Translator Disclaimer
Paper
22 May 2020 Deep learning to calculate breast density from processed mammography images
Author Affiliations +
Proceedings Volume 11513, 15th International Workshop on Breast Imaging (IWBI2020); 115131C (2020) https://doi.org/10.1117/12.2561278
Event: Fifteenth International Workshop on Breast Imaging, 2020, Leuven, Belgium
Abstract
Purpose: To calculate continuous breast density measures from processed images using deep learning. Method: Processed and unprocessed mammograms were collected for 3251 women attending the UK NHS Breast Screening Programme (NHSBSP). The breast density measures investigated included volumetric breast density, fibroglandular volume and breast volume. The ground truth for these measures was calculated using Volpara software on unprocessed mammograms. A deep learning model was trained and validated to predict each breast density measure. The performance of the deep learning model was assessed using a hold-out test set. Results: The breast volume and fibroglandular volume predicted with deep learning were strongly correlated with the ground truth (r=0.96 and r=0.88 respectively). The volumetric breast density had a Pearson correlation coefficient of 0.90. Conclusions: It is possible to predict volumetric breast density from processed images using deep learning.
© (2020) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Lucy M. Warren, Peter Harris, Sandra Gomes, Matthew Trumble, Mark D. Halling-Brown, David R. Dance, Louise Wilkinson, Ros Given-Wilson, and Kenneth C. Young "Deep learning to calculate breast density from processed mammography images", Proc. SPIE 11513, 15th International Workshop on Breast Imaging (IWBI2020), 115131C (22 May 2020); https://doi.org/10.1117/12.2561278
PROCEEDINGS
7 PAGES


SHARE
Advertisement
Advertisement
Back to Top