Style Randomization Improves the Robustness of Breast Density Estimation in MR Images

Goksenin Yuksel, Koen Eppenhof, Jaap Kroes, Marcel Worring
Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, PMLR 250:1841-1850, 2024.

Abstract

Breast density, a crucial risk factor for future breast cancer development, is defined bythe ratio of fat to fibro-glandular tissue (FGT) in the breast. Accurate breast and FGTsegmentation is essential for robust density estimation. Previous research on FGT segmen-tation in MRI has highlighted the significance of training on both images with and withoutfat suppression to enhance network’s robustness. In this study, we propose a novel dataaugmentation technique to further exploit the multi-modal training setup motivated by theresearch in style randomization. We demonstrate that the network trained with the pro-posed augmentation is resilient to variations in fat content, showcasing improved robustnesscompared to solely training with multi-modal data. Our method effectively improves FGTsegmentation, thereby enhancing the overall reliability of breast density estimation

Cite this Paper

BibTeX
@InProceedings{pmlr-v250-yuksel24a, title = {Style Randomization Improves the Robustness of Breast Density Estimation in MR Images}, author = {Yuksel, Goksenin and Eppenhof, Koen and Kroes, Jaap and Worring, Marcel}, booktitle = {Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning}, pages = {1841--1850}, year = {2024}, editor = {Burgos, Ninon and Petitjean, Caroline and Vakalopoulou, Maria and Christodoulidis, Stergios and Coupe, Pierrick and Delingette, Hervé and Lartizien, Carole and Mateus, Diana}, volume = {250}, series = {Proceedings of Machine Learning Research}, month = {03--05 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v250/main/assets/yuksel24a/yuksel24a.pdf}, url = {https://proceedings.mlr.press/v250/yuksel24a.html}, abstract = {Breast density, a crucial risk factor for future breast cancer development, is defined bythe ratio of fat to fibro-glandular tissue (FGT) in the breast. Accurate breast and FGTsegmentation is essential for robust density estimation. Previous research on FGT segmen-tation in MRI has highlighted the significance of training on both images with and withoutfat suppression to enhance network’s robustness. In this study, we propose a novel dataaugmentation technique to further exploit the multi-modal training setup motivated by theresearch in style randomization. We demonstrate that the network trained with the pro-posed augmentation is resilient to variations in fat content, showcasing improved robustnesscompared to solely training with multi-modal data. Our method effectively improves FGTsegmentation, thereby enhancing the overall reliability of breast density estimation} }
Endnote
%0 Conference Paper %T Style Randomization Improves the Robustness of Breast Density Estimation in MR Images %A Goksenin Yuksel %A Koen Eppenhof %A Jaap Kroes %A Marcel Worring %B Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning %C Proceedings of Machine Learning Research %D 2024 %E Ninon Burgos %E Caroline Petitjean %E Maria Vakalopoulou %E Stergios Christodoulidis %E Pierrick Coupe %E Hervé Delingette %E Carole Lartizien %E Diana Mateus %F pmlr-v250-yuksel24a %I PMLR %P 1841--1850 %U https://proceedings.mlr.press/v250/yuksel24a.html %V 250 %X Breast density, a crucial risk factor for future breast cancer development, is defined bythe ratio of fat to fibro-glandular tissue (FGT) in the breast. Accurate breast and FGTsegmentation is essential for robust density estimation. Previous research on FGT segmen-tation in MRI has highlighted the significance of training on both images with and withoutfat suppression to enhance network’s robustness. In this study, we propose a novel dataaugmentation technique to further exploit the multi-modal training setup motivated by theresearch in style randomization. We demonstrate that the network trained with the pro-posed augmentation is resilient to variations in fat content, showcasing improved robustnesscompared to solely training with multi-modal data. Our method effectively improves FGTsegmentation, thereby enhancing the overall reliability of breast density estimation
APA
Yuksel, G., Eppenhof, K., Kroes, J. & Worring, M.. (2024). Style Randomization Improves the Robustness of Breast Density Estimation in MR Images. Proceedings of The 7nd International Conference on Medical Imaging with Deep Learning, in Proceedings of Machine Learning Research 250:1841-1850 Available from https://proceedings.mlr.press/v250/yuksel24a.html.

Related Material