XctDiff: Reconstruction of CT Images with Consistent Anatomical Structures from a Single Radiographic Projection Image
This addresses the challenge of reducing radiation exposure and cost in medical imaging by enabling CT reconstruction from a single radiograph, though it appears incremental as it builds on existing methods with specific improvements.
The paper tackles the problem of reconstructing CT images from a single radiographic projection by proposing XctDiff, a framework that decomposes reconstruction into feature extraction and CT reconstruction tasks, achieving state-of-the-art performance and overcoming blurring issues.
In this paper, we present XctDiff, an algorithm framework for reconstructing CT from a single radiograph, which decomposes the reconstruction process into two easily controllable tasks: feature extraction and CT reconstruction. Specifically, we first design a progressive feature extraction strategy that is able to extract robust 3D priors from radiographs. Then, we use the extracted prior information to guide the CT reconstruction in the latent space. Moreover, we design a homogeneous spatial codebook to improve the reconstruction quality further. The experimental results show that our proposed method achieves state-of-the-art reconstruction performance and overcomes the blurring issue. We also apply XctDiff on self-supervised pre-training task. The effectiveness indicates that it has promising additional applications in medical image analysis. The code is available at:https://github.com/qingze-bai/XctDiff