# Learning Perspective Deformation in X-Ray Transmission Imaging

arXiv: https://arxiv.org/abs/2202.06366 · HTML: https://mlsanity.com/paper/2202.06366/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 19 of its 63 references that are in the map.
- First posted on arXiv 13 Feb 2022.

## Builds on (most cited first, 19 of 19)

- [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)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks](https://mlsanity.com/paper/1703.10593/) (2017)
- [Twins: Revisiting the Design of Spatial Attention in Vision Transformers](https://mlsanity.com/paper/2104.13840/) (2021)
- [Training Deep Networks with Synthetic Data: Bridging the Reality Gap by Domain Randomization](https://mlsanity.com/paper/1804.06516/) (2018)
- [The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 Challenge](https://mlsanity.com/paper/1912.01054/) (2019)
- [Learning to Find Good Correspondences](https://mlsanity.com/paper/1711.05971/) (2017)
- [Learning Two-View Correspondences and Geometry Using Order-Aware Network](https://mlsanity.com/paper/1908.04964/) (2019)
- [X2CT-GAN: Reconstructing CT from Biplanar X-Rays with Generative Adversarial Networks](https://mlsanity.com/paper/1905.06902/) (2019)
- [Conditional Deformable Image Registration with Convolutional Neural Network](https://mlsanity.com/paper/2106.12673/) (2021)
- [Task Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image Segmentation](https://mlsanity.com/paper/1806.07201/) (2018)
- [Deep Learning for Low-Dose CT Denoising](https://mlsanity.com/paper/1902.10127/) (2019)
- [Synthetic Image Rendering Solves Annotation Problem in Deep Learning Nanoparticle Segmentation](https://mlsanity.com/paper/2011.10505/) (2020)
- [Scale-Space Anisotropic Total Variation for Limited Angle Tomography](https://mlsanity.com/paper/1712.06930/) (2017)
- [Projection-to-Projection Translation for Hybrid X-ray and Magnetic Resonance Imaging](https://mlsanity.com/paper/1911.08163/) (2019)
- [Robust Self-Supervised Learning of Deterministic Errors in Single-Plane (Monoplanar) and Dual-Plane (Biplanar) X-ray Fluoroscopy](https://mlsanity.com/paper/2001.00686/) (2020)
- [Cephalogram Synthesis and Landmark Detection in Dental Cone-Beam CT Systems](https://mlsanity.com/paper/2009.04420/) (2020)
- [Computed tomography data collection of the complete human mandible and valid clinical ground truth models](https://mlsanity.com/paper/1902.05255/) (2019)

## Abstract (arXiv)

In cone-beam X-ray transmission imaging, perspective deformation causes difficulty in direct, accurate geometric assessments of anatomical structures. In this work, the perspective deformation correction problem is formulated and addressed in a framework using two complementary (180deg) views. The complementary view setting provides a practical way to identify perspectively deformed structures by assessing the deviation between the two views. It also provides bounding information and reduces uncertainty for learning perspective deformation. Two representative networks Pix2pixGAN and TransU-Net for correcting perspective deformation are investigated. Experiments on numerical bead phantom data demonstrate the advantage of complementary views over orthogonal views or a single view. They show that Pix2pixGAN as a fully convolutional network achieves better performance in polar space than Cartesian space, while TransU-Net as a transformer-based hybrid network achieves comparable performance in Cartesian space to polar space. Further study demonstrates that the trained model has certain tolerance to geometric inaccuracy within calibration accuracy. The efficacy of the proposed framework on synthetic projection images from patients' chest and head data as well as real cadaver CBCT projection data and its robustness in the presence of bulky metal implants and surgical screws indicate the promising aspects of future real applications.