Journal Article
. 2019 Sep;21(1).
doi: 10.1186/s13058-019-1187-z.

Radiomic signatures with contrast-enhanced magnetic resonance imaging for the assessment of breast cancer receptor status and molecular subtypes: initial results

Doris Leithner 1 Joao V Horvat 1 Maria Adele Marino 1 Blanca Bernard-Davila 2 Maxine S Jochelson 1 R Elena Ochoa-Albiztegui 1 Danny F Martinez 1 Elizabeth A Morris 1 Sunitha Thakur 3 Katja Pinker 4 
  • PMID: 31514736
  •     31 References
  •     10 citations


Background: To evaluate the diagnostic performance of radiomic signatures extracted from contrast-enhanced magnetic resonance imaging (CE-MRI) for the assessment of breast cancer receptor status and molecular subtypes.

Methods: One hundred and forty-three patients with biopsy-proven breast cancer who underwent CE-MRI at 3 T were included in this IRB-approved HIPAA-compliant retrospective study. The training dataset comprised 91 patients (luminal A, n = 49; luminal B, n = 8; HER2-enriched, n = 11; triple negative, n = 23), while the validation dataset comprised 52 patients from a second institution (luminal A, n = 17; luminal B, n = 17; triple negative, n = 18). Radiomic analysis of manually segmented tumors included calculation of features derived from the first-order histogram (HIS), co-occurrence matrix (COM), run-length matrix (RLM), absolute gradient (GRA), autoregressive model (ARM), discrete Haar wavelet transform (WAV), and lesion geometry (GEO). Fisher, probability of error and average correlation (POE + ACC), and mutual information coefficients were used for feature selection. Linear discriminant analysis followed by k-nearest neighbor classification (with leave-one-out cross-validation) was used for pairwise radiomic-based separation of receptor status and molecular subtypes. Histopathology served as the standard of reference.

Results: In the training dataset, radiomic signatures yielded the following accuracies > 80%: luminal B vs. luminal A, 84.2% (mainly based on COM features); luminal B vs. triple negative, 83.9% (mainly based on GEO features); luminal B vs. all others, 89% (mainly based on COM features); and HER2-enriched vs. all others, 81.3% (mainly based on COM features). Radiomic signatures were successfully validated in the separate validation dataset for luminal A vs. luminal B (79.4%) and luminal B vs. triple negative (77.1%).

Conclusions: In this preliminary study, radiomic signatures with CE-MRI enable the assessment of breast cancer receptor status and molecular subtypes with high diagnostic accuracy. These results need to be confirmed in future larger studies.

Keywords: Breast cancer; Contrast-enhanced; Magnetic resonance imaging; Molecular subtype; Radiomics.

Diffusion-Weighted Imaging With Apparent Diffusion Coefficient Mapping for Breast Cancer Detection as a Stand-Alone Parameter: Comparison With Dynamic Contrast-Enhanced and Multiparametric Magnetic Resonance Imaging.
Katja Pinker, Linda Moy, +8 authors, Thomas H Helbich.
Invest Radiol, 2018 Apr 06; 53(10). PMID: 29620604    Free PMC article.
Texture-based classification of focal liver lesions on MRI at 3.0 Tesla: a feasibility study in cysts and hemangiomas.
Marius E Mayerhoefer, Wolfgang Schima, +3 authors, Ahmed Ba-Ssalamah.
J Magn Reson Imaging, 2010 Aug 03; 32(2). PMID: 20677262
Breast cancer complexity: implications of intratumoral heterogeneity in clinical management.
Brittany Haynes, Ashapurna Sarma, Pratima Nangia-Makker, Malathy P Shekhar.
Cancer Metastasis Rev, 2017 Jul 29; 36(3). PMID: 28752247    Free PMC article.
MRI texture analysis in differentiating luminal A and luminal B breast cancer molecular subtypes - a feasibility study.
Kirsi Holli-Helenius, Annukka Salminen, +4 authors, Riitta Parkkola.
BMC Med Imaging, 2017 Dec 30; 17(1). PMID: 29284425    Free PMC article.
Influence of MRI acquisition protocols and image intensity normalization methods on texture classification.
G Collewet, M Strzelecki, F Mariette.
Magn Reson Imaging, 2004 Feb 20; 22(1). PMID: 14972397
Comprehensive molecular portraits of human breast tumours.
Cancer Genome Atlas Network.
Nature, 2012 Sep 25; 490(7418). PMID: 23000897    Free PMC article.
Highly Cited.
Quantitative MRI radiomics in the prediction of molecular classifications of breast cancer subtypes in the TCGA/TCIA data set.
Hui Li, Yitan Zhu, +13 authors, Maryellen L Giger.
NPJ Breast Cancer, 2016 Nov 18; 2. PMID: 27853751    Free PMC article.
Highly Cited.
Effects of MRI acquisition parameter variations and protocol heterogeneity on the results of texture analysis and pattern discrimination: an application-oriented study.
Marius E Mayerhoefer, Pavol Szomolanyi, +2 authors, Siegfried Trattnig.
Med Phys, 2009 May 29; 36(4). PMID: 19472631
Breast cancer molecular subtypes: from TNBC to QNBC.
Jane Date C Hon, Baljit Singh, +7 authors, Peng Lee.
Am J Cancer Res, 2016 Oct 12; 6(9). PMID: 27725895    Free PMC article.
Differentiating brain metastases from different pathological types of lung cancers using texture analysis of T1 postcontrast MR.
Zhenjiang Li, Yu Mao, +3 authors, Baosheng Li.
Magn Reson Med, 2015 Dec 02; 76(5). PMID: 26621795
Magnetic resonance imaging texture analysis classification of primary breast cancer.
S A Waugh, C A Purdie, +4 authors, A M Thompson.
Eur Radiol, 2015 Jun 13; 26(2). PMID: 26065395
Clinical implications of the intrinsic molecular subtypes of breast cancer.
Aleix Prat, Estela Pineda, +7 authors, Montserrat Muñoz.
Breast, 2015 Aug 09; 24 Suppl 2. PMID: 26253814
Highly Cited. Review.
Differences in Clinical Outcomes between Luminal A and B Type Breast Cancers according to the St. Gallen Consensus 2013.
Hyo Jung Ahn, Soo Jin Jung, +2 authors, Hye-Kyoung Yoon.
J Breast Cancer, 2015 Jul 15; 18(2). PMID: 26155291    Free PMC article.
Breast cancer molecular subtype classifier that incorporates MRI features.
Elizabeth J Sutton, Brittany Z Dashevsky, +5 authors, Joseph O Deasy.
J Magn Reson Imaging, 2016 Jan 13; 44(1). PMID: 26756416    Free PMC article.
Breast cancer molecular subtypes in patients with locally advanced disease: impact on prognosis, patterns of recurrence, and response to therapy.
Kathryn E Huber, Lisa A Carey, David E Wazer.
Semin Radiat Oncol, 2009 Sep 08; 19(4). PMID: 19732684
Identifying Triple-Negative Breast Cancer Using Background Parenchymal Enhancement Heterogeneity on Dynamic Contrast-Enhanced MRI: A Pilot Radiomics Study.
Jeff Wang, Fumi Kato, +6 authors, Hiroki Shirato.
PLoS One, 2015 Nov 26; 10(11). PMID: 26600392    Free PMC article.
Race, breast cancer subtypes, and survival in the Carolina Breast Cancer Study.
Lisa A Carey, Charles M Perou, +14 authors, Robert C Millikan.
JAMA, 2006 Jun 08; 295(21). PMID: 16757721
Highly Cited.
St. Gallen consensus 2013: optimizing and personalizing primary curative therapy of breast cancer worldwide.
Hans-Joerg Senn.
Breast Care (Basel), 2014 Jan 15; 8(2). PMID: 24415963    Free PMC article.
Non-genetic cancer cell plasticity and therapy-induced stemness in tumour relapse: 'What does not kill me strengthens me'.
A O Pisco, S Huang.
Br J Cancer, 2015 May 13; 112(11). PMID: 25965164    Free PMC article.
Highly Cited. Review.
Texture-based and diffusion-weighted discrimination of parotid gland lesions on MR images at 3.0 Tesla.
Julia Fruehwald-Pallamar, Christian Czerny, +4 authors, Marius E Mayerhoefer.
NMR Biomed, 2013 May 25; 26(11). PMID: 23703801
Meta-analysis of gene expression profiles in breast cancer: toward a unified understanding of breast cancer subtyping and prognosis signatures.
Pratyaksha Wirapati, Christos Sotiriou, +10 authors, Mauro Delorenzi.
Breast Cancer Res, 2008 Jul 30; 10(4). PMID: 18662380    Free PMC article.
Highly Cited.
Apparent diffusion coefficient in estrogen receptor-positive and lymph node-negative invasive breast cancers at 3.0T DW-MRI: A potential predictor for an oncotype Dx test recurrence score.
Sunitha B Thakur, Manuela Durando, +5 authors, Elizabeth A Morris.
J Magn Reson Imaging, 2017 Jun 24; 47(2). PMID: 28640531    Free PMC article.
How could breast cancer molecular features contribute to locoregional treatment decision making?
Pelagia G Tsoutsou, Marie-Catherine Vozenin, André-Dante Durham, Jean Bourhis.
Crit Rev Oncol Hematol, 2017 Jan 23; 110. PMID: 28109404
Radiomic analysis reveals DCE-MRI features for prediction of molecular subtypes of breast cancer.
Ming Fan, Hui Li, +3 authors, Lihua Li.
PLoS One, 2017 Feb 07; 12(2). PMID: 28166261    Free PMC article.
Relationships Between MRI Breast Imaging-Reporting and Data System (BI-RADS) Lexicon Descriptors and Breast Cancer Molecular Subtypes: Internal Enhancement is Associated with Luminal B Subtype.
Lars J Grimm, Jing Zhang, +3 authors, Maciej A Mazurowski.
Breast J, 2017 Mar 16; 23(5). PMID: 28295860
Breast cancer classification by proteomic technologies: current state of knowledge.
S W Lam, C R Jimenez, E Boven.
Cancer Treat Rev, 2013 Jul 31; 40(1). PMID: 23891266
Identifying relations between imaging phenotypes and molecular subtypes of breast cancer: Model discovery and external validation.
Jia Wu, Xiaoli Sun, +5 authors, Ruijiang Li.
J Magn Reson Imaging, 2017 Feb 09; 46(4). PMID: 28177554    Free PMC article.
Breast cancer intra-tumor heterogeneity.
Luciano G Martelotto, Charlotte K Y Ng, +2 authors, Jorge S Reis-Filho.
Breast Cancer Res, 2014 Jan 01; 16(3). PMID: 25928070    Free PMC article.
Highly Cited. Review.
Radiogenomic analysis of breast cancer: luminal B molecular subtype is associated with enhancement dynamics at MR imaging.
Maciej A Mazurowski, Jing Zhang, +2 authors, James I Silber.
Radiology, 2014 Jul 17; 273(2). PMID: 25028781
Highly Cited.
Clinical management of breast cancer heterogeneity.
Dimitrios Zardavas, Alexandre Irrthum, Charles Swanton, Martine Piccart.
Nat Rev Clin Oncol, 2015 Apr 22; 12(7). PMID: 25895611
Highly Cited. Review.
Deconstructing the molecular portraits of breast cancer.
Aleix Prat, Charles M Perou.
Mol Oncol, 2010 Dec 15; 5(1). PMID: 21147047    Free PMC article.
Highly Cited. Review.
MRI Radiomic Features: Association with Disease-Free Survival in Patients with Triple-Negative Breast Cancer.
Sungwon Kim, Min Jung Kim, +2 authors, Vivian Youngjean Park.
Sci Rep, 2020 Mar 01; 10(1). PMID: 32111957    Free PMC article.
A rapid volume of interest-based approach of radiomics analysis of breast MRI for tumor decoding and phenotyping of breast cancer.
Aydin Demircioglu, Johannes Grueneisen, +7 authors, Lale Umutlu.
PLoS One, 2020 Jun 27; 15(6). PMID: 32589681    Free PMC article.
Radiomics for Tumor Characterization in Breast Cancer Patients: A Feasibility Study Comparing Contrast-Enhanced Mammography and Magnetic Resonance Imaging.
Maria Adele Marino, Doris Leithner, +4 authors, Maxine S Jochelson.
Diagnostics (Basel), 2020 Jul 28; 10(7). PMID: 32708512    Free PMC article.
Radiomic Analysis in Contrast-Enhanced Spectral Mammography for Predicting Breast Cancer Histological Outcome.
Daniele La Forgia, Annarita Fanizzi, +10 authors, Alfredo Zito.
Diagnostics (Basel), 2020 Sep 23; 10(9). PMID: 32957690    Free PMC article.
MRI-based machine learning radiomics can predict HER2 expression level and pathologic response after neoadjuvant therapy in HER2 overexpressing breast cancer.
Almir G V Bitencourt, Peter Gibbs, +8 authors, Maxine S Jochelson.
EBioMedicine, 2020 Oct 12; 61. PMID: 33039708    Free PMC article.
[Multimodal, multiparametric and genetic breast imaging].
Roberto LoGullo, Joao Horvat, Jeffrey Reiner, Katja Pinker.
Radiologe, 2021 Jan 20; 61(2). PMID: 33464404
Incorporating radiomics into clinical trials: expert consensus endorsed by the European Society of Radiology on considerations for data-driven compared to biologically driven quantitative biomarkers.
Laure Fournier, Lena Costaridou, +31 authors, European Society Of Radiology.
Eur Radiol, 2021 Jan 26;. PMID: 33492473
Imaging features of breast cancer molecular subtypes: state of the art.
Nariya Cho.
J Pathol Transl Med, 2020 Nov 07; 55(1). PMID: 33153242    Free PMC article.
An Approach Based on Mammographic Imaging and Radiomics for Distinguishing Male Benign and Malignant Lesions: A Preliminary Study.
Yan Huang, Qin Xiao, +4 authors, Yajia Gu.
Front Oncol, 2021 Mar 06; 10. PMID: 33665164    Free PMC article.
Breast Tumor Characterization Using [18F]FDG-PET/CT Imaging Combined with Data Preprocessing and Radiomics.
Denis Krajnc, Laszlo Papp, +11 authors, Katja Pinker.
Cancers (Basel), 2021 Apr 04; 13(6). PMID: 33809057    Free PMC article.