UDCR: Unsupervised Aortic DSA/CTA Rigid Registration Using Deep Reinforcement Learning and Overlap Degree Calculation
This addresses a cross-modal image registration challenge in medical imaging for clinicians, offering a flexible and unsupervised approach that could enhance surgical planning, though it appears incremental as it builds on existing reinforcement learning methods for registration.
The paper tackled the problem of rigid registration between aortic DSA and CTA images for clinical applications like aortic dissection treatment, proposing an unsupervised method using deep reinforcement learning and an overlap degree reward function, achieving a Mean Absolute Error of 2.85 mm in translation and 4.35° in rotation.
The rigid registration of aortic Digital Subtraction Angiography (DSA) and Computed Tomography Angiography (CTA) can provide 3D anatomical details of the vasculature for the interventional surgical treatment of conditions such as aortic dissection and aortic aneurysms, holding significant value for clinical research. However, the current methods for 2D/3D image registration are dependent on manual annotations or synthetic data, as well as the extraction of landmarks, which is not suitable for cross-modal registration of aortic DSA/CTA. In this paper, we propose an unsupervised method, UDCR, for aortic DSA/CTA rigid registration based on deep reinforcement learning. Leveraging the imaging principles and characteristics of DSA and CTA, we have constructed a cross-dimensional registration environment based on spatial transformations. Specifically, we propose an overlap degree calculation reward function that measures the intensity difference between the foreground and background, aimed at assessing the accuracy of registration between segmentation maps and DSA images. This method is highly flexible, allowing for the loading of pre-trained models to perform registration directly or to seek the optimal spatial transformation parameters through online learning. We manually annotated 61 pairs of aortic DSA/CTA for algorithm evaluation. The results indicate that the proposed UDCR achieved a Mean Absolute Error (MAE) of 2.85 mm in translation and 4.35° in rotation, showing significant potential for clinical applications.