End-to-End Learning-Based Ultrasound Reconstruction
This work addresses the need for improved, clinically viable ultrasound reconstruction, though it appears incremental as it builds on existing deep learning approaches.
The paper tackles the problem of balancing image quality and clinical usability in ultrasound imaging by proposing a fully convolutional neural network with a custom loss function for end-to-end reconstruction, demonstrating performance increases in a clinical environment.
Ultrasound imaging is caught between the quest for the highest image quality, and the necessity for clinical usability. Our contribution is two-fold: First, we propose a novel fully convolutional neural network for ultrasound reconstruction. Second, a custom loss function tailored to the modality is employed for end-to-end training of the network. We demonstrate that training a network to map time-delayed raw data to a minimum variance ground truth offers performance increases in a clinical environment. In doing so, a path is explored towards improved clinically viable ultrasound reconstruction. The proposed method displays both promising image reconstruction quality and acquisition frequency when integrated for live ultrasound scanning. A clinical evaluation is conducted to verify the diagnostic usefulness of the proposed method in a clinical setting.