Related Experiment Video
Updated: Aug 15, 2025
Author Spotlight: Advancing Human Brain Modulation – Optimized Protocols for Transcranial Ultrasound Stimulation Experiments
Published on: June 28, 2024
Simulation-to-real generalization for deep-learning-based refraction-corrected ultrasound tomography image
Wenzhao Zhao1, Yuling Fan1, Hongjian Wang2
1Interdisciplinary Center for Scientific Computing (IWR), Central Institute for Computer Engineering (ZITI), Mannheim Institute for Intelligent Systems in Medicine (MIISM), Medical Faculty Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, D-68167 Mannheim, Germany.
Deep learning significantly speeds up ultrasound tomography image reconstruction. Novel methods bridge the simulation-to-real gap, improving performance on actual data and outperforming traditional methods.
Area of Science:
- Medical Imaging
- Computational Imaging
- Artificial Intelligence
Background:
- Ultrasound computed tomography (UCT) image reconstruction is computationally intensive with iterative methods.
- Deep learning offers faster direct reconstruction but struggles with the simulation-to-real data gap.
- Lack of real labeled data hinders neural network training for UCT.
Purpose of the Study:
- To enhance the simulation-to-real generalization of deep learning models for UCT.
- To develop strategies for improving neural network performance on real UCT measurement data.
- To enable faster and more accurate UCT image reconstruction using deep learning.
Main Methods:
- Developed a Fourier-transform-integrated neural network.
- Implemented measurement-domain data augmentation techniques.
- Utilized a self-supervised learning-based patch-wise preprocessing neural network.
- Evaluated methods on simulation and real measurement datasets from two prototype machines.
Main Results:
- Deep learning methods improved neural network robustness against noise.
- Enhanced generalizability to real measurement data was demonstrated.
- Superior imaging quality compared to traditional iterative methods was achieved.
- Real-time 2D-image reconstruction capability was enabled.
Conclusions:
- The developed strategies effectively bridge the simulation-to-real gap in UCT deep learning.
- Deep learning models can outperform conventional iterative reconstruction algorithms in UCT.
- This research facilitates the practical application of deep learning for UCT image reconstruction using simulation data.
