Normalization of breast MRIs using cycle-consistent generative adversarial networks
Related Experiment Video
Updated: Oct 31, 2025
Tracking the Mammary Architectural Features and Detecting Breast Cancer with Magnetic Resonance Diffusion Tensor Imaging
Published on: December 15, 2014
Gourav Modanwal1, Adithya Vellal2, Maciej A Mazurowski1
1Department of Radiology, Duke University, Durham, NC, USA.
Objectives:
Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) is widely used to complement ultrasound examinations and x-ray mammography for early detection and diagnosis of breast cancer. However, images generated by various MRI scanners (e.g., GE Healthcare, and Siemens) differ both in intensity and noise distribution, preventing algorithms trained on MRIs from one scanner to generalize to data from other scanners. In this work, we propose a method to solve this problem by normalizing images between various scanners.
Methods:
MRI normalization is challenging because it requires normalizing intensity values and mapping noise distributions between scanners. We utilize a cycle-consistent generative adversarial network to learn a bidirectional mapping and perform normalization between MRIs produced by GE Healthcare and Siemens scanners in an unpaired setting. Initial experiments demonstrate that the traditional CycleGAN architecture struggles to preserve the anatomical structures of the breast during normalization. Thus, we propose two technical innovations in order to preserve both the shape of the breast as well as the tissue structures within the breast. First, we incorporate mutual information loss during training in order to ensure anatomical consistency. Second, we propose a modified discriminator architecture that utilizes a smaller field-of-view to ensure the preservation of finer details in the breast tissue.
Results:
Quantitative and qualitative evaluations show that the second innovation consistently preserves the breast shape and tissue structures while also performing the proper intensity normalization and noise distribution mapping.
Conclusion:
Our results demonstrate that the proposed model can successfully learn a bidirectional mapping and perform normalization between MRIs produced by different vendors, potentially enabling improved diagnosis and detection of breast cancer. All the data used in this study are publicly available at https://wiki.cancerimagingarchive.net/pages/viewpage.action?pageId=70226903.
