20 March 2015 Automatic breast density classification using a convolutional neural network architecture search procedure
Author Affiliations +
Abstract
Breast parenchymal density is considered a strong indicator of breast cancer risk and therefore useful for preventive tasks. Measurement of breast density is often qualitative and requires the subjective judgment of radiologists. Here we explore an automatic breast composition classification workflow based on convolutional neural networks for feature extraction in combination with a support vector machines classifier. This is compared to the assessments of seven experienced radiologists. The experiments yielded an average kappa value of 0.58 when using the mode of the radiologists’ classifications as ground truth. Individual radiologist performance against this ground truth yielded kappa values between 0.56 and 0.79.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Pablo Fonseca, Pablo Fonseca, Julio Mendoza, Julio Mendoza, Jacques Wainer, Jacques Wainer, Jose Ferrer, Jose Ferrer, Joseph Pinto, Joseph Pinto, Jorge Guerrero, Jorge Guerrero, Benjamin Castaneda, Benjamin Castaneda, } "Automatic breast density classification using a convolutional neural network architecture search procedure", Proc. SPIE 9414, Medical Imaging 2015: Computer-Aided Diagnosis, 941428 (20 March 2015); doi: 10.1117/12.2081576; https://doi.org/10.1117/12.2081576
PROCEEDINGS
8 PAGES


SHARE
Back to Top