Deep-Learning-Based Semantic Labeling for 2D Mammography and Comparison of Complexity for Machine Learning Tasks

Machine learning has several potential uses in medical imaging for semantic labeling of images to improve radiologist workflow and to triage studies for review. The purpose of this study was to (1) develop deep convolutional neural networks (DCNNs) for automated classification of 2D mammography view...

Full description

Saved in:
Bibliographic Details
Published in:Journal of digital imaging 2019-08, Vol.32 (4), p.565-570
Main Authors: Yi, Paul H., Lin, Abigail, Wei, Jinchi, Yu, Alice C., Sair, Haris I., Hui, Ferdinand K., Hager, Gregory D., Harvey, Susan C.
Format: Article
Language:English
Subjects:
Artificial intelligence
Artificial neural networks
Automation
Breast
Breasts
Classification
Datasets
Deep learning
Density
Digital imaging
Image classification
Imaging
Labeling
Learning algorithms
Machine learning
Mammography
Medical imaging
Medicine
Medicine & Public Health
Neural networks
Original Paper
Radiology
Semantics
Task complexity
Workflow
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Machine learning has several potential uses in medical imaging for semantic labeling of images to improve radiologist workflow and to triage studies for review. The purpose of this study was to (1) develop deep convolutional neural networks (DCNNs) for automated classification of 2D mammography views, determination of breast laterality, and assessment and of breast tissue density; and (2) compare the performance of DCNNs on these tasks of varying complexity to each other. We obtained 3034 2D-mammographic images from the Digital Database for Screening Mammography, annotated with mammographic view, image laterality, and breast tissue density. These images were used to train a DCNN to classify images for these three tasks. The DCNN trained to classify mammographic view achieved receiver-operating-characteristic (ROC) area under the curve (AUC) of 1. The DCNN trained to classify breast image laterality initially misclassified right and left breasts (AUC 0.75); however, after discontinuing horizontal flips during data augmentation, AUC improved to 0.93 ( p  
ISSN:0897-1889
1618-727X
DOI:10.1007/s10278-019-00244-w