# Simulator-Based Self-Supervision for Learned 3D Tomography Reconstruction

arXiv: https://arxiv.org/abs/2212.07431 · HTML: https://mlsanity.com/paper/2212.07431/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 40 references that are in the map.
- First posted on arXiv 14 Dec 2022.

## Builds on (most cited first, 13 of 13)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification](https://mlsanity.com/paper/1502.01852/) (2015)
- [Noise2Noise: Learning Image Restoration without Clean Data](https://mlsanity.com/paper/1803.04189/) (2018)
- [Modular Primitives for High-Performance Differentiable Rendering](https://mlsanity.com/paper/2011.03277/) (2020)
- [DiffTaichi: Differentiable Programming for Physical Simulation](https://mlsanity.com/paper/1910.00935/) (2019)
- [Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)](https://mlsanity.com/paper/1702.00288/) (2017)
- [Low Dose CT Image Denoising Using a Generative Adversarial Network with Wasserstein Distance and Perceptual Loss](https://mlsanity.com/paper/1708.00961/) (2017)
- [Single-Image SVBRDF Capture with a Rendering-Aware Deep Network](https://mlsanity.com/paper/1810.09718/) (2018)
- [Distribution Matching Losses Can Hallucinate Features in Medical Image Translation](https://mlsanity.com/paper/1805.08841/) (2018)
- [Reblur2Deblur: Deblurring Videos via Self-Supervised Learning](https://mlsanity.com/paper/1801.05117/) (2018)
- [Radon Inversion via Deep Learning](https://mlsanity.com/paper/1808.03015/) (2018)

## Built on by (most cited first, 1 of 1)

- [Self-Supervised Denoiser Framework](https://mlsanity.com/paper/2411.19593/) (2024)

## Abstract (arXiv)

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.