Simulating Dynamic Tumor Contrast Enhancement in Breast MRI using Conditional Generative Adversarial Networks

2024-09-27

arXiv.org

AI Summary

This study addresses the health risks associated with gadolinium-based contrast agents in dynamic contrast-enhanced breast MRI (DCE-MRI) by proposing a contrast-free virtual enhancement method. Leveraging a conditional generative adversarial network (cGAN), the approach jointly models multi-temporal DCE-MRI sequence synthesis, incorporating a multi-scale discriminator and temporal consistency constraints to ensure physiologically plausible dynamics. We introduce SAMe—a task-oriented, weighted evaluation metric—and present the first end-to-end validation of synthesized DCE sequences for tumor segmentation: achieving a Dice score of 0.82±0.05, SAMe of 0.79, and PSNR/SSIM/NCC values comparable to real acquisitions. Results demonstrate that the method preserves both visual realism and quantitative fidelity while enabling reliable tumor localization and characterization, indicating strong potential for clinical translation.

Technology Category

• Computer Vision: Generative Adversarial Networks (GANs) for Vision
• Machine Learning: Deep Generative Models & Autoencoders
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Web Mining and Content Analysis: Web data generation and simulation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

This paper presents a method for virtual contrast enhancement in breast MRI, offering a promising non-invasive alternative to traditional contrast agent-based DCE-MRI acquisition. Using a conditional generative adversarial network, we predict DCE-MRI images, including jointly-generated sequences of multiple corresponding DCE-MRI timepoints, from non-contrast-enhanced MRIs, enabling tumor localization and characterization without the associated health risks. Furthermore, we qualitatively and quantitatively evaluate the synthetic DCE-MRI images, proposing a multi-metric Scaled Aggregate Measure (SAMe), assessing their utility in a tumor segmentation downstream task, and conclude with an analysis of the temporal patterns in multi-sequence DCE-MRI generation. Our approach demonstrates promising results in generating realistic and useful DCE-MRI sequences, highlighting the potential of virtual contrast enhancement for improving breast cancer diagnosis and treatment, particularly for patients where contrast agent administration is contraindicated.

Problem

• Simulating DCE-MRI images without contrast agents
• Predicting tumor localization from non-contrast MRI
• Evaluating synthetic DCE-MRI for cancer diagnosis

Innovation

• Conditional GANs for virtual contrast enhancement
• Non-contrast MRI to DCE-MRI sequence prediction
• Multi-metric SAMe for synthetic image evaluation