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
. 2017;1(1):22.
doi: 10.1186/s41747-017-0025-2. Epub 2017 Nov 21.

Breast MRI radiomics: comparison of computer- and human-extracted imaging phenotypes

Elizabeth J Sutton  1 , Erich P Huang  2 , Karen Drukker  3 , Elizabeth S Burnside  4 , Hui Li  3 , Jose M Net  5 , Arvind Rao  6 , Gary J Whitman  7 , Margarita Zuley  8 , Marie Ganott  8 , Ermelinda Bonaccio  9 , Maryellen L Giger  3 , Elizabeth A Morris  1   10 ; TCGA group
Affiliations

Breast MRI radiomics: comparison of computer- and human-extracted imaging phenotypes

Elizabeth J Sutton et al. Eur Radiol Exp. 2017.

Abstract

Background: In this study, we sought to investigate if computer-extracted magnetic resonance imaging (MRI) phenotypes of breast cancer could replicate human-extracted size and Breast Imaging-Reporting and Data System (BI-RADS) imaging phenotypes using MRI data from The Cancer Genome Atlas (TCGA) project of the National Cancer Institute.

Methods: Our retrospective interpretation study involved analysis of Health Insurance Portability and Accountability Act-compliant breast MRI data from The Cancer Imaging Archive, an open-source database from the TCGA project. This study was exempt from institutional review board approval at Memorial Sloan Kettering Cancer Center and the need for informed consent was waived. Ninety-one pre-operative breast MRIs with verified invasive breast cancers were analysed. Three fellowship-trained breast radiologists evaluated the index cancer in each case according to size and the BI-RADS lexicon for shape, margin, and enhancement (human-extracted image phenotypes [HEIP]). Human inter-observer agreement was analysed by the intra-class correlation coefficient (ICC) for size and Krippendorff's α for other measurements. Quantitative MRI radiomics of computerised three-dimensional segmentations of each cancer generated computer-extracted image phenotypes (CEIP). Spearman's rank correlation coefficients were used to compare HEIP and CEIP.

Results: Inter-observer agreement for HEIP varied, with the highest agreement seen for size (ICC 0.679) and shape (ICC 0.527). The computer-extracted maximum linear size replicated the human measurement with p < 10-12. CEIP of shape, specifically sphericity and irregularity, replicated HEIP with both p values < 0.001. CEIP did not demonstrate agreement with HEIP of tumour margin or internal enhancement.

Conclusions: Quantitative radiomics of breast cancer may replicate human-extracted tumour size and BI-RADS imaging phenotypes, thus enabling precision medicine.

Keywords: Breast cancer; Inter-observer variability; Machine learning; Magnetic resonance imaging; Radiomics.

PubMed Disclaimer

Conflict of interest statement

In this retrospective study, all patient data were Health Insurance Portability and Accountability Act-compliant and acquired under institutional review board approval that waived the need for informed consent.Not applicable.The authors declare that they have no competing interests.Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Figures

Fig. 1
Fig. 1
Schematic of breast magnetic resonance imaging human-extracted image phenotypes (HEIP) and computer-extracted imaging phenotypes (CEIP). TCIA The Cancer Imaging Archive
Fig. 2
Fig. 2
Comparison between human- and computer-measured maximum linear size
Fig. 3
Fig. 3
Comparison of computer- and human-extracted shapes
Fig. 4
Fig. 4
Sagittal fat-suppressed T1-weighted first post-contrast image of a breast cancer (arrow) where computer-extracted image phenotype (CEIP) sphericity is high and the radiologist assessed it as round/oval for shape. CEIP and human-extracted image phenotype are concordant
Fig. 5
Fig. 5
Axial fat-suppressed T1-weighted first post-contrast image of a breast cancer (arrow) where computer-extracted image phenotype (CEIP) sphericity is high and the radiologist assessed it as irregular for shape. CEIP and human-extracted image phenotype are discordant
See this image and copyright information in PMC

References

    1. Morris EA. Diagnostic breast MR imaging: current status and future directions. Magn Reson Imaging Clin N Am. 2010;18:57–74. doi: 10.1016/j.mric.2009.09.005. - DOI - PubMed
    1. Morris E, Comstock C, Lee C, et al. ACR BI-RADS® Atlas, Breast Imaging Reporting and Data System. Reston: American College of Radiology; 2013. ACR BI-RADS® magnetic resonance imaging.
    1. Heye T, Merkle EM, Reiner CS, et al. Reproducibility of dynamic contrast-enhanced MR imaging. Part II. Comparison of intra- and interobserver variability with manual region of interest placement versus semiautomatic lesion segmentation and histogram analysis. Radiology. 2013;266:812–821. doi: 10.1148/radiol.12120255. - DOI - PubMed
    1. Liu YH, Xu L, Liu LH, et al. 3.0T MR-CAD: clinical value in diagnosis of breast tumor compared with conventional MRI. J Cancer. 2014;5:585–589. doi: 10.7150/jca.9785. - DOI - PMC - PubMed
    1. Kuhl CK, Mielcareck P, Klaschik S, et al. Dynamic breast MR imaging: are signal intensity time course data useful for differential diagnosis of enhancing lesions? Radiology. 1999;211:101–110. doi: 10.1148/radiology.211.1.r99ap38101. - DOI - PubMed