Use of clinical MRI maximum intensity projections for improved breast lesion classification with deep convolutional neural networks

Natalia O. Antropova; Hiroyuki Abe; Maryellen L. Giger

doi:10.1117/1.JMI.5.1.014503

5 February 2018 Use of clinical MRI maximum intensity projections for improved breast lesion classification with deep convolutional neural networks

Natalia O. Antropova, Hiroyuki Abe, Maryellen L. Giger

Author Affiliations +

Journal of Medical Imaging, Vol. 5, Issue 1, 014503 (February 2018). https://doi.org/10.1117/1.JMI.5.1.014503

Abstract

Deep learning methods have been shown to improve breast cancer diagnostic and prognostic decisions based on selected slices of dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). However, incorporation of volumetric and temporal components into DCE-MRIs has not been well studied. We propose maximum intensity projection (MIP) images of subtraction MRI as a way to simultaneously include four-dimensional (4-D) images into lesion classification using convolutional neural networks (CNN). The study was performed on a dataset of 690 cases. Regions of interest were selected around each lesion on three MRI presentations: (i) the MIP image generated on the second postcontrast subtraction MRI, (ii) the central slice of the second postcontrast MRI, and (iii) the central slice of the second postcontrast subtraction MRI. CNN features were extracted from the ROIs using pretrained VGGNet. The features were utilized in the training of three support vector machine classifiers to characterize lesions as malignant or benign. Classifier performances were evaluated with fivefold cross-validation and compared based on area under the ROC curve (AUC). The approach using MIPs [AUC=0.88(se=0.01)] outperformed that using central-slices of either second postcontrast MRIs [0.80(se=0.02)] or second postcontrast subtraction MRIs [AUC=0.84(se=0.02)], at statistically significant levels.

Citation Download Citation

Natalia O. Antropova, Hiroyuki Abe, and Maryellen L. Giger "Use of clinical MRI maximum intensity projections for improved breast lesion classification with deep convolutional neural networks," Journal of Medical Imaging 5(1), 014503 (5 February 2018). https://doi.org/10.1117/1.JMI.5.1.014503

Received: 10 October 2017; Accepted: 11 January 2018; Published: 5 February 2018

ACCESS THE FULL ARTICLE

JOURNAL ARTICLE
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

CITATIONS

Cited by 64 scholarly publications.

Explore citations on Lens.org

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Magnetic resonance imaging

Feature extraction

Breast

Image classification

Medical imaging

Convolutional neural networks

Breast cancer

Show All Keywords

RELATED CONTENT

Identifying metastatic breast tumors using textural kinetic features of a...
Proceedings of SPIE (March 20 2015)

Evaluating deep learning techniques for dynamic contrast enhanced MRI in...
Proceedings of SPIE (March 13 2019)

Computerized classification scheme for distinguishing between benign and malignant masses...
Proceedings of SPIE (May 22 2020)

Discriminating between benign and malignant breast tumors using 3D convolutional...
Proceedings of SPIE (March 13 2017)

Radiomics analysis of MRI for predicting molecular subtypes of breast...
Proceedings of SPIE (March 13 2019)

Comparison of 2D and 3D U Net breast lesion segmentations...
Proceedings of SPIE (February 15 2021)

Segmentation of suspicious lesions in dynamic contrast enhanced breast MR...
Proceedings of SPIE (March 29 2007)

Subscribe to Digital Library

Receive Erratum Email Alert

Show All Keywords

Keywords/Phrases

Search In:

Publication Years