Journal Article
. 2017 Nov;3().
doi: 10.1038/s41523-017-0045-3.

Integrated radiomic framework for breast cancer and tumor biology using advanced machine learning and multiparametric MRI

Vishwa S Parekh 1 Michael A Jacobs 1 
  • PMID: 29152563
  •     36 References
  •     30 citations


Radiomics deals with the high throughput extraction of quantitative textural information from radiological images that not visually perceivable by radiologists. However, the biological correlation between radiomic features and different tissues of interest has not been established. To that end, we present the radiomic feature mapping framework to generate radiomic MRI texture image representations called the radiomic feature maps (RFM) and correlate the RFMs with quantitative texture values, breast tissue biology using quantitative MRI and classify benign from malignant tumors. We tested our radiomic feature mapping framework on a retrospective cohort of 124 patients (26 benign and 98 malignant) who underwent multiparametric breast MR imaging at 3 T. The MRI parameters used were T1-weighted imaging, T2-weighted imaging, dynamic contrast enhanced MRI (DCE-MRI) and diffusion weighted imaging (DWI). The RFMs were computed by convolving MRI images with statistical filters based on first order statistics and gray level co-occurrence matrix features. Malignant lesions demonstrated significantly higher entropy on both post contrast DCE-MRI (Benign-DCE entropy: 5.72 ± 0.12, Malignant-DCE entropy: 6.29 ± 0.06, p = 0.0002) and apparent diffusion coefficient (ADC) maps as compared to benign lesions (Benign-ADC entropy: 5.65 ± 0.15, Malignant ADC entropy: 6.20 ± 0.07, p = 0.002). There was no significant difference between glandular tissue entropy values in the two groups. Furthermore, the RFMs from DCE-MRI and DWI demonstrated significantly different RFM curves for benign and malignant lesions indicating their correlation to tumor vascular and cellular heterogeneity respectively. There were significant differences in the quantitative MRI metrics of ADC and perfusion. The multiview IsoSVM model classified benign and malignant breast tumors with sensitivity and specificity of 93 and 85%, respectively, with an AUC of 0.91.

Modeling tracer kinetics in dynamic Gd-DTPA MR imaging.
P S Tofts.
J Magn Reson Imaging, 1997 Jan 01; 7(1). PMID: 9039598
Highly Cited. Review.
Error propagation in eigenimage filtering.
H Soltanian-Zadeh, J P Windham, J M Jenkins.
IEEE Trans Med Imaging, 1990 Jan 01; 9(4). PMID: 18222788
Dynamic breast MR imaging: are signal intensity time course data useful for differential diagnosis of enhancing lesions?
C K Kuhl, P Mielcareck, +4 authors, H H Schild.
Radiology, 1999 Apr 06; 211(1). PMID: 10189459
Highly Cited.
Diffusion-weighted magnetic resonance imaging: a potential non-invasive marker of tumour aggressiveness in localized prostate cancer.
N M deSouza, S F Riches, +5 authors, C Parker.
Clin Radiol, 2008 Jun 17; 63(7). PMID: 18555035
Breast fibroadenoma: mapping of pathophysiologic features with three-time-point, contrast-enhanced MR imaging--pilot study.
D Weinstein, S Strano, +3 authors, H Degani.
Radiology, 1999 Jan 14; 210(1). PMID: 9885614
Eigenimage filtering in MR imaging.
J P Windham, M A Abd-Allah, +2 authors, A M Haggar.
J Comput Assist Tomogr, 1988 Jan 01; 12(1). PMID: 3335646
Quantitative analysis of lesion morphology and texture features for diagnostic prediction in breast MRI.
Ke Nie, Jeon-Hor Chen, +3 authors, Min-Ying Su.
Acad Radiol, 2008 Nov 13; 15(12). PMID: 19000868    Free PMC article.
Radiomics: Images Are More than Pictures, They Are Data.
Robert J Gillies, Paul E Kinahan, Hedvig Hricak.
Radiology, 2015 Nov 19; 278(2). PMID: 26579733    Free PMC article.
Highly Cited.
Multifeature analysis of Gd-enhanced MR images of breast lesions.
S Sinha, F A Lucas-Quesada, +4 authors, L W Bassett.
J Magn Reson Imaging, 1997 Dec 24; 7(6). PMID: 9400844
Quantitative diffusion-weighted imaging as an adjunct to conventional breast MRI for improved positive predictive value.
Savannah C Partridge, Wendy B DeMartini, +3 authors, Constance D Lehman.
AJR Am J Roentgenol, 2009 Nov 26; 193(6). PMID: 19933670
Improved lesion detection in MR mammography: three-dimensional segmentation, moving voxel sampling, and normalized maximum intensity-time ratio entropy.
Gökhan Ertaş, H Ozcan Gülçür, Mehtap Tunaci.
Acad Radiol, 2007 Jan 24; 14(2). PMID: 17236988
Estimating kinetic parameters from dynamic contrast-enhanced T(1)-weighted MRI of a diffusable tracer: standardized quantities and symbols.
P S Tofts, G Brix, +10 authors, R M Weisskoff.
J Magn Reson Imaging, 1999 Oct 03; 10(3). PMID: 10508281
Highly Cited. Review.
Characterization of breast cancer types by texture analysis of magnetic resonance images.
Kirsi Holli, Anna-Leena Lääperi, +6 authors, Hannu Eskola.
Acad Radiol, 2009 Dec 01; 17(2). PMID: 19945302
A global geometric framework for nonlinear dimensionality reduction.
J B Tenenbaum, V de Silva, J C Langford.
Science, 2000 Dec 23; 290(5500). PMID: 11125149
Highly Cited.
Diffusion-weighted imaging improves the diagnostic accuracy of conventional 3.0-T breast MR imaging.
Riham H Ei Khouli, Michael A Jacobs, +4 authors, David A Bluemke.
Radiology, 2010 Jun 25; 256(1). PMID: 20574085    Free PMC article.
Highly Cited.
Diagnosis of breast masses from dynamic contrast-enhanced and diffusion-weighted MR: a machine learning approach.
Hongmin Cai, Yanxia Peng, +2 authors, Li Li.
PLoS One, 2014 Feb 06; 9(1). PMID: 24498092    Free PMC article.
Radiomics: extracting more information from medical images using advanced feature analysis.
Philippe Lambin, Emmanuel Rios-Velazquez, +8 authors, Hugo J W L Aerts.
Eur J Cancer, 2012 Jan 20; 48(4). PMID: 22257792    Free PMC article.
Highly Cited. Review.
Relationship of temporal resolution to diagnostic performance for dynamic contrast enhanced MRI of the breast.
Riham H El Khouli, Katarzyna J Macura, +3 authors, David A Bluemke.
J Magn Reson Imaging, 2009 Oct 27; 30(5). PMID: 19856413    Free PMC article.
Differentiation of clinically benign and malignant breast lesions using diffusion-weighted imaging.
Yong Guo, You-Quan Cai, +5 authors, Jia-Hong Gao.
J Magn Reson Imaging, 2002 Aug 31; 16(2). PMID: 12203765
Highly Cited.
Identification of cerebral ischemic lesions in rat using Eigenimage filtered magnetic resonance imaging.
M A Jacobs, R A Knight, +5 authors, M Chopp.
Brain Res, 1999 Aug 06; 837(1-2). PMID: 10433991
Mapping pathophysiological features of breast tumors by MRI at high spatial resolution.
H Degani, V Gusis, +2 authors, S Strano.
Nat Med, 1997 Jul 01; 3(7). PMID: 9212107
Cerebral tumor volume calculations using planimetric and eigenimage analysis.
D J Peck, J P Windham, +3 authors, T Mikkelsen.
Med Phys, 1996 Dec 01; 23(12). PMID: 8994168
Textural kinetics: a novel dynamic contrast-enhanced (DCE)-MRI feature for breast lesion classification.
Shannon C Agner, Salil Soman, +7 authors, Anant Madabhushi.
J Digit Imaging, 2010 May 29; 24(3). PMID: 20508965    Free PMC article.
Changes in primary breast cancer heterogeneity may augment midtreatment MR imaging assessment of response to neoadjuvant chemotherapy.
Jyoti Parikh, Mariyah Selmi, +7 authors, Vicky Goh.
Radiology, 2014 Mar 25; 272(1). PMID: 24654970
Dynamic contrast-enhanced MRI of the breast: quantitative method for kinetic curve type assessment.
Riham H El Khouli, Katarzyna J Macura, +4 authors, David A Bluemke.
AJR Am J Roentgenol, 2009 Sep 23; 193(4). PMID: 19770298    Free PMC article.
Radiomics: the process and the challenges.
Virendra Kumar, Yuhua Gu, +13 authors, Robert J Gillies.
Magn Reson Imaging, 2012 Aug 18; 30(9). PMID: 22898692    Free PMC article.
Highly Cited. Review.
The role of diffusion-weighted imaging and the apparent diffusion coefficient (ADC) values for breast tumors.
Mi Jung Park, Eun Suk Cha, +2 authors, Jun Hyun Baik.
Korean J Radiol, 2007 Oct 10; 8(5). PMID: 17923781    Free PMC article.
Prediction of malignant breast lesions from MRI features: a comparison of artificial neural network and logistic regression techniques.
Christine E McLaren, Wen-Pin Chen, Ke Nie, Min-Ying Su.
Acad Radiol, 2009 May 05; 16(7). PMID: 19409817    Free PMC article.
Diffusion-weighted imaging of malignant breast tumors: the usefulness of apparent diffusion coefficient (ADC) value and ADC map for the detection of malignant breast tumors and evaluation of cancer extension.
Reiko Woodhams, Keiji Matsunaga, +5 authors, Kazushige Hayakawa.
J Comput Assist Tomogr, 2005 Sep 16; 29(5). PMID: 16163035
Computer-aided diagnosis of breast DCE-MRI using pharmacokinetic model and 3-D morphology analysis.
Teh-Chen Wang, Yan-Hao Huang, +4 authors, Ruey-Feng Chang.
Magn Reson Imaging, 2014 Jan 21; 32(3). PMID: 24439361
Texture analysis in assessment and prediction of chemotherapy response in breast cancer.
Arfan Ahmed, Peter Gibbs, Martin Pickles, Lindsay Turnbull.
J Magn Reson Imaging, 2012 Dec 15; 38(1). PMID: 23238914
Diagnostic architectural and dynamic features at breast MR imaging: multicenter study.
Mitchell D Schnall, Jeffrey Blume, +14 authors, Constantine A Gatsonis.
Radiology, 2005 Dec 24; 238(1). PMID: 16373758
Highly Cited.
Radiomics: a new application from established techniques.
Vishwa Parekh, Michael A Jacobs.
Expert Rev Precis Med Drug Dev, 2017 Jan 04; 1(2). PMID: 28042608    Free PMC article.
Highly Cited.
Diagnostic assessment by dynamic contrast-enhanced and diffusion-weighted magnetic resonance in differentiation of breast lesions under different imaging protocols.
Hongmin Cai, Lizhi Liu, +2 authors, Li Li.
BMC Cancer, 2014 Jun 03; 14. PMID: 24885156    Free PMC article.
Textural analysis of contrast-enhanced MR images of the breast.
Peter Gibbs, Lindsay W Turnbull.
Magn Reson Med, 2003 Jun 20; 50(1). PMID: 12815683
Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach.
Hugo J W L Aerts, Emmanuel Rios Velazquez, +15 authors, Philippe Lambin.
Nat Commun, 2014 Jun 04; 5. PMID: 24892406    Free PMC article.
Highly Cited.
A Gradient-Based Approach for Breast DCE-MRI Analysis.
L Losurdo, T M A Basile, +14 authors, D La Forgia.
Biomed Res Int, 2018 Aug 25; 2018. PMID: 30140703    Free PMC article.
Application of Radiomics and Decision Support Systems for Breast MR Differential Diagnosis.
Ioannis Tsougos, Alexandros Vamvakas, +2 authors, Katerina Vassiou.
Comput Math Methods Med, 2018 Oct 23; 2018. PMID: 30344618    Free PMC article.
Artificial intelligence in medical imaging: threat or opportunity? Radiologists again at the forefront of innovation in medicine.
Filippo Pesapane, Marina Codari, Francesco Sardanelli.
Eur Radiol Exp, 2018 Oct 26; 2(1). PMID: 30353365    Free PMC article.
Highly Cited. Review.
A New Challenge for Radiologists: Radiomics in Breast Cancer.
Paola Crivelli, Roberta Eufrasia Ledda, +3 authors, Maurizio Conti.
Biomed Res Int, 2018 Nov 08; 2018. PMID: 30402486    Free PMC article.
Radiomics and liquid biopsy in oncology: the holons of systems medicine.
Emanuele Neri, Marzia Del Re, +4 authors, Romano Danesi.
Insights Imaging, 2018 Nov 16; 9(6). PMID: 30430428    Free PMC article.
Imaging Phenotypes of Breast Cancer Heterogeneity in Preoperative Breast Dynamic Contrast Enhanced Magnetic Resonance Imaging (DCE-MRI) Scans Predict 10-Year Recurrence.
Rhea D Chitalia, Jennifer Rowland, +7 authors, Despina Kontos.
Clin Cancer Res, 2019 Nov 17; 26(4). PMID: 31732521    Free PMC article.
The Use of Quantitative Imaging in Radiation Oncology: A Quantitative Imaging Network (QIN) Perspective.
Robert H Press, Hui-Kuo G Shu, +23 authors, John M Buatti.
Int J Radiat Oncol Biol Phys, 2018 Jul 04; 102(4). PMID: 29966725    Free PMC article.
The volumetric-tumour histogram-based analysis of intravoxel incoherent motion and non-Gaussian diffusion MRI: association with prognostic factors in HER2-positive breast cancer.
Chao You, Jianwei Li, +4 authors, Weijun Peng.
J Transl Med, 2019 Jul 03; 17(1). PMID: 31262334    Free PMC article.
Multicenter study demonstrates radiomic features derived from magnetic resonance perfusion images identify pseudoprogression in glioblastoma.
Nabil Elshafeey, Aikaterini Kotrotsou, +14 authors, Rivka R Colen.
Nat Commun, 2019 Jul 20; 10(1). PMID: 31320621    Free PMC article.
Will traditional biopsy be substituted by radiomics and liquid biopsy for breast cancer diagnosis and characterisation?
Filippo Pesapane, Matteo Basilio Suter, +7 authors, Enrico Cassano.
Med Oncol, 2020 Mar 18; 37(4). PMID: 32180032
Machine learning in breast MRI.
Beatriu Reig, Laura Heacock, Krzysztof J Geras, Linda Moy.
J Magn Reson Imaging, 2019 Jul 06; 52(4). PMID: 31276247    Free PMC article.
Radiomic Signatures Derived from Diffusion-Weighted Imaging for the Assessment of Breast Cancer Receptor Status and Molecular Subtypes.
Doris Leithner, Blanca Bernard-Davila, +9 authors, Katja Pinker.
Mol Imaging Biol, 2019 Jun 19; 22(2). PMID: 31209778    Free PMC article.
Multiparametric radiomics methods for breast cancer tissue characterization using radiological imaging.
Vishwa S Parekh, Michael A Jacobs.
Breast Cancer Res Treat, 2020 Feb 06; 180(2). PMID: 32020435    Free PMC article.
Use of MRI for Personalized Treatment of More Aggressive Tumors.
Riham H El Khouli, Michael A Jacobs.
Radiology, 2020 Apr 03; 295(3). PMID: 32233918    Free PMC article.
Radiomics in Breast Imaging from Techniques to Clinical Applications: A Review.
Seung Hak Lee, Hyunjin Park, Eun Sook Ko.
Korean J Radiol, 2020 Jun 12; 21(7). PMID: 32524780    Free PMC article.
A deep learning methodology for improved breast cancer diagnosis using multiparametric MRI.
Qiyuan Hu, Heather M Whitney, Maryellen L Giger.
Sci Rep, 2020 Jul 01; 10(1). PMID: 32601367    Free PMC article.
Radiomics: from qualitative to quantitative imaging.
William Rogers, Sithin Thulasi Seetha, +14 authors, Philippe Lambin.
Br J Radiol, 2020 Feb 27; 93(1108). PMID: 32101448    Free PMC article.
Overview of radiomics in breast cancer diagnosis and prognostication.
Alberto Stefano Tagliafico, Michele Piana, +3 authors, Nehmat Houssami.
Breast, 2019 Nov 19; 49. PMID: 31739125    Free PMC article.
Non-Invasive Assessment of Breast Cancer Molecular Subtypes with Multiparametric Magnetic Resonance Imaging Radiomics.
Doris Leithner, Marius E Mayerhoefer, +4 authors, Katja Pinker.
J Clin Med, 2020 Jun 18; 9(6). PMID: 32545851    Free PMC article.
MRI-based radiomics in breast cancer: feature robustness with respect to inter-observer segmentation variability.
R W Y Granzier, N M H Verbakel, +6 authors, H C Woodruff.
Sci Rep, 2020 Aug 28; 10(1). PMID: 32843663    Free PMC article.
Deep learning and radiomics in precision medicine.
Vishwa S Parekh, Michael A Jacobs.
Expert Rev Precis Med Drug Dev, 2019 May 14; 4(2). PMID: 31080889    Free PMC article.
Oropharyngeal squamous cell carcinoma: radiomic machine-learning classifiers from multiparametric MR images for determination of HPV infection status.
Chong Hyun Suh, Kyung Hwa Lee, +6 authors, Namkug Kim.
Sci Rep, 2020 Oct 18; 10(1). PMID: 33067484    Free PMC article.
Integrated Multiparametric Radiomics and Informatics System for Characterizing Breast Tumor Characteristics with the OncotypeDX Gene Assay.
Michael A Jacobs, Christopher B Umbricht, +5 authors, Antonio C Wolff.
Cancers (Basel), 2020 Oct 01; 12(10). PMID: 32992569    Free PMC article.
Diffusion-weighted imaging of the breast: current status as an imaging biomarker and future role.
Julia Camps-Herrero.
BJR Open, 2019 Mar 08; 1(1). PMID: 33178933    Free PMC article.
Distinguishing True Progression From Radionecrosis After Stereotactic Radiation Therapy for Brain Metastases With Machine Learning and Radiomics.
Luke Peng, Vishwa Parekh, +19 authors, Lawrence Kleinberg.
Int J Radiat Oncol Biol Phys, 2018 Oct 26; 102(4). PMID: 30353872    Free PMC article.
Radiomic analysis of planning computed tomograms for predicting radiation-induced lung injury and outcome in lung cancer patients treated with robotic stereotactic body radiation therapy.
Khaled Bousabarah, Susanne Temming, +7 authors, Harald Treuer.
Strahlenther Onkol, 2019 Mar 16; 195(9). PMID: 30874846
Radiomics in hepatocellular carcinoma: a quantitative review.
Taiga Wakabayashi, Farid Ouhmich, +8 authors, Benoit Gallix.
Hepatol Int, 2019 Sep 02; 13(5). PMID: 31473947
Independent validation of machine learning in diagnosing breast Cancer on magnetic resonance imaging within a single institution.
Yu Ji, Hui Li, +4 authors, Maryellen L Giger.
Cancer Imaging, 2019 Sep 20; 19(1). PMID: 31533838    Free PMC article.
Radiomic features based on Hessian index for prediction of prognosis in head-and-neck cancer patients.
Quoc Cuong Le, Hidetaka Arimura, Kenta Ninomiya, Yutaro Kabata.
Sci Rep, 2020 Dec 06; 10(1). PMID: 33277570    Free PMC article.
Radiomic analysis of HTR-DCE MR sequences improves diagnostic performance compared to BI-RADS analysis of breast MR lesions.
Saskia Vande Perre, Loïc Duron, +5 authors, Isabelle Thomassin-Naggara.
Eur Radiol, 2021 Jan 07;. PMID: 33404696