Automated artificial intelligence quantification of fibroglandular tissue on breast MRI.

Abstract

e12071 Background: The objective of this study is to examine if a convolutional neural network can be utilized to automate breast fibroglandular tissue segmentation, a risk factor for breast cancer, on MRIs. Methods: This institutional review board approved study assessed retrospectively acquired MRI T1 pre-contrast image data for 238 patients. Ground truth parameters were derived through manual segmentation. A hybrid 3D/2D U-Net architecture was developed for fibroglandular tissue segmentation. The network was trained with T1 pre-contrast MRI data and their corresponding ground-truth labels. The analysis was started with image pre-processing. Each MRI volume was re-sampled and normalized using z-scores. Convolution operations reduced 3D volumes into a 2D slice in the contracting arm of the U-Net architecture. Results: A 5-fold cross validation was performed and the Dice similarity coefficient was used to assess the accuracy of fibroglandular tissue segmentation. Cross-validation results showed that the automated hybrid CNN approach resulted in a Dice similarity coefficient of 0.848 and a Pearson correlation of 0.961 in comparison to the ground-truth for fibroglandular breast tissue segmentation, which demonstrates high accuracy. Conclusions: The results demonstrate significant application of deep learning in accurately automating segmentation of breast fibroglandular tissue.