# OSNet & MNetO: Two Types of General Reconstruction Architectures for Linear Computed Tomography in Multi-Scenarios

arXiv: https://arxiv.org/abs/2309.11858 · HTML: https://mlsanity.com/paper/2309.11858/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 51 references that are in the map.
- First posted on arXiv 21 Sep 2023.

## Builds on (most cited first, 18 of 18)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Progressive Growing of GANs for Improved Quality, Stability, and Variation](https://mlsanity.com/paper/1710.10196/) (2017)
- [Bottleneck Transformers for Visual Recognition](https://mlsanity.com/paper/2101.11605/) (2021)
- [Why do deep convolutional networks generalize so poorly to small image transformations?](https://mlsanity.com/paper/1805.12177/) (2018)
- [Framing U-Net via Deep Convolutional Framelets: Application to Sparse-view CT](https://mlsanity.com/paper/1708.08333/) (2017)
- [Can Deep Learning Outperform Modern Commercial CT Image Reconstruction Methods?](https://mlsanity.com/paper/1811.03691/) (2018)
- [Understanding Geometry of Encoder-Decoder CNNs](https://mlsanity.com/paper/1901.07647/) (2019)
- [2DeteCT -- A large 2D expandable, trainable, experimental Computed Tomography dataset for machine learning](https://mlsanity.com/paper/2306.05907/) (2023)
- [One Network to Solve All ROIs: Deep Learning CT for Any ROI using Differentiated Backprojection](https://mlsanity.com/paper/1810.00500/) (2018)
- [Fiducial marker recovery and detection from severely truncated data in navigation assisted spine surgery](https://mlsanity.com/paper/2108.13844/) (2021)
- [DiffusionCT: Latent Diffusion Model for CT Image Standardization](https://mlsanity.com/paper/2301.08815/) (2023)
- [BPF Algorithms for Multiple Source-Translation Computed Tomography Reconstruction](https://mlsanity.com/paper/2305.18878/) (2023)
- [Differentiated Backprojection Domain Deep Learning for Conebeam Artifact Removal](https://mlsanity.com/paper/1906.06854/) (2019)
- [Analytical reconstructions of full-scan multiple source-translation computed tomography under large field of views](https://mlsanity.com/paper/2305.19767/) (2023)

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

- [Transformer-based Single-Cell Language Model: A Survey](https://mlsanity.com/paper/2407.13205/) (2024)

## Abstract (arXiv)

Recently, linear computed tomography (LCT) systems have actively attracted attention. To weaken projection truncation and image the region of interest (ROI) for LCT, the backprojection filtration (BPF) algorithm is an effective solution. However, in BPF for LCT, it is difficult to achieve stable interior reconstruction, and for differentiated backprojection (DBP) images of LCT, multiple rotation-finite inversion of Hilbert transform (Hilbert filtering)-inverse rotation operations will blur the image. To satisfy multiple reconstruction scenarios for LCT, including interior ROI, complete object, and exterior region beyond field-of-view (FOV), and avoid the rotation operations of Hilbert filtering, we propose two types of reconstruction architectures. The first overlays multiple DBP images to obtain a complete DBP image, then uses a network to learn the overlying Hilbert filtering function, referred to as the Overlay-Single Network (OSNet). The second uses multiple networks to train different directional Hilbert filtering models for DBP images of multiple linear scannings, respectively, and then overlays the reconstructed results, i.e., Multiple Networks Overlaying (MNetO). In two architectures, we introduce a Swin Transformer (ST) block to the generator of pix2pixGAN to extract both local and global features from DBP images at the same time. We investigate two architectures from different networks, FOV sizes, pixel sizes, number of projections, geometric magnification, and processing time. Experimental results show that two architectures can both recover images. OSNet outperforms BPF in various scenarios. For the different networks, ST-pix2pixGAN is superior to pix2pixGAN and CycleGAN. MNetO exhibits a few artifacts due to the differences among the multiple models, but any one of its models is suitable for imaging the exterior edge in a certain direction.