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
. 2016:2:16012.
doi: 10.1038/npjbcancer.2016.12. Epub 2016 May 11.

Quantitative MRI radiomics in the prediction of molecular classifications of breast cancer subtypes in the TCGA/TCIA data set

Hui Li  1 , Yitan Zhu  2 , Elizabeth S Burnside  3 , Erich Huang  4 , Karen Drukker  1 , Katherine A Hoadley  5 , Cheng Fan  5 , Suzanne D Conzen  6 , Margarita Zuley  7 , Jose M Net  8 , Elizabeth Sutton  9 , Gary J Whitman  10 , Elizabeth Morris  9 , Charles M Perou  5 , Yuan Ji  11 , Maryellen L Giger  1
Affiliations

Quantitative MRI radiomics in the prediction of molecular classifications of breast cancer subtypes in the TCGA/TCIA data set

Hui Li et al. NPJ Breast Cancer. 2016.

Abstract

Using quantitative radiomics, we demonstrate that computer-extracted magnetic resonance (MR) image-based tumor phenotypes can be predictive of the molecular classification of invasive breast cancers. Radiomics analysis was performed on 91 MRIs of biopsy-proven invasive breast cancers from National Cancer Institute's multi-institutional TCGA/TCIA. Immunohistochemistry molecular classification was performed including estrogen receptor, progesterone receptor, human epidermal growth factor receptor 2, and for 84 cases, the molecular subtype (normal-like, luminal A, luminal B, HER2-enriched, and basal-like). Computerized quantitative image analysis included: three-dimensional lesion segmentation, phenotype extraction, and leave-one-case-out cross validation involving stepwise feature selection and linear discriminant analysis. The performance of the classifier model for molecular subtyping was evaluated using receiver operating characteristic analysis. The computer-extracted tumor phenotypes were able to distinguish between molecular prognostic indicators; area under the ROC curve values of 0.89, 0.69, 0.65, and 0.67 in the tasks of distinguishing between ER+ versus ER-, PR+ versus PR-, HER2+ versus HER2-, and triple-negative versus others, respectively. Statistically significant associations between tumor phenotypes and receptor status were observed. More aggressive cancers are likely to be larger in size with more heterogeneity in their contrast enhancement. Even after controlling for tumor size, a statistically significant trend was observed within each size group (P = 0.04 for lesions ≤ 2 cm; P = 0.02 for lesions >2 to ≤5 cm) as with the entire data set (P-value = 0.006) for the relationship between enhancement texture (entropy) and molecular subtypes (normal-like, luminal A, luminal B, HER2-enriched, basal-like). In conclusion, computer-extracted image phenotypes show promise for high-throughput discrimination of breast cancer subtypes and may yield a quantitative predictive signature for advancing precision medicine.

PubMed Disclaimer

Conflict of interest statement

M.L.G. is a stockholder in R2 technology/Hologic and receives royalties from Hologic, GE Medical Systems, MEDIAN Technologies, Riverain Medical, Mitsubishi and Toshiba. She is a cofounder of and stockholder in Quantitative Insights. K.D., and H.L. receives royalties from Hologic. C.M.P. is an equity stock holder, and Board of Director Member, of Bioclassifier, LLC. C.M.P. is also listed as an inventor on a patent application on the PAM50 assay. M.L.G., and H.L. were responsible for the computer analysis of the TCIA images; E.S.B., M.Z., J.M.N., E.S., G.J.W., E.M., E.B., K.B., B.D., M.G., and H.L.P. were responsible for acquiring the lesion locations in the TCIA MRIs; C.M.P., K.A.H., and C.F. were responsible for the assessment of the molecular subtyping of the breast cancer lesions from the TCGA; M.L.G., H.L., Y.Z., K.D., E.S.B., S.D.C., E.M., and Y.J. were involved in the analytic concept and design; M.L.G., H.L., K.D., and E.H. contributed to the statistical analyses; all authors participated in the manuscript preparation, the interpretation of data analysis results, and critical review/revision of the manuscript for important intellectual content. All authors read and approved the final manuscript. All authors agreed to be accountable for all aspects of the work.

Figures

Figure 1
Figure 1
Example cases including segmentation outlines obtained from the computer segmentation method. (a) ER-positive example; (b) ER-negative example; (c) CEIP values (and ranges) for size, irregularity, and enhancement texture for two example cases. CEIP, computer-extracted image phenotypes; ER, estrogen receptor; HER2, human epidermal growth factor receptor 2; MRI, magnetic resonance imaging.
Figure 2
Figure 2
Relationship between MRI phenotype of size (effective diameter) and receptor status (a: ER; b: PR; c: HER2; d: TN). The P-values from the Mann–Whitney U-test are 0.001, 0.14, 1.0, and 0.006 for ER, PR, HER2, and TN, respectively. ER, estrogen receptor; HER2, human epidermal growth factor receptor 2; MRI, magnetic resonance imaging; PR, progesterone receptor; TN, triple negative.
Figure 3
Figure 3
Relationship between MRI phenotype of lesion shape (irregularity) and receptor status (a: ER; b: PR; c: HER2; d: TN).The P-values from the Mann–Whitney U-test are 0.23, 0.43, 0.36, and 0.03 for ER, PR, HER2, and TN, respectively. ER, estrogen receptor; HER2, human epidermal growth factor receptor 2; MRI, magnetic resonance imaging; PR, progesterone receptor; TN, triple negative.
Figure 4
Figure 4
Relationship between MRI phenotype of enhancement texture (entropy) and receptor status (a: ER; b: PR; c: HER2; d: TN). The P-values from the Mann–Whitney U-test are 0.08, 0.03, 0.93, and 0.13 for ER, PR, HER2, and TN, respectively. ER, estrogen receptor; HER2, human epidermal growth factor receptor 2; MRI, magnetic resonance imaging; PR, progesterone receptor; TN, triple negative.
Figure 5
Figure 5
Relationship between the MRI phenotype of size (effective diameter) and the molecular subtypes. Shown is a statistically significant trend between size and molecular subtype (P-value of 0.01 from the Kendall test). HER2, human epidermal growth factor receptor 2; MRI, magnetic resonance imaging.
Figure 6
Figure 6
Relationship between the MRI phenotypes of enhancement texture (entropy) and the molecular subtypes. The enhancement texture is calculated at the first-post-contrast MR image thus quantitatively characterizing the heterogeneous uptake of contrast within the tumor. Shown is a statistically significant trend between entropy and molecular subtype (P-value of 0.006 from the Kendall test). HER2, human epidermal growth factor receptor 2; MRI, magnetic resonance imaging.
Figure 7
Figure 7
Relationship between the MRI phenotypes of enhancement texture (entropy) and the molecular subtypes based on size strata (a: lesion size⩽2 cm; b: lesion size >2 cm to ⩽5 cm). Shown are the statistically significant trends between entropy and molecular subtype (P-values of 0.04 and 0.02, respectively, from the Kendall tests). HER2, human epidermal growth factor receptor 2; MRI, magnetic resonance imaging.
See this image and copyright information in PMC

References

    1. Siegel, R., Ma, J., Zou, Z. & Jemal, A. Cancer statistics, 2014. CA Cancer J. Clin. 64, 9–29 (2014). - PubMed
    1. Carey, L. A. et al. Race, breast cancer subtypes, and survival in the Carolina Breast cancer study. JAMA 295, 2492–2502 (2006). - PubMed
    1. Voduc, K. D. et al. Breast cancer subtypes and the risk of local and regional relapse. J. Clin. Oncol. 28, 1684–1691 (2010). - PubMed
    1. Metzger-Filho, O. et al. Patterns of recurrence and outcome according to breast cancer subtypes in lymph node-negative disease: results from international breast cancer study group trials VIII and IX. J. Clin. Oncol. 31, 3083–3090 (2013). - PMC - PubMed
    1. Arvold, N. D. et al. Age, breast cancer subtype approximation, and local recurrence after breast-conserving therapy. J. Clin. Oncol. 29, 3885–3891 (2011). - PMC - PubMed