Trent Kyono1, Fiona J Gilbert2, Mihaela van der Schaar3. 1. Department of Computer Science, University of California Los Angeles, Los Angeles, California. Electronic address: tmkyono@gmail.com. 2. Department of Radiology, University of Cambridge School of Clinical Medicine, Cambridge, United Kingdom; NIHR Cambridge Biomedical Research Center, Cambridge, United Kingdom. 3. Department of Computer Science, University of California Los Angeles, Los Angeles, California.
Abstract
OBJECTIVE: The aim of this study was to determine whether machine learning could reduce the number of mammograms the radiologist must read by using a machine-learning classifier to correctly identify normal mammograms and to select the uncertain and abnormal examinations for radiological interpretation. METHODS: Mammograms in a research data set from over 7,000 women who were recalled for assessment at six UK National Health Service Breast Screening Program centers were used. A convolutional neural network in conjunction with multitask learning was used to extract imaging features from mammograms that mimic the radiological assessment provided by a radiologist, the patient's nonimaging features, and pathology outcomes. A deep neural network was then used to concatenate and fuse multiple mammogram views to predict both a diagnosis and a recommendation of whether or not additional radiological assessment was needed. RESULTS: Ten-fold cross-validation was used on 2,000 randomly selected patients from the data set; the remainder of the data set was used for convolutional neural network training. While maintaining an acceptable negative predictive value of 0.99, the proposed model was able to identify 34% (95% confidence interval, 25%-43%) and 91% (95% confidence interval: 88%-94%) of the negative mammograms for test sets with a cancer prevalence of 15% and 1%, respectively. CONCLUSION: Machine learning was leveraged to successfully reduce the number of normal mammograms that radiologists need to read without degrading diagnostic accuracy.
OBJECTIVE: The aim of this study was to determine whether machine learning could reduce the number of mammograms the radiologist must read by using a machine-learning classifier to correctly identify normal mammograms and to select the uncertain and abnormal examinations for radiological interpretation. METHODS: Mammograms in a research data set from over 7,000 women who were recalled for assessment at six UK National Health Service Breast Screening Program centers were used. A convolutional neural network in conjunction with multitask learning was used to extract imaging features from mammograms that mimic the radiological assessment provided by a radiologist, the patient's nonimaging features, and pathology outcomes. A deep neural network was then used to concatenate and fuse multiple mammogram views to predict both a diagnosis and a recommendation of whether or not additional radiological assessment was needed. RESULTS: Ten-fold cross-validation was used on 2,000 randomly selected patients from the data set; the remainder of the data set was used for convolutional neural network training. While maintaining an acceptable negative predictive value of 0.99, the proposed model was able to identify 34% (95% confidence interval, 25%-43%) and 91% (95% confidence interval: 88%-94%) of the negative mammograms for test sets with a cancer prevalence of 15% and 1%, respectively. CONCLUSION: Machine learning was leveraged to successfully reduce the number of normal mammograms that radiologists need to read without degrading diagnostic accuracy.
Authors: Sarah E Hickman; Ramona Woitek; Elizabeth Phuong Vi Le; Yu Ri Im; Carina Mouritsen Luxhøj; Angelica I Aviles-Rivero; Gabrielle C Baxter; James W MacKay; Fiona J Gilbert Journal: Radiology Date: 2021-10-19 Impact factor: 11.105