Can AI Detect What Is Not Injected? Evaluation of Lesion Detection in Virtual Contrast-Enhanced Breast MRI Using a Large-Scale AI Model Trained on GBCA-Enhanced Data

Heidarikahkesh S, Schreiter H, George A, Nguyen TT, Skwierawska D, Brock L, Hadler D, Uder M, Laun FB, Ehring C, Graber J, Döppmann L, Horishnyi I, Kapsner L, Ohlmeyer S, Liebert A, Bickelhaupt S (2026)

Publication Type: Journal article

Publication year: 2026

Journal

Tomography MDPI Publishing

Book Volume: 12

Article Number: 105

Journal Issue: 7

DOI: 10.3390/tomography12070105

Abstract

Background/Objectives: Artificial intelligence (AI) can support lesion detection in gadolinium-based contrast agent-enhanced (GBCA-enhanced) breast MRI. However, its effectiveness on virtual contrast-enhanced (vCE) images remains unclear. This feasibility study evaluated the publicly available MAMA-MIA nnU-Net model trained on GBCA-enhanced data using an independent cohort of both GBCA-enhanced and vCE breast MRI. Methods: This IRB-approved retrospective study included the publicly available nnU-Net model trained on n = 1506 MAMA-MIA breast MRI scans and a cohort of n = 2126 in-house 3T breast MRI scans. A generative adversarial network (Pix2Pix-GAN) was developed on n = 1870 of the in-house scans and used to generate vCE data on the remaining independent n = 256 in-house cases. The MAMA-MIA nnU-net was applied to both GBCA-enhanced (GBCA) and corresponding vCE images. Ground-truth segmentations of malignant lesions served to calculate the Dice score, Hausdorff distance, and lesion dimension differences. Results: The final test set comprised n = 250 cases (n = 69 malignant, n = 181 benign). Lesion detection rates were 91% (n = 63/n = 69; 95% confidence interval (CI): 82.3–96.0%) for GBCA and 84% (n = 58/n = 69; 95% CI: 73.7–90.9%) for vCE. Two lesions missed in GBCA were identified by vCE. The Hausdorff distances were similar (GBCA: 6.4 (IQR: 3.2–9.3; 95% CI: 5.2–7.8) mm; vCE: 6.7 (IQR: 3.9–9.7; 95% CI: 5.3–8.0) mm, p = 0.564). The Dice scores showed minor differences (GBCA: 0.829 (IQR: 0.723–0.900; 95% CI: 0.786–0.865) vs. vCE: 0.826 (IQR: 0.720–0.857; 95% CI: 0.770–0.836); p < 0.001). vCE images had slightly higher non-target tissue segmentation (median 6072 mm³ vs. 5754 mm³). Conclusions: A GBCA-trained algorithm demonstrated some cross-domain transferability to vCE images, albeit with a reduced case-level sensitivity of 84% (95% CI: 73.7–90.9%) vs. 91% (95% CI: 82.3–96.0%). Based on these preliminary results, further research, including larger cohorts and more diverse datasets, is warranted.

Authors with CRIS profile

Shirin Heidarikahkesh Institute of Radiology Hannes Schreiter Institute of Radiology Aju George Institute of Radiology Tri-Thien Nguyen Institute of Radiology Dominika Skwierawska Institute of Radiology Luise Brock Institute of Radiology Dominique Hadler Institute of Radiology Michael Uder Lehrstuhl für Diagnostische Radiologie Frederik Bernd Laun Institute of Radiology Johanna Graber Professur für Experimentelle Nieren- und Kreislaufforschung Lorenz Döppmann Institute of Radiology Lorenz Kapsner Institute of Radiology Sabine Ohlmeyer Institute of Radiology Andrzej Liebert Institute of Radiology Sebastian Bickelhaupt Institute of Radiology

How to cite

APA:

Heidarikahkesh, S., Schreiter, H., George, A., Nguyen, T.-T., Skwierawska, D., Brock, L.,... Bickelhaupt, S. (2026). Can AI Detect What Is Not Injected? Evaluation of Lesion Detection in Virtual Contrast-Enhanced Breast MRI Using a Large-Scale AI Model Trained on GBCA-Enhanced Data. Tomography, 12(7). https://doi.org/10.3390/tomography12070105

MLA:

Heidarikahkesh, Shirin, et al. "Can AI Detect What Is Not Injected? Evaluation of Lesion Detection in Virtual Contrast-Enhanced Breast MRI Using a Large-Scale AI Model Trained on GBCA-Enhanced Data." Tomography 12.7 (2026).

BibTeX: Download