Transcranial ultrasound viscoelasticity and fluidity imaging of brain tissue based on multi-scale spatiotemporal deep learning.
Authors
Affiliations (5)
Affiliations (5)
- The Key Laboratory of Biomedical Information Engineering of Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, Shaanxi, PR China; Shenzhen Mindray Bio-Medical Electronics Co., Ltd, Shenzhen, 518057, Guangdong, PR China.
- The Key Laboratory of Biomedical Information Engineering of Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, Shaanxi, PR China.
- Shenzhen Mindray Bio-Medical Electronics Co., Ltd, Shenzhen, 518057, Guangdong, PR China.
- The Key Laboratory of Biomedical Information Engineering of Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, Shaanxi, PR China. Electronic address: [email protected].
- The Key Laboratory of Biomedical Information Engineering of Ministry of Education, Department of Biomedical Engineering, School of Life Science and Technology, Xi'an Jiaotong University, Xi'an, 710049, Shaanxi, PR China. Electronic address: [email protected].
Abstract
Brain tissue mechanics play a critical role in neurological disorders. However, noninvasive characterization is impeded by the tissue's biphasic composition and small shear modulus. We developed a transcranial ultrasound viscoelasticity and fluidity imaging method using multiscale spatiotemporal deep learning. This method integrates multiscale pyramidal convolution and hybrid losses to overcome the limitations of low-SNR signals and small shear displacements through dual-branch processing, capturing high-frequency details (300 Hz) and low-frequency patterns (100 Hz) simultaneously. The proposed method achieves transcranial ultrasound viscoelasticity and fluidity imaging in brain tissue, outperforming the pyramid, warping, and cost volume network (PWC-Net) with a 4% reduction in low-frequency reconstruction errors and enhanced high-frequency signal fidelity. Validation of the method was conducted on simulation data, phantom data, and ex vivo animal data, demonstrating dual-tumor imaging at a 5.5 mm radius with quantitatively superior metrics (SNR=17.43, CNR=5.64) compared to existing methods.