Research map / 3D vision / Face and shape
X2CT-GAN: Reconstructing CT From Biplanar X-Rays With Generative Adversarial Networks
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use biplanar rather than single-view X-rays (ablation) | X2CT-CNN · LIDC-IDRI test | PSNR (dB): 23.12($\pm$0.02) -> 27.29($\pm$0.04) | Helped |
| Use biplanar rather than single-view X-rays (ablation) | X2CT-GAN · LIDC-IDRI test | PSNR (dB): 22.30($\pm$0.10) -> 26.19($\pm$0.13) | Helped |
| Add adversarial training to the MSE-only X2CT-CNN (ablation) | X2CT-GAN+B · LIDC-IDRI test | PSNR (dB): 27.29($\pm$0.04) -> 26.19($\pm$0.13) | Hurt |
| Add adversarial training to the MSE-only X2CT-CNN (ablation) | X2CT-GAN+B · LIDC-IDRI test | SSIM: 0.721($\pm$0.001) -> 0.656($\pm$0.008) | Hurt |
| Add Connection-B to single-view XC (ablation) | X2CT-CNN · LIDC-IDRI test | PSNR (dB): 22.46($\pm$0.02) -> 23.12($\pm$0.02) | Helped |
| Add Connection-B and Connection-C to biplanar XC (ablation) | X2CT-CNN · LIDC-IDRI test | PSNR (dB): 24.84($\pm$0.05) -> 27.29($\pm$0.04) | Helped |
| Add reconstruction loss to adversarial loss (ablation) | X2CT-GAN · LIDC-IDRI test | PSNR (dB): 17.38($\pm$0.36) -> 25.82($\pm$0.08) | Helped |
| Add projection loss to adversarial plus reconstruction loss (ablation) | X2CT-GAN · LIDC-IDRI test | PSNR (dB): 25.82($\pm$0.08) -> 26.05($\pm$0.02) | Helped |
| Condition the discriminator on input X-rays (ablation) | X2CT-GAN · LIDC-IDRI test | SSIM: 0.645($\pm$0.002) -> 0.656($\pm$0.008) | Helped |
| Use adversarial loss alone without reconstruction or projection constraints (ablation) | X2CT-GAN · LIDC-IDRI test | PSNR (dB): 17.38($\pm$0.36) vs 26.19($\pm$0.13) | Hurt |
Closest papers by meaning
- Lose the Views: Limited Angle CT Reconstruction via Implicit Sinogram Completion (CVPR 2018 · similarity 0.85)
- Translating and Segmenting Multimodal Medical Volumes With Cycle- and Shape-Consistency Generative Adversarial Network (CVPR 2018 · similarity 0.85)
- Improving Robustness of Deep-Learning-Based Image Reconstruction (ICML 2020 · similarity 0.85)
- C^2RV: Cross-Regional and Cross-View Learning for Sparse-View CBCT Reconstruction (CVPR 2024 · similarity 0.84)
- TCAM-Diff: Triplane-Aware Cross-Attention Medical Diffusion Model (AAAI 2025 · similarity 0.82)
- Bootstrapping Chest CT Image Understanding by Distilling Knowledge from X-ray Expert Models (CVPR 2024 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.