Authors: Richard Osuala, Smriti Joshi, Apostolia Tsirikoglou, Lidia Garrucho, Walter H.L. Pinaya, Daniel M. Lang, Julia A. Schnabel, Oliver Diaz, Karim Lekadir

Published on: September 27, 2024

Impact Score: 8.0

Arxiv code: Arxiv:2409.18872

Summary

• What is new: A new method for generating virtual contrast-enhanced breast MRI images using AI, which doesn’t require traditional contrast agents.
• Why this is important: Traditional DCE-MRI uses contrast agents that can pose health risks.
• What the research proposes: Using a conditional generative adversarial network (cGAN) to predict contrast-enhanced MRI images from non-contrast-enhanced MRIs.
• Results: The approach produces realistic contrast-enhanced MRI sequences that can aid in tumor localization and characterization, potentially benefiting patients who cannot use contrast agents.

Technical Details

Technological frameworks used: Conditional Generative Adversarial Network (cGAN)

Models used: cGANs for image generation

Data used: Non-contrast-enhanced MRI and DCE-MRI images for training and validation

Potential Impact

Healthcare providers, medical imaging companies, especially those focused on MRI technology, and pharmaceutical companies involved in producing contrast agents.

Want to implement this idea in a business?

We have generated a startup concept here: VCE-BreastTech.