close
Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2018 Jan;5(1):014503.
doi: 10.1117/1.JMI.5.1.014503. Epub 2018 Feb 5.

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

Natalia Antropova  1 , Hiroyuki Abe  1 , Maryellen L Giger  1
Affiliations

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

Natalia Antropova et al. J Med Imaging (Bellingham). 2018 Jan.

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 [Formula: see text] outperformed that using central-slices of either second postcontrast MRIs [Formula: see text] or second postcontrast subtraction MRIs [Formula: see text], at statistically significant levels.

Keywords: breast cancer; convolutional neural networks; dynamic contrast-enhanced magnetic resonance imaging; four-dimensional data; maximum intensity projection.

PubMed Disclaimer

Figures

Fig. 1
Fig. 1
Example of a benign lesion. Full MRI images and ROIs for (a) the MIP image of the second postcontrast subtraction MRI, (b) the center slice of the second postcontrast MRI, and (c) the central slice of the second postcontrast subtraction MRI.
Fig. 2
Fig. 2
Example of a malignant lesion. Full MRI images and ROIs for (a) the MIP image of the second postcontrast subtraction MRI, (b) the center slice of the second postcontrast MRI, and (c) the central slice of the second postcontrast subtraction MRI.
Fig. 3
Fig. 3
Lesion classification pipeline.
Fig. 4
Fig. 4
Feature extraction methodology. Lesion ROIs were input into a pretrained VGGNet and features were extracted from five max-pooling layers. The features were then average-pooled, normalized, and concatenated to form the CNN feature vector corresponding to the input ROI.
Fig. 5
Fig. 5
ROC curves showing the performance of three classifiers. The classifiers were trained on CNN features extracted from ROIs selected on: (a) the MIP images of second postcontrast subtraction MRIs, AUCMIP, (b) the central slices of the second postcontrast MRIs, AUCCS, and (c) the central slices of second postcontrast subtraction MRIs, AUCCSSubtracted.
See this image and copyright information in PMC

References

    1. Turkbey B., et al. , “The role of dynamic contrast enhanced MR imaging in cancer diagnosis and treatment,” Diagn. Interventional Radiol. 13, e45–e53 (2009).https://doi.org/10.4261/1305-3825.DIR.2537-08.1 - DOI - PMC - PubMed
    1. American Cancer Society, Breast Cancer Facts and Figures 2015–2016, American Cancer Society, Inc. (2015).
    1. Pickles M. D., et al. , “Prognostic value of DCE-MRI in breast cancer patients undergoing neoadjuvant chemotherapy: a comparison with traditional survival indicators,” Eur. Radiol. 25, 1097–1106 (2015).https://doi.org/10.1007/s00330-014-3502-5 - DOI - PubMed
    1. Morrow M., Waters J., Morris E., “MRI for breast cancer screening, diagnosis, and treatment,” Lancet 378, 1804–1811 (2011).https://doi.org/10.1016/S0140-6736(11)61350-0 - DOI - PubMed
    1. Kuhl C. K., et al. , “Abbreviated breast magnetic resonance imaging (MRI): first postcontrast subtracted images and maximum-intensity projection—a novel approach to breast cancer screening with MRI,” J. Clin. Oncol. 32, 2304–2310 (2014).https://doi.org/10.1200/JCO.2013.52.5386 - DOI - PubMed