A progressively dual reconstruction network for plane wave beamforming with both paired and unpaired training data

• Published in: Ultrasonics Vol. 127; p. 106833
• Main Authors: Gao, Junling, Xu, Lei, Zou, Qin, Zhang, Bo, Wang, Diya, Wan, Mingxi
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.01.2023
• Subjects: Beamforming; Coherent compounding; Progressively dual reconstruction network; Transfer learning; Ultrasound plane wave imaging; Coherent compounding; Beamforming; Ultrasound plane wave imaging; Progressively dual reconstruction network; Transfer learning
• ISSN: 0041-624X; 1874-9968
• DOI: 10.1016/j.ultras.2022.106833

High-frame-rate plane wave (PW) imaging suffers from unsatisfactory image quality due to the absence of focus in transmission. Although coherent compounding from tens of PWs can improve PW image quality, it in turn results in a decreased frame rate, which is limited for tracking fast moving tissues. To overcome the trade-off between frame rate and image quality, we propose a progressively dual reconstruction network (PDRN) to achieve adaptive beamforming and enhance the image quality via both supervised and transfer learning in the condition of single or a few PWs transmission. Specifically, the proposed model contains a progressive network and a dual network to form a close loop and provide collaborative supervision for model optimization. The progressive network takes the channel delay of each spatial point as input and progressively learns coherent compounding beamformed data with increased numbers of steered PWs step by step. The dual network learns the downsampling process and reconstructs the beamformed data with decreased numbers of steered PWs, which reduces the space of the possible learning functions and improves the model’s discriminative ability. In addition, the dual network is leveraged to perform transfer learning for the training data without sufficient steered PWs. The simulated, in vivo, vocal cords (VCs), and public available CUBDL dataset are collected for model evaluation. •We propose a PDRN scheme to improve PW beamforming and enhance the quality of the image.•Inspired by the dual model in image reconstruction tasks, we consider a more general case where there is no groundtruth data with enough steered PWs.•Extensive experiments with both supervised setting (using paired data) and transfer learning setting (using both paired and unpaired data) demonstrate the superiority of our method for adaptive PW beamforming by only using the channel delay of the ROI.