A diffusion-stimulated CT-US registration model with self-supervised learning and synthetic-to-real domain adaptation.
Authors
Affiliations (6)
Affiliations (6)
- Hanglok-Tech Co., Ltd., Zhuhai, China.
- School of Medical Information Engineering, Guangzhou University of Chinese Medicine, Guangzhou, China.
- Department of Radiology, First Medical Center, Chinese People's Liberation Army General Hospital, Beijing, China.
- School of Medical Information Engineering, Guangzhou University of Chinese Medicine, Guangzhou, China. Electronic address: [email protected].
- Hanglok-Tech Co., Ltd., Zhuhai, China. Electronic address: [email protected].
- Center of Interventional Radiology and Vascular Surgery, Department of Radiology, Zhongda Hospital, Medical School, Southeast University, Nanjing, China. Electronic address: [email protected].
Abstract
In abdominal interventional procedures, achieving precise registration of 2D ultrasound (US) frames with 3D computed tomography (CT) scans presents a significant challenge. Traditional tracking methods often rely on high-precision sensors, which can be prohibitively expensive. Furthermore, the clinical need for real-time registration with a broad capture range frequently exceeds the performance of standard image-based optimization techniques. Current automatic registration methods that utilize deep learning are either heavily reliant on manual annotations for training or struggle to effectively bridge the gap between different imaging domains. To address these challenges, we propose a novel diffusion-stimulated CT-US registration model. This model harnesses the physical diffusion properties of US to generate synthetic US images from preoperative CT data. Additionally, we introduce a synthetic-to-real domain adaptation strategy using a diffusion model to mitigate the discrepancies between real and synthetic US images. A dual-stream self-supervised regression neural network, trained on these synthetic images, is then used to estimate the pose within the CT space. The effectiveness of our proposed approach is verified through validation using US and CT scans from a dual-modality human abdominal phantom. The results of our experiments confirm that our method can accurately initialize the US image pose within an acceptable range of error and subsequently refine it to achieve precise alignment. This enables real-time, tracker-independent, and robust rigid registration of CT and US images.