# QN-Mixer: A Quasi-Newton MLP-Mixer Model for Sparse-View CT Reconstruction

arXiv: https://arxiv.org/abs/2402.17951 · HTML: https://mlsanity.com/paper/2402.17951/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 24 of its 57 references that are in the map.
- First posted on arXiv 28 Feb 2024.

## Builds on (most cited first, 24 of 24)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [MLP-Mixer: An all-MLP Architecture for Vision](https://mlsanity.com/paper/2105.01601/) (2021)
- [Deep Convolutional Neural Network for Inverse Problems in Imaging](https://mlsanity.com/paper/1611.03679/) (2016)
- [Learned Primal-dual Reconstruction](https://mlsanity.com/paper/1707.06474/) (2017)
- [Low-Dose CT with a Residual Encoder-Decoder Convolutional Neural Network (RED-CNN)](https://mlsanity.com/paper/1702.00288/) (2017)
- [End-to-End Variational Networks for Accelerated MRI Reconstruction](https://mlsanity.com/paper/2004.06688/) (2020)
- [Adversarial Regularizers in Inverse Problems](https://mlsanity.com/paper/1805.11572/) (2018)
- [Equivariant Imaging: Learning Beyond the Range Space](https://mlsanity.com/paper/2103.14756/) (2021)
- [CNN-Based Projected Gradient Descent for Consistent Image Reconstruction](https://mlsanity.com/paper/1709.01809/) (2017)
- [FISTA-Net: Learning A Fast Iterative Shrinkage Thresholding Network for Inverse Problems in Imaging](https://mlsanity.com/paper/2008.02683/) (2020)
- [DuDoNet: Dual Domain Network for CT Metal Artifact Reduction](https://mlsanity.com/paper/1907.00273/) (2019)
- [Total Deep Variation for Linear Inverse Problems](https://mlsanity.com/paper/2001.05005/) (2020)
- [Deep-neural-network based sinogram synthesis for sparse-view CT image reconstruction](https://mlsanity.com/paper/1803.00694/) (2018)
- [End-to-end reconstruction meets data-driven regularization for inverse problems](https://mlsanity.com/paper/2106.03538/) (2021)
- [Practical tradeoffs between memory, compute, and performance in learned optimizers](https://mlsanity.com/paper/2203.11860/) (2022)
- [HUMUS-Net: Hybrid unrolled multi-scale network architecture for accelerated MRI reconstruction](https://mlsanity.com/paper/2203.08213/) (2022)
- [LEARN++: Recurrent Dual-Domain Reconstruction Network for Compressed Sensing CT](https://mlsanity.com/paper/2012.06983/) (2020)
- [Learning to Distill Global Representation for Sparse-View CT](https://mlsanity.com/paper/2308.08463/) (2023)
- [Transformer-Based Learned Optimization](https://mlsanity.com/paper/2212.01055/) (2022)
- [Quasi-Newton Methods for Saddle Point Problems and Beyond](https://mlsanity.com/paper/2111.02708/) (2021)
- [Self-Supervised Training For Low Dose CT Reconstruction](https://mlsanity.com/paper/2010.13232/) (2020)

## Built on by (most cited first, 6 of 6)

- [Expanding-and-Shrinking Binary Neural Networks](https://mlsanity.com/paper/2503.23709/) (2025)
- [L-SR1: Learned Symmetric-Rank-One Preconditioning](https://mlsanity.com/paper/2508.12270/) (2025)
- [TPG-INR: Target Prior-Guided Implicit 3D CT Reconstruction for Enhanced Sparse-view Imaging](https://mlsanity.com/paper/2511.18806/) (2025)
- [Resolution-Agnostic Neural Operators for Multi-Rate Sparse-View CT](https://mlsanity.com/paper/2512.12236/) (2025)
- [CG-GLORE: A Conjugate Gradient-Based Global-Local Regularization Network for Sparse-View CT Reconstruction](https://mlsanity.com/paper/2608.15246/) (2026)
- [TomoTransformer: Towards a Foundation Model for CT Reconstruction](https://mlsanity.com/paper/2609.37605/) (2026)

## Abstract (arXiv)

Inverse problems span across diverse fields. In medical contexts, computed tomography (CT) plays a crucial role in reconstructing a patient's internal structure, presenting challenges due to artifacts caused by inherently ill-posed inverse problems. Previous research advanced image quality via post-processing and deep unrolling algorithms but faces challenges, such as extended convergence times with ultra-sparse data. Despite enhancements, resulting images often show significant artifacts, limiting their effectiveness for real-world diagnostic applications. We aim to explore deep second-order unrolling algorithms for solving imaging inverse problems, emphasizing their faster convergence and lower time complexity compared to common first-order methods like gradient descent. In this paper, we introduce QN-Mixer, an algorithm based on the quasi-Newton approach. We use learned parameters through the BFGS algorithm and introduce Incept-Mixer, an efficient neural architecture that serves as a non-local regularization term, capturing long-range dependencies within images. To address the computational demands typically associated with quasi-Newton algorithms that require full Hessian matrix computations, we present a memory-efficient alternative. Our approach intelligently downsamples gradient information, significantly reducing computational requirements while maintaining performance. The approach is validated through experiments on the sparse-view CT problem, involving various datasets and scanning protocols, and is compared with post-processing and deep unrolling state-of-the-art approaches. Our method outperforms existing approaches and achieves state-of-the-art performance in terms of SSIM and PSNR, all while reducing the number of unrolling iterations required.