Deep learning-based generation of synthetic multiphasic MRI in hepatocellular carcinoma and cirrhosis

Abosabie, Sara A.; Abosabie, Salma A.S.; Dai, Weicheng; Yang, Junlin; Gross, Moritz; Weinreb, Jeffrey; Revzin, Margarita V.; Parmar, Gaurav; You, Chenyu; Lin, MingDe; Gaddum, Olivia; Gebauer, Bernhard; Savic, Lynn Jeanette; Madoff, David Craig; Duncan, James S.; Chapiro, Julius

Deep learning-based generation of synthetic multiphasic MRI in hepatocellular carcinoma and cirrhosis

Tools

Preview	PDF (Original Article) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader 6MB
	Other (Supplementary Data) 17MB

Item Type:	Article
Title:	Deep learning-based generation of synthetic multiphasic MRI in hepatocellular carcinoma and cirrhosis
Creators:	Abosabie, Sara A., Abosabie, Salma A.S., Dai, Weicheng, Yang, Junlin, Gross, Moritz, Weinreb, Jeffrey, Revzin, Margarita V., Parmar, Gaurav, You, Chenyu, Lin, MingDe, Gaddum, Olivia, Gebauer, Bernhard, Savic, Lynn Jeanette ORCID: https://orcid.org/0000-0003-2115-6728, Madoff, David Craig, Duncan, James S. and Chapiro, Julius
Abstract:	BACKGROUND & AIMS: There is growing interest in reducing contrast medium use and the lengthy scan duration in liver imaging. This proof of concept study evaluated the feasibility of deep learning-based generation of synthetic 3D liver contrast-enhanced multiphasic magnetic resonance imaging (MRI) exams, which are similar to ground-truth exams in hepatocellular carcinoma and cirrhosis. METHODS: MRI exams from patients with hepatocellular carcinoma (HCC) or cirrhosis at a single academic center were retrospectively collected. A 3D cycle-consistent generative adversarial network was trained to generate synthetic 3D T1-weighted contrast-enhanced multiphasic liver MRI exams, including arterial, portal venous, delayed, and hepatobiliary phases, using two pre-contrast T1-weighted and T2-weighted input phases. Quantitative performance evaluated similarity, error, and overlap metrics between synthetic and ground-truth exams. For the qualitative multireader study, three blinded radiologists assessed the ground-truth and synthetic MRI exams using a comprehensive questionnaire. Questionnaire tasks 1–5 comprised: visual Turing test (ground-truth vs. synthetic nature), image quality, anatomic accuracy, disease diagnosability, and artifacts. Task 6 comprised Liver Imaging Reporting and Data System features. RESULTS: The study included 3,198 MRI phases from 533 MRI exams from 185 patients with HCC (mean age, 62.1 years ± 9.7 [SD]; 141 men) and 182 patients with cirrhosis (54.4 years ± 10.0; 111 men). Synthetic MRI exams achieved high quantitative and qualitative similarity to ground-truth exams. Quantitative analysis demonstrated high structural similarity index (0.86 ± 0.03), overlap (0.97 ± 0.05), and low symmetric mean absolute percent error (0.63 ± 0.23%). The qualitative multireader study showed no significant difference in tasks 1–5 (p = 0.06–0.50) and high performance metrics in task 6 (accuracy: 0.76–0.86; precision: 0.96–1.00) with moderate to perfect Fleiss’s Kappa inter-rater agreement (0.58–1.00, p <0.001). CONCLUSIONS: Deep learning enabled the generation of synthetic 3D liver contrast-enhanced multiphasic MRI exams from precontrast sequences, achieving high quantitative and qualitative similarity to ground-truth images.
Keywords:	Deep Learning, Generative Adversarial Networks, Synthetic 3D Contrast-Enhanced Liver MRI, Contrastenhanced Multiphasic Liver MRI, Hepatocellular Carcinoma, Cirrhosis
Source:	JHEP Reports
ISSN:	2589-5559
Publisher:	Elsevier / European Association for the Study of the Liver (EASL)
Volume:	8
Number:	7
Page Range:	101813
Date:	July 2026
Official Publication:	https://doi.org/10.1016/j.jhepr.2026.101813
PubMed:	View item in PubMed

Repository Staff Only: item control page

Download Statistics

Downloads

Downloads per month over past year