Non-contrast CT-based pulmonary embolism detection using GAN-generated synthetic contrast enhancement: Development and validation of an AI framework.
Authors
Affiliations (5)
Affiliations (5)
- Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA 02114, United States; Department of Biomedical Sciences, Korea University College of Medicine, Seoul 02841, Republic of Korea.
- Department of Radiology and Research Institute of Radiology, University of Ulsan College of Medicine, Asan Medical Center, Seoul 05505, Republic of Korea.
- Department of Internal Medicine, Kangwon National University, Chuncheon 24341, Republic of Korea.
- Department of Computer Science and Artificial Intelligence, Dongguk University, Seoul 04620, Republic of Korea. Electronic address: [email protected].
- Department of Pulmonary, Allergy and Critical Care Medicine, Kyung Hee University Hospital at Gangdong, School of Medicine, Kyung Hee University, Seoul 05278, Republic of Korea. Electronic address: [email protected].
Abstract
Acute pulmonary embolism (PE) is a life-threatening condition often diagnosed using CT pulmonary angiography (CTPA). However, CTPA is contraindicated in patients with contrast allergies or at risk for contrast-induced nephropathy. This study explores an AI-driven approach to generate synthetic contrast-enhanced images from non-contrast CT scans for accurate diagnosis of acute PE without contrast agents. This retrospective study used dual-energy and standard CT datasets from two institutions. The internal dataset included 84 patients: 41 PE-negative cases for generative model training and 43 patients (30 PE-positive) for diagnostic evaluation. An external dataset of 62 patients (26 PE-positive) was used for further validation. We developed a generative adversarial network (GAN) based on U-Net, trained on paired non-contrast and contrast-enhanced images. The model was optimized using contrast-enhanced L1-loss with hyperparameter λ to improve anatomical accuracy. A ConvNeXt-based classifier trained on the RSNA dataset (N = 7,122) generated per-slice PE probabilities, which were aggregated for patient-level prediction via a Random Forest model. Diagnostic performance was assessed using five-fold cross-validation on both internal and external datasets. The GAN achieved optimal image similarity at λ = 0.5, with the lowest mean absolute error (0.0089) and highest MS-SSIM (0.9674). PE classification yielded AUCs of 0.861 and 0.836 in the internal dataset, and 0.787 and 0.680 in the external dataset, using real and synthetic images, respectively. No statistically significant differences were observed. Our findings demonstrate that synthetic contrast CT can serve as a viable alternative for PE diagnosis in patients contraindicated for CTPA, supporting safe and accessible imaging strategies.