We propose a deep learning method for 3D volumetric reconstruction in low-dose helical cone-beam computed tomography. Prior machine learning approaches require reference reconstructions computed by another algorithm for training. In contrast, we train our model in a fully self-supervised manner using only noisy 2D X-ray data. This is enabled by incorporating a fast differentiable CT simulator in the training loop. As we do not rely on reference reconstructions, the fidelity of our results is not limited by their potential shortcomings. We evaluate our method on real helical cone-beam projections and simulated phantoms. Our results show significantly higher visual fidelity and better PSNR over techniques that rely on existing reconstructions. When applied to full-dose data, our method produces high-quality results orders of magnitude faster than iterative techniques.

翻译：我们提出了一种用于低剂量螺旋锥束计算机断层扫描中三维体素重建的深度学习方法。以往机器学习方法需要依赖另一算法计算出的参考重建结果进行训练。相比之下，我们的模型仅使用含噪二维X射线数据进行完全自监督训练，其关键在于将可微分的快速CT模拟器融入训练循环中。由于无需依赖参考重建结果，我们的方法不受限于传统重建可能存在的缺陷。我们使用真实螺旋锥束投影数据和仿真体模评估该方法。结果显示，相较于依赖现有重建结果的技术，我们的方法在视觉保真度和峰值信噪比（PSNR）上均显著更优。当应用于全剂量数据时，本方法能以迭代技术数百倍的速度生成高质量重建结果。