We use cookies to understand how you use our site and to improve your experience. This includes personalizing content and advertising. To learn more, click here. By continuing to use our site, you accept our use of cookies. Cookie Policy.
Features Partner Sites Information LinkXpress
Sign In
Advertise with Us
Ampronix,  Inc

Download Mobile App




Machine Learning Helps Improve Mammography Workflow Efficiency

By Medimaging International staff writers
Posted on 22 Jun 2019
Print article
Image: New research shows machine learning can reduce the number of mammograms a radiologist needs to read (Photo courtesy of HealthManagement.org).
Image: New research shows machine learning can reduce the number of mammograms a radiologist needs to read (Photo courtesy of HealthManagement.org).
A team of researchers from the University of California Los Angeles (California, LA, USA) has demonstrated that machine learning can reduce the number of mammograms a radiologist needs to read by using a machine learning classifier to correctly identify normal mammograms and select the uncertain and abnormal examinations for radiological interpretation.

The researchers created an autonomous radiologist assistant (AURA), which was a modified version of a previous clinical decision support system, The aim was to determine if AURA could diagnose mammograms as negative while maintaining diagnostic accuracy and noting which scans would a radiologist would still require to read.

For the study, a research data set from over 7,000 women who were recalled for assessment at six UK National Health Service Breast Screening Program centers was used. The researchers used a convolutional neural network in conjunction with multi-task learning to extract imaging features from mammograms that mimic the radiological assessment provided by a radiologist, the patient’s non-imaging features, and pathology outcomes. The researchers then used a deep neural network to concatenate and fuse multiple mammogram views to predict both a diagnosis and a recommendation of whether or not additional radiological assessment was needed.

The study used a ten-fold cross-validation on 2,000 randomly selected patients from the data set, while using the remainder of the data set for convolutional neural network training. AURA maintained an acceptable negative predictive value of 0.99 while identifying 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.

The researchers concluded that machine learning can be leveraged to successfully reduce the number of normal mammograms that radiologists need to read without degrading diagnostic accuracy.

Related Links:
University of California Los Angeles


Print article
Radcal

Channels

Industry News

view channel
Image: A demonstration featuring ACR AI-LAB will allow Summit attendees to gain a better understanding of how radiologists can use ACR AI-LAB tools to learn the basics of AI and participate in the creation, evaluation and use of health care AI (Photo courtesy of ACR).

Imaging Informatics Summit Highlights Impact of AI Technologies on Patient Care

The 2019 Imaging Informatics Summit organized by the American College of Radiology {(ACR) Reston, VA, USA} will be held in Washington, D.C., USA, on October 5–6, 2019, and will focus on the role that artificial... Read more
Copyright © 2000-2019 Globetech Media. All rights reserved.