Screening Mammogram Classification with Prior Exams

Radiologists typically compare a patient's most recent breast cancer screening exam to their previous ones in making informed diagnoses. To reflect this practice, we propose new neural network models that compare pairs of screening mammograms from the same patient. We train and evaluate our pro...

Full description

Saved in:
Bibliographic Details
Main Authors Park, Jungkyu, Phang, Jason, Shen, Yiqiu, Wu, Nan, Kim, S. Gene, Moy, Linda, Cho, Kyunghyun, Geras, Krzysztof J
Format Journal Article
LanguageEnglish
Published 30.07.2019
Subjects
Computer Science - Computer Vision and Pattern Recognition
Computer Science - Learning
Statistics - Machine Learning
Online AccessGet full text

Cover

More Information
Summary:Radiologists typically compare a patient's most recent breast cancer screening exam to their previous ones in making informed diagnoses. To reflect this practice, we propose new neural network models that compare pairs of screening mammograms from the same patient. We train and evaluate our proposed models on over 665,000 pairs of images (over 166,000 pairs of exams). Our best model achieves an AUC of 0.866 in predicting malignancy in patients who underwent breast cancer screening, reducing the error rate of the corresponding baseline.
Bibliography:MIDL/2019/ExtendedAbstract/HkgCdUaMq4
DOI:10.48550/arxiv.1907.13057