Although contrast-enhanced (CE) breast MRI is an important tool for cancer detection, intravenous gadolinium administration introduces additional considerations for patients and clinical workflows. AI based virtual contrast enhanced (VCE) MRI could help identify patients for whom acquired CE imaging may be avoidable without compromising diagnostic performance. We developed a framework that combines non contrast (NC) and VCE MRI predictions for cancer detection. On the held-out test set, cancer detection using NC MRI alone achieved an AUROC of 0.865. Combining the predictions from NC and VCE MRI improved AUROC to 0.901. Building on this complementary predictive value, we evaluated patient-level routing to progressively replace acquired CE examinations with the NC plus VCE pathway, prioritizing patients with the most confident NC predictions. This simulation suggests that diagnostic performance can be largely preserved while limiting acquired CE imaging to approximately 40% of patients. Together, these findings demonstrate the complementary value of VCE MRI and suggest its potential to support selective contrast use in breast cancer screening.
Figures & tables
Figure 1: Qualitative examples of virtual contrast enhanced MRI. Blue outlines indicate annotated lesions.
Exp.
Input / strategy
Held-out test set
Dataset-specific AUROC
AUROC
AUPRC
DUKE
MAMAMIA
ODELIA
1
NC MRI (NC Classifier)
0.865±0.007
0.831±0.020
0.861±0.005
0.897±0.017
0.795±0.012
2
VCE MRI (CE Classifier)
0.866±0.007
0.841±0.005
0.864±0.014
0.891±0.011
0.799±0.016
3
VCE MRI (VCE Classifier)
0.883±0.010
0.854±0.022
0.882±0.003
0.908±0.007
0.833±0.029
4
CE MRI (CE Classifier)
0.945±0.003
0.927±0.007
0.950±0.013
0.966±0.001
0.900±0.010
5
NC + VCE (NC + CE Classifiers)
0.901±0.005
0.874±0.005
0.888±0.008
0.939±0.012
0.841±0.003
Table 1: Cancer detection performance on the held-out test set, overall and by source dataset. Overall AUROC and AUPRC are reported as mean ± SD across three classifier repeats.
Figure 2: Selective contrast-sparing. AUROC and AUPRC versus the proportion of patients assigned to the NC plus VCE pathway. Shaded regions indicate 95% randomization intervals under random patient assignment.
Virtual contrast enhancement (VCE) synthesizes enhanced breast MR images from pre-contrast acquisitions. Modern latent generators offer strong image priors, but their bounded natural-image autoencoders conflict with the non-canonical intensity scale of MRI. We show that the upper bound can alter radiomic fidelity before generation, while scaling source and target independently creates a coordinate inconsistency. We propose Predictive Enhancement Calibration (PEC), which represents each pair in a shared, case-adaptive coordinate during training and predicts its unavailable upper endpoint from the pre-contrast image at inference. We integrate PEC with a pretrained FLUX latent flow transformer via parameter-efficient reference conditioning. Target round trips first isolate representation loss before generation; near-matched conditional models then compare PEC with fixed-wide and separate coordinates under comparable training budgets and backbone settings. On the fixed internal MAMA100 development cohort, PEC improves all eight point estimates in this source-only VCE setting, with paired evidence strongest for MSE and LPIPS.\noindentCode: https://github.com/tanlei0/pec-breast-mri-vce
Qin Lei, Hao Wu
Center for Big Data and Intelligent Medicine, The First Affiliated Hospital of Chongqing Medical University, Chongqing, China · Key Laboratory of Digital Health and Intelligent Medicine, Chongqing Municipal Health Commission, Chongqing, China · Chongqing Translational Medicine Center, Chongqing, China
Dynamic contrast-enhanced breast MRI (DCE-MRI) is rich in anatomical and perfusion information, but its reliance on gadolinium-based contrast agents raises safety concerns and adds cost. Virtual contrast enhancement, synthesizing post-contrast from pre-contrast images, is a promising alternative. We address the MAMA-SYNTH challenge task of predicting peak-enhancement breast MRI. Rather than adopting the full machinery of diffusion or flow matching, we observe that under a rectified, straight-line path the generative process collapses to a single difference prediction: the synthetic peak image is the pre-contrast image plus a predicted enhancement map, recovered in one forward pass. Around this we build Anguinus Sculpturae, a compositional pipeline in which nnU-Net segmentations of lesion, foreground and breast region guide two generators - one optimized for global fidelity, one for lesion structure through an asymmetric Tversky term routed via a frozen segmenter - composited region-wise with Gaussian-weighted blending. On the held-out Duke subset of MAMA-MIA our model achieves the best FRD and Dice among all evaluated variants, showing that single-step difference prediction with segmentation guidance suffices to recover both global fidelity and lesion structure. Code is available at https://github.com/MIC-DKFZ/AnguinusSculpturae.
Benjamin Hamm, Nico Albert Disch, Maximilian Rokuss +3
German Cancer Research Center (DKFZ) Heidelberg, Division of Medical Image Computing, Germany · Medical Faculty, Heidelberg University, Germany · Faculty of Mathematics and Computer Science, Heidelberg University, Germany +3
Dynamic contrast-enhanced (DCE) imaging is the gold standard technique for the detection and characterization of breast cancer using magnetic resonance imaging (MRI). However, DCE-MRI requires long acquisition times and the administration of contrast into the bloodstream, which can cause allergic reactions. Alternatively, diffusion-weighted MRI (DW-MRI) is a standard complementary technique for breast MRI that does not require contrast, has shorter acquisition times, and enables calculation of apparent diffusion coefficient (ADC) maps that correlate with tumor cellularity. Yet, despite these technical advantages, deep learning research has focused on DCE-based models and has barely explored the tumor detection performance of DW-MRI and ADC maps either in combination with DCE-MRI or as standalone alternatives. Here, we evaluate the application of different state-of-the-art deep learning techniques for detection and segmentation of breast cancer using ADC-only images. This is, to our knowledge, the first comprehensive evaluation of ADC-only breast cancer pipelines for classification, detection, and segmentation tasks.
Pablo García Marcos, Paula Puerta Gonzĺez, Guillermo Lorenzo +4
Computer Sciences Department, University of Oviedo, Asturias, Spain · Biomedical Engineering Center (BME), University of Oviedo, Asturias, Spain · Electrical Engineering Department, University of Oviedo, Asturias, Spain +6