Geometry-Aware Attenuation Learning for Sparse-View CBCT Reconstruction

TL;DR

A novel geometry-aware encoder-decoder framework that respects the geometric relationship between 3D CBCT image and its 2D X-ray projections during feature back projection stage, and enjoys the prior knowledge learned from the data population ensures its adaptability in dealing with extremely sparse view inputs without individual training.

Abstract

Cone Beam Computed Tomography (CBCT) plays a vital role in clinical imaging. Traditional methods typically require hundreds of 2D X-ray projections to reconstruct a high-quality 3D CBCT image, leading to considerable radiation exposure. This has led to a growing interest in sparse-view CBCT reconstruction to reduce radiation doses. While recent advances, including deep learning and neural rendering algorithms, have made strides in this area, these methods either produce unsatisfactory results or suffer from time inefficiency of individual optimization. In this paper, we introduce a novel geometry-aware encoder-decoder framework to solve this problem. Our framework starts by encoding multi-view 2D features from various 2D X-ray projections with a 2D CNN encoder. Leveraging the geometry of CBCT scanning, it then back-projects the multi-view 2D features into the 3D space to formulate a comprehensive volumetric feature map, followed by a 3D CNN decoder to recover 3D CBCT image. Importantly, our approach respects the geometric relationship between 3D CBCT image and its 2D X-ray projections during feature back projection stage, and enjoys the prior knowledge learned from the data population. This ensures its adaptability in dealing with extremly sparse view inputs without individual training, such as scenarios with only 5 or 10 X-ray projections. Extensive evaluations on two simulated datasets and one real-world dataset demonstrate exceptional reconstruction quality and time efficiency of our method.

Figures (15)

• Figure 1: CBCT scanning and reconstruction. In the CBCT imaging process, CBCT scanning (a) would generate a sequence of 2D X-ray projections (b). These projections are utilized to reconstruct 3D CBCT image (c).
• Figure 2: Geometric configuration of CBCT scanning and X-ray projection simulation.
• Figure 3: Overview of our proposed method. A 2D CNN encoder first extracts feature representations from multi-view X-ray projections. Then, we build a 3D feature map by feature back projection and adaptive feature fusing. Finally, this 3D feature map is fed into a 3D CNN decoder to produce the final CBCT image.
• Figure 4: Coordinate transformation of query point for feature back projection.
• Figure 5: Qualitative comparison on case #10 from dental dataset (axial slice). Window: [-1000, 2000] HU.