Publications by authors named "Dejia Cai"
Background: Although B-mode imaging has been widely used in ultrasound-guided high-intensity focused ultrasound (HIFU) treatment, challenges remain in improving its quality and sensitivity for monitoring the thermal dose. Recently, quantitative ultrasound (QUS) imaging has been recognized with the potential to better sense the changes in the microstructure of ablated tissues.
Purpose: This study proposed to use a QUS method called weighted ultrasound entropy (WUE) imaging to monitor the HIFU ablation.
Suppressing the HIFU interference in ultrasound guiding images with a diffusion-based deep learning model.
Comput Methods Programs Biomed
September 2024
Background And Objectives: In ultrasound guided high-intensity focused ultrasound (HIFU) surgery, it is necessary to transmit sound waves at different frequencies simultaneously using two transducers: one for the HIFU therapy and another for the ultrasound imaging guidance. In this specific setting, real-time monitoring of non-invasive surgery is challenging due to severe contamination of the ultrasound guiding images by strong acoustic interference from the HIFU sonication.
Methods: This paper proposed the use of a deep learning (DL) solution, specifically a diffusion implicit model, to suppress the HIFU interference.
Article Synopsis
- HIFU generates intense acoustic interference that disrupts B-mode monitoring images, reducing their effectiveness.
- A study proposes that one-dimensional (1D) U-Net-based networks are more effective than two-dimensional (2D) networks in suppressing this interference and improving image quality.
- Experiments showed that 1D U-Net-based methods improved structural similarity by over 30% compared to 2D methods, indicating their potential for better ultrasound monitoring in HIFU systems.