Improving localization-based approaches for breast cancer screening exam classification

08/01/2019
by   Thibault Févry, et al.
13

We trained and evaluated a localization-based deep CNN for breast cancer screening exam classification on over 200,000 exams (over 1,000,000 images). Our model achieves an AUC of 0.919 in predicting malignancy in patients undergoing breast cancer screening, reducing the error rate of the baseline (Wu et al., 2019a) by 23 benign and malignant findings, providing interpretable predictions.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset