34
0
3
Name
Order
Citations
PageRank
Shujaat Khan1389.56
Jaeyoung Huh251.40
Jong Chul Ye371579.99