Trans${^2}$-CBCT: A Dual-Transformer Framework for Sparse-View CBCT Reconstruction

TL;DR

This paper introduces Trans$^2$-CBCT, a novel dual-transformer framework that combines CNN-Transformer hybrid models and point transformers to improve sparse-view CBCT reconstruction, achieving higher image quality with fewer X-ray views.

Contribution

The paper proposes a unified dual-transformer framework for sparse-view CBCT, integrating global and local feature extraction with volumetric coherence enforcement, surpassing prior methods in image quality metrics.

Findings

Trans$^2$-CBCT outperforms baselines by 1.17 dB PSNR and 0.0163 SSIM on LUNA16.

The model shows consistent improvements from 6 to 10 views.

Combining CNN-Transformer features with point-based geometry reasoning enhances reconstruction quality.

Abstract

Cone-beam computed tomography (CBCT) using only a few X-ray projection views enables faster scans with lower radiation dose, but the resulting severe under-sampling causes strong artifacts and poor spatial coverage. We address these challenges in a unified framework. First, we replace conventional UNet/ResNet encoders with TransUNet, a hybrid CNN-Transformer model. Convolutional layers capture local details, while self-attention layers enhance global context. We adapt TransUNet to CBCT by combining multi-scale features, querying view-specific features per 3D point, and adding a lightweight attenuation-prediction head. This yields Trans-CBCT, which surpasses prior baselines by 1.17 dB PSNR and 0.0163 SSIM on the LUNA16 dataset with six views. Second, we introduce a neighbor-aware Point Transformer to enforce volumetric coherence. This module uses 3D positional encoding and attention over k-nearest neighbors to improve spatial consistency. The resulting model, Trans$^2$-CBCT, provides an additional gain of 0.63 dB PSNR and 0.0117 SSIM. Experiments on LUNA16 and ToothFairy show consistent gains from six to ten views, validating the effectiveness of combining CNN-Transformer features with point-based geometry reasoning for sparse-view CBCT reconstruction.