Enhanced Visualization: Transforming Non-Contrast into Contrast-Enhanced Computed Tomography Images Through Advanced Generative Adversarial Networks

TL;DR

This paper introduces a GAN-based model that generates synthetic contrast-enhanced CT images from non-contrast scans, offering a potential alternative for patients who cannot receive contrast dye.

Contribution

The novel contribution is a GAN model that transforms non-contrast CT into synthetic contrast-enhanced images with improved qualitative visualization for mediastinal structures.

Findings

sCECT showed modest quantitative improvements over NCCT in pixel-wise similarity metrics.

Radiologists qualitatively rated sCECT higher, especially for mediastinal structure visualization.

SNR and CNR analyses confirmed enhanced contrast depiction in sCECT compared to NCCT.

Abstract

Background/Objectives: Contrast-enhanced CT (CECT) is essential for mediastinal and lymph node assessment but is often limited in patients with renal dysfunction, prior severe contrast reactions, or pediatric populations. Deep learning approaches, such as generative adversarial networks (GANs), allow the generation of synthetic CECT (sCECT) from non-contrast CT (NCCT) without contrast injection. Materials and Methods: A GAN-based model was trained using 400 CECT scans acquired between March and July 2024. The model was tested in 20 patients with lymphoma or metastatic lymphadenopathy diagnosed between January and July 2025, using only NCCT scans. Quantitative evaluation compared sCECT with CECT using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index (SSIM), and Pearson Correlation Coefficient (PCC). Two radiologists performed qualitative assessment, and Signal-to-Noise Ratio (SNR)/Contrast-to-Noise Ratio (CNR) values were measured for thoracic structures. Results: Compared with NCCT, sCECT demonstrated slightly lower MAE (20.87 ± 8.84 vs. 21.26 ± 9.26) and RMSE (45.22 ± 14.22 vs. 45.94 ± 15.07), and marginally higher PSNR (15.44 ± 2.70 vs. 15.38 ± 3.02), indicating modest improvements in pixel-wise similarity. SSIM values were comparable (0.610 ± 0.09 vs. 0.63 ± 0.10), while PCC decreased (0.61 ± 0.09 vs. 0.77 ± 0.15). All differences were statistically significant (p < 0.001). Despite these mixed quantitative results, sCECT was qualitatively rated significantly higher by radiologists, with improved visualization of mediastinal structures. SNR and CNR analyses further supported enhanced contrast depiction in sCECT compared with NCCT. Conclusions: The GAN-based model successfully generated sCECT from NCCT with modest quantitative similarity gains but clear qualitative improvement, particularly for mediastinal lymph node evaluation. Although synthetic enhancement represents a learned intensity transformation rather than true iodine-based attenuation, sCECT may serve as a valuable adjunct in patients with contraindications to iodinated contrast.

Figures