# Sparse2Inverse: Self-supervised inversion of sparse-view CT data

arXiv: https://arxiv.org/abs/2402.16921 · HTML: https://mlsanity.com/paper/2402.16921/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Feb 2024.

## Built on by (most cited first, 8 of 8)

- [Noisier2Inverse: Self-Supervised Learning for Image Reconstruction with Correlated Noise](https://mlsanity.com/paper/2503.19468/) (2025)
- [Benchmarking Self-Supervised Learning Methods for Accelerated MRI Reconstruction](https://mlsanity.com/paper/2502.14009/) (2025)
- [TomoSelfDEQ: Self-Supervised Deep Equilibrium Learning for Sparse-Angle CT Reconstruction](https://mlsanity.com/paper/2502.21320/) (2025)
- [Locally-Supervised Global Image Restoration](https://mlsanity.com/paper/2511.01998/) (2025)
- [HyDRA: Hybrid Denoising Regularization for Measurement-Only DEQ Training](https://mlsanity.com/paper/2601.01228/) (2026)
- [SPLIT: Self-supervised Partitioning for Learned Inversion in Nonlinear Tomography](https://mlsanity.com/paper/2604.15651/) (2026)
- [Self-Supervised Angular Deblurring in Photoacoustic Reconstruction via Noisier2Inverse](https://mlsanity.com/paper/2604.15681/) (2026)
- [Design Choices in Splitting-Based Self-Supervised Sparse-View CT Reconstruction](https://mlsanity.com/paper/2607.10898/) (2026)

## Abstract (arXiv)

Sparse-view computed tomography (CT) enables fast and low-dose CT imaging, an essential feature for patient-save medical imaging and rapid non-destructive testing. In sparse-view CT, only a few projection views are acquired, causing standard reconstructions to suffer from severe artifacts and noise. To address these issues, we propose a self-supervised image reconstruction strategy. Specifically, in contrast to the established Noise2Inverse, our proposed training strategy uses a loss function in the projection domain, thereby bypassing the otherwise prescribed nullspace component. We demonstrate the effectiveness of the proposed method in reducing stripe-artifacts and noise, even from highly sparse data.