@article{wu2018expert,
author = {Wu, Jimmy and Peck, Diondra and Hsieh, Scott and Dialani, Vandana and Lehman, Constance D. and Zhou, Bolei and Syrgkanis, Vasilis and Mackey, Lester and Patterson, Genevieve},
title = {Expert identification of visual primitives used by CNNs during mammogram classification},
year = {2018},
month = {February},
abstract = {This work interprets the internal representations of deep neural networks trained for classifying diseased tissue in 2D mammograms. We propose an expert-in-the-loop interpretation method to label the behavior of internal units in convolutional neural networks (CNNs). Expert radiologists identify that the visual patterns detected by the units are correlated with meaningful medical phenomena such as mass tissue and calcificated vessels. We demonstrate that several trained CNN models are able to produce explanatory descriptions to support the final classification decisions. We view this as an important first step toward interpreting the internal representations of medical classification CNNs and explaining their predictions.},
url = {http://approjects.co.za/?big=en-us/research/publication/expert-identification-of-visual-primitives-used-by-cnns-during-mammogram-classification/},
journal = {Medical Imaging 2018: Computer-Aided Diagnosis, Proc. of SPIE Vol. 10575, 105752T},
}