# Multi-Pass, Multi-View Blended Learning for High-Fidelity Volumetric CT Synthesis from Chest X-Rays

arXiv: https://arxiv.org/abs/2609.09920 · HTML: https://mlsanity.com/paper/2609.09920/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 27 references that are in the map.
- First posted on arXiv 9 Sep 2026.

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

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison](https://mlsanity.com/paper/1901.07031/) (2019)
- [X2CT-GAN: Reconstructing CT from Biplanar X-Rays with Generative Adversarial Networks](https://mlsanity.com/paper/1905.06902/) (2019)
- [Self-Organized Operational Neural Networks with Generative Neurons](https://mlsanity.com/paper/2004.11778/) (2020)
- [Self-Organized Operational Neural Networks for Severe Image Restoration Problems](https://mlsanity.com/paper/2008.12894/) (2020)
- [FastONN -- Python based open-source GPU implementation for Operational Neural Networks](https://mlsanity.com/paper/2006.02267/) (2020)
- [Real-Time Patient-Specific ECG Classification by 1D Self-Operational Neural Networks](https://mlsanity.com/paper/2110.02215/) (2021)
- [Real-Time Glaucoma Detection from Digital Fundus Images using Self-ONNs](https://mlsanity.com/paper/2109.13604/) (2021)
- [Robust Peak Detection for Holter ECGs by Self-Organized Operational Neural Networks](https://mlsanity.com/paper/2110.02381/) (2021)
- [Blind ECG Restoration by Operational Cycle-GANs](https://mlsanity.com/paper/2202.00589/) (2022)
- [Global ECG Classification by Self-Operational Neural Networks with Feature Injection](https://mlsanity.com/paper/2204.03768/) (2022)
- [Operational vs Convolutional Neural Networks for Image Denoising](https://mlsanity.com/paper/2009.00612/) (2020)
- [CT Reconstruction from Few Planar X-rays with Application towards Low-resource Radiotherapy](https://mlsanity.com/paper/2308.02100/) (2023)
- [BM3D vs 2-Layer ONN](https://mlsanity.com/paper/2103.03060/) (2021)
- [XTransCT: Ultra-Fast Volumetric CT Reconstruction using Two Orthogonal X-Ray Projections for Image-guided Radiation Therapy via a Transformer Network](https://mlsanity.com/paper/2305.19621/) (2023)
- [Zero-Shot Motor Health Monitoring by Blind Domain Transition](https://mlsanity.com/paper/2212.06154/) (2022)
- [Improved Active Fire Detection using Operational U-Nets](https://mlsanity.com/paper/2304.09721/) (2023)
- [Progressive Transfer Learning for Multi-Pass Fundus Image Restoration](https://mlsanity.com/paper/2504.10025/) (2025)

## Abstract (arXiv)

Reconstructing volumetric Computed Tomography (CT) from a single 2D chest radiograph (CXR) is an ill-posed inverse problem, further complicated by the scarcity of paired CXR-CT training data. Prior approaches address this by training on Digitally Reconstructed Radiographs (DRRs), which are synthetic projections derived from CT volumes. However, the domain gap between DRRs and real CXRs limits generalization, often resulting in coarse or anatomically inconsistent reconstructions when applied to clinical images. To address this challenging problem, this study introduces a Multi-Pass Multi-View Blended Learning framework for synthesizing high-fidelity volumetric CT directly from real chest X-ray (CXR) images. The proposed approach progressively decomposes the synthesis task into two distinct, complementary learning stages. Stage 1 is an unsupervised CXR-to-DRR Domain Adaptation, while Stage 2 includes three passes, namely, (a) supervised DRR-to-CT Transformation, (b) unsupervised Multi-View Slice Refinement, followed by (c) Progressive Transfer Learning (PTL). With such a blended learning paradigm, the proposed approach mitigates the synthetic-to-real domain gap while enhancing both the structural integrity and anatomical detail of the final output. On the LIDC-IDRI dataset, where paired DRR-CT ground truth is available for quantitative evaluation, the proposed method improves upon prior methods by up to 14% in PSNR and 7.6% in SSIM. The framework successfully generates structurally consistent and anatomically realistic high-fidelity CT volumes from real CXRs, marking a significant advancement toward clinical viability of CT reconstruction from standard radiographic images.