Radiomic analysis of imaging heterogeneity in tumours and the surrounding parenchyma based on unsupervised decomposition of DCE-MRI for predicting molecular subtypes of breast cancer
- 45 Downloads
This study aimed to predict the molecular subtypes of breast cancer via intratumoural and peritumoural radiomic analysis with subregion identification based on the decomposition of contrast-enhanced magnetic resonance imaging (DCE-MRI).
The study included 211 women with histopathologically confirmed breast cancer. We utilised a completely unsupervised convex analysis of mixtures (CAM) method by unmixing dynamic imaging series from heterogeneous tissues. Each tumour and the surrounding parenchyma were thus decomposed into multiple subregions, representing different vascular characterisations, from which radiomic features were extracted. A random forest model was trained and tested using a leave-one-out cross-validation (LOOCV) method to predict breast cancer subtypes. The predictive models from tumoural and peritumoural subregions were fused for classification.
Tumour and peritumour DCE-MR images were decomposed into three compartments, representing plasma input, fast-flow kinetics, and slow-flow kinetics. The tumour subregion related to fast-flow kinetics showed the best performance among the subregions for differentiating between patients with four molecular subtypes (area under the receiver operating characteristic curve (AUC) = 0.832), exhibiting an AUC value significantly (p < 0.0001) higher than that obtained with the entire tumour (AUC = 0.719). When the tumour- and parenchyma-based predictive models were fused, the performance, measured as the AUC, increased to 0.897; this value was significantly higher than that obtained with other tumour partition methods.
Radiomic analysis of intratumoural and peritumoural heterogeneity based on the decomposition of image time-series signals has the potential to more accurately identify tumour kinetic features and serve as a valuable clinical marker to enhance the prediction of breast cancer subtypes.
• Decomposition of image time-series signals has the potential to more accurately identify tumour kinetic features.
• Fusion of intratumoural- and peritumoural-based predictive models improves the prediction of breast cancer subtypes.
KeywordsBreast neoplasms Magnetic resonance imaging Diagnostic imaging
Convex analysis of mixtures
Grey level co-occurrence matrix
Kinetic pattern clustering
Peak enhancement rate
This work has received funding by the National Natural Science Foundation of China (61731008, 61871428, and 61401131), the Natural Science Foundation of Zhejiang Province of China (LJ19H180001, LZ15F010001), and the King Abdullah University of Science and Technology (KAUST) Office of Sponsored Research (OSR) under Award No. URF/1/3450-01.
Compliance with ethical standards
The scientific guarantor of this publication is Professor Lihua Li.
Conflict of interest
The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.
Statistics and biometry
No complex statistical methods were necessary for this paper.
Written informed consent was waived by the Institutional Review Board.
Institutional Review Board approval was obtained.
• diagnostic or prognostic study
• performed at one institution
- 4.Wan T, Bloch BN, Plecha D et al (2016) A radio-genomics approach for identifying high risk estrogen receptor-positive breast cancers on DCE-MRI: preliminary results in predicting OncotypeDX risk scores. Sci Rep 6:21394Google Scholar
- 7.Sutton EJ, Dashevsky BZ, Oh JH et al (2016) Breast cancer molecular subtype classifier that incorporates MRI features. J Magn Reson Imaging 44(1):122–129Google Scholar
- 8.Wu J, Cui Y, Sun X et al (2017) Unsupervised clustering of quantitative image phenotypes reveals breast cancer subtypes with distinct prognoses and molecular pathways. Clin Cancer Res 23:3334–3342Google Scholar
- 10.Fan M, Cheng H, Zhang P et al (2018) DCE-MRI texture analysis with tumor subregion partitioning for predicting Ki-67 status of estrogen receptor-positive breast cancers. J Magn Reson Imaging 48:237–247Google Scholar
- 11.Chaudhury B, Zhou M, Goldgof DB et al (2015) Heterogeneity in intratumoral regions with rapid gadolinium washout correlates with estrogen receptor status and nodal metastasis. J Magn Reson Imaging 42:1421–1430Google Scholar
- 13.Braman NM, Etesami M, Prasanna P et al (2017) Intratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI. Breast Cancer Res 19:57Google Scholar
- 15.Burnside ES, Drukker K, Li H et al (2016) Using computer-extracted image phenotypes from tumors on breast magnetic resonance imaging to predict breast cancer pathologic stage. Cancer 122:748–757Google Scholar
- 17.Chen L, Choyke PL, Wang N et al (2014) Unsupervised deconvolution of dynamic imaging reveals intratumor vascular heterogeneity and repopulation dynamics. PLoS One 9:e112143Google Scholar
- 18.Chen L, Chan TH, Choyke PL et al (2011) CAM-CM: a signal deconvolution tool for in vivo dynamic contrast-enhanced imaging of complex tissues. Bioinformatics 27:2607–2609Google Scholar
- 19.Wang N, Gong T, Clarke R et al (2015) UNDO: a Bioconductor R package for unsupervised deconvolution of mixed gene expressions in tumor samples. Bioinformatics 31:137–139Google Scholar
- 22.Yili Z, Xiaoyan H, Hongwen D et al (2009) The value of diffusion-weighted imaging in assessing the ADC changes of tissues adjacent to breast carcinoma. BMC Cancer 9:18Google Scholar
- 24.Wu J, Li B, Sun X et al (2017) Heterogeneous enhancement patterns of tumor-adjacent parenchyma at MR imaging are associated with dysregulated signaling pathways and poor survival in breast cancer. Radiology 285:401–413Google Scholar
- 25.Ashraf A, Gaonkar B, Mies C et al (2015) Breast DCE-MRI kinetic heterogeneity tumor markers: preliminary associations with neoadjuvant chemotherapy response. Transl Oncol 8:154–162Google Scholar
- 26.Nie K, Chen JH, Chan S et al (2008) Development of a quantitative method for analysis of breast density based on three-dimensional breast MRI. Med Phys 35:5253–5262Google Scholar
- 28.Wu S, Berg WA, Zuley ML et al (2016) Breast MRI contrast enhancement kinetics of normal parenchyma correlate with presence of breast cancer. Breast Cancer Res 18:76Google Scholar
- 29.Wang N, Hoffman EP, Chen L et al (2016) Mathematical modelling of transcriptional heterogeneity identifies novel markers and subpopulations in complex tissues. Sci Rep 6:18909Google Scholar
- 32.Wu J, Sun XL, Wang J et al (2017) Identifying relations between imaging phenotypes and molecular subtypes of breast cancer: model discovery and external validation. J Magn Reson Imaging 46:1017–1027Google Scholar
- 33.Yamaguchi K, Abe H, Newstead GM et al (2015) Intratumoral heterogeneity of the distribution of kinetic parameters in breast cancer: comparison based on the molecular subtypes of invasive breast cancer. Breast Cancer 22:496–502Google Scholar
- 35.Kim JY, Kim SH, Kim YJ et al (2015) Enhancement parameters on dynamic contrast enhanced breast MRI: do they correlate with prognostic factors and subtypes of breast cancers? Magn Reson Imaging 33:72–80Google Scholar
- 36.Amornsiripanitch N, Nguyen VT, Rahbar H et al (2018) Diffusion weighted MRI characteristics associated with prognostic pathological factors and recurrence risk in invasive ER+/HER2- breast cancers. J Magn Reson Imaging 48:226–236Google Scholar
- 37.Henderson S, Purdie C, Michie C et al (2017) Interim heterogeneity changes measured using entropy texture features on T2-weighted MRI at 3.0 T are associated with pathological response to neoadjuvant chemotherapy in primary breast cancer. Eur Radiol 27:4602–4611Google Scholar