RESUMEN
Background Lung MRI with ultrashort echo times (UTEs) enables high-resolution and radiation-free morphologic imaging; however, its image quality is still lower than that of CT. Purpose To assess the image quality and clinical applicability of synthetic CT images generated from UTE MRI by a generative adversarial network (GAN). Materials and Methods This retrospective study included patients with cystic fibrosis (CF) who underwent both UTE MRI and CT on the same day at one of six institutions between January 2018 and December 2022. The two-dimensional GAN algorithm was trained using paired MRI and CT sections and tested, along with an external data set. Image quality was assessed quantitatively by measuring apparent contrast-to-noise ratio, apparent signal-to-noise ratio, and overall noise and qualitatively by using visual scores for features including artifacts. Two readers evaluated CF-related structural abnormalities and used them to determine clinical Bhalla scores. Results The training, test, and external data sets comprised 82 patients with CF (mean age, 21 years ± 11 [SD]; 42 male), 28 patients (mean age, 18 years ± 11; 16 male), and 46 patients (mean age, 20 years ± 11; 24 male), respectively. In the test data set, the contrast-to-noise ratio of synthetic CT images (median, 303 [IQR, 221-382]) was higher than that of UTE MRI scans (median, 9.3 [IQR, 6.6-35]; P < .001). The median signal-to-noise ratio was similar between synthetic and real CT (88 [IQR, 84-92] vs 88 [IQR, 86-91]; P = .96). Synthetic CT had a lower noise level than real CT (median score, 26 [IQR, 22-30] vs 42 [IQR, 32-50]; P < .001) and the lowest level of artifacts (median score, 0 [IQR, 0-0]; P < .001). The concordance between Bhalla scores for synthetic and real CT images was almost perfect (intraclass correlation coefficient, ≥0.92). Conclusion Synthetic CT images showed almost perfect concordance with real CT images for the depiction of CF-related pulmonary alterations and had better image quality than UTE MRI. Clinical trial registration no. NCT03357562 © RSNA, 2023 Supplemental material is available for this article. See also the editorial by Schiebler and Glide-Hurst in this issue.
