Advertisement

MRI Radiomics of Breast Cancer: Machine Learning-Based Prediction of Lymphovascular Invasion Status

Published:December 04, 2021DOI:https://doi.org/10.1016/j.acra.2021.10.026

      Rationale and Objectives

      In patients with breast cancer (BC), lymphovascular invasion (LVI) status is considered an important prognostic factor. We aimed to develop machine learning (ML)-based radiomics models for the prediction of LVI status in patients with BC, using preoperative MRI images.

      Materials and Methods

      This retrospective study included patients with BC with known LVI status and preoperative MRI. The dataset was split into training and unseen testing sets by stratified sampling with a 2:1 ratio. 2D and 3D radiomic features were extracted from contrast-enhanced T1 weighted images (C+T1W) and apparent diffusion coefficient (ADC) maps. The reliability of the features was assessed with two radiologists' segmentation data. Dimension reduction was done with reliability analysis, multi-collinearity analysis, removal of low-variance features, and feature selection. ML models were created with base, tuned, and boosted random forest algorithms.

      Result

      A total of 128 lesions (LVI-positive, 76; LVI-negative, 52) were included. The best model performance was achieved with tunning and boosting model based on 3D ADC maps and selected four radiomic features. The area under the curve and accuracy were 0.726 and 63.5% in the training data, 0.732 and 76.7% in the test data, respectively. The overall sensitivity and positive predictive values were 68% and 69.6% in the training data, 84.6% and 78.6% in the test data, respectively.

      Conclusion

      : ML and radiomics based on 3D segmentation of ADC maps can be used to predict LVI status in BC, with satisfying performance.

      Key Words

      Abbreviations:

      ADC (Apparent diffusion coefficient), AUC (Area under the curve), BC (Breast cancer), C+T1W (Contrast-enhanced T1 weighted), CV (Cross-validation), DWI (Diffusion-weighted imaging), LVI (Lymphovascular invasion), ML (Machine learning), MRI (Magnetic resonance imaging), NAC (Neoadjuvant chemotherapy), PPV (Positive predictive value), RF (Random Forest), 2D (Two dimensional), 3D (Three dimensional)
      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Academic Radiology
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      REFERENCES

        • Ma Q
        • Dieterich LC
        • Detmar M
        Multiple roles of lymphatic vessels in tumor progression.
        Curr Opin Immunol. 2018; 53: 7-12
        • Zhang S
        • Zhang D
        • Gong M
        • Wen L
        • Liao C
        • Zou L
        High lymphatic vessel density and presence of lymphovascular invasion both predict poor prognosis in breast cancer.
        BMC Cancer. 2017; 17: 335
        • Karlsson P
        • Cole BF
        • Price KN
        • et al.
        The role of the number of uninvolved lymph nodes in predicting locoregional recurrence in breast cancer.
        J Clin Oncol. 2007; 25: 2019-2026
        • Lowery AJ
        • Kell MR
        • Glynn RW
        • Kerin MJ
        • Sweeney KJ
        Locoregional recurrence after breast cancer surgery: a systematic review by receptor phenotype.
        Breast Cancer Res Treat. 2012; 133: 831-841
        • van Dongen JA
        • Voogd AC
        • Fentiman IS
        • et al.
        Long-term results of a randomized trial comparing breast-conserving therapy with mastectomy: european organization for research and treatment of cancer 10801 trial.
        J Natl Cancer Inst. 2000; 92: 1143-1150
        • Nielsen HM
        • Overgaard M
        • Grau C
        • Jensen AR
        • Overgaard J
        • Danish Breast Cancer Cooperative Group
        Study of failure pattern among high-risk breast cancer patients with or without postmastectomy radiotherapy in addition to adjuvant systemic therapy: long-term results from the Danish Breast Cancer Cooperative Group DBCG 82 b and c randomized studies.
        J Clin Oncol. 2006; 24: 2268-2275
        • Ignatiadis M
        • Buyse M
        • Sotiriou C
        St gallen international expert consensus on the primary therapy of early breast cancer: an invaluable tool for physicians and scientists.
        Ann Oncol. 2015; 26: 1519-1520
        • Ragage F
        • Debled M
        • MacGrogan G
        • et al.
        Is it useful to detect lymphovascular invasion in lymph node-positive patients with primary operable breast cancer?.
        Cancer. 2010; 116: 3093-3101
      1. Cheung SM, Husain E, Mallikourti V, Masannat Y, Heys S, He J. Intra-tumoural lipid composition and lymphovascular invasion in breast cancer via non-invasive magnetic resonance spectroscopy. Eur Radiol 202;31:3703–3711.

        • Shafiq-Ul-Hassan M
        • Zhang GG
        • Latifi K
        • et al.
        Intrinsic dependencies of CT radiomic features on voxel size and number of gray levels.
        Med Phys. 2017; 44: 1050-1062
        • Ye DM
        • Wang HT
        • Yu T
        The application of radiomics in breast MRI: a review.
        Technol Cancer Res Treat. 2020; 191533033820916191
        • Larue RTHM
        • van Timmeren JE
        • de Jong EEC
        • et al.
        Influence of gray level discretization on radiomic feature stability for different CT scanners, tube currents and slice thicknesses: a comprehensive phantom study.
        Acta Oncol. 2017; 56 (1544–1153)
        • Duron L
        • Balvay D
        • Vande Perre S
        • et al.
        Gray-level discretization impacts reproducible MRI radiomics texture features.
        PLoS One. 2019; 14e0213459
        • van Griethuysen JJM
        • Fedorov A
        • Parmar C
        • et al.
        Computational radiomics system to decode the radiographic phenotype.
        Cancer Res. 2017; 77: e104-e107
        • Saha A
        • Harowicz MR
        • Grimm LJ
        • et al.
        A machine learning approach to radiogenomics of breast cancer: a study of 922 subjects and 529 DCE-MRI features.
        Br J Cancer. 2018; 119: 508-516
        • Erickson BJ
        • Korfiatis P
        • Akkus Z
        • Kline TL
        Machine learning for medical imaging.
        Radiographics. 2017; 37: 505-515
        • Grimm LJ
        • Zhang J
        • Mazurowski MA
        Computational approach to radiogenomics of breast cancer: luminal A and luminal B molecular subtypes are associated with imaging features on routine breast MRI extracted using computer vision algorithms.
        J Magn Reson Imaging. 2015; 42: 902-907
        • Mazurowski M.A.
        • Zhang J.
        • Grimm L.J.
        • Yoon S.C.
        • Silber J.I.
        Radiogenomic analysis of breast cancer: luminal b molecular subtype is associated with enhancement dynamics at MR imaging.
        Radiology. 2014; 273: 365-372
        • Granzier RWY
        • Verbakel NMH
        • Ibrahim A
        • et al.
        MRI-based radiomics in breast cancer: feature robustness with respect to inter-observer segmentation variability.
        Sci Rep. 2020; 10: 14163
        • Liu Z
        • Feng B
        • Li C
        • et al.
        Preoperative prediction of lymphovascular invasion in invasive breast cancer with dynamic contrast-enhanced-MRI-based radiomics.
        J Magn Reson Imaging. 2019; 50: 847-857
      2. Kayadibi Y, Kocak B, Ucar N, Akan YN, Akbas P, Bektas S. Radioproteomics in Breast Cancer: Prediction of Ki-67 Expression With MRI-based Radiomic Models. Acad Radiol. 2021 Mar 17:S1076-6332(21)00063-5. doi: 10.1016/j.acra.2021.02.001. Epub ahead of print. PMID: 33744071.

        • Kocak B
        • Ates E
        • Durmaz ES
        • Ulusan MB
        • Kilickesmez O
        Influence of segmentation margin on machine learning-based high-dimensional quantitative CT texture analysis: a reproducibility study on renal clear cell carcinomas.
        Eur Radiol. 2019; 29: 4765-4775
        • Pinder SE
        • Ellis IO
        • Galea M
        • O'Rouke S
        • Blamey RW
        • Elston CW
        Pathological prognostic factors in breast cancer. III. vascular invasion: relationship with recurrence and survival in a large study with long-term follow-up.
        Histopathology. 1994; 24: 41-47
        • Collewet G
        • Strzelecki M
        • Mariette F
        Influence of MRI acquisition protocols and image intensity normalization methods on texture classification.
        Magn Reson Imaging. 2004; 22: 81-91
        • Koçak B
        • Durmaz EŞ
        • Ateş E
        • Kılıçkesmez Ö
        Radiomics with artificial intelligence: a practical guide for beginners.
        Diagn Interv Radiol. 2019; 25: 485-495
        • Koo TK
        • Li MY
        A guideline of selecting and reporting intraclass correlation coefficients for reliability research.
        J Chiropr Med. 2016; 15: 155-163
        • Kursa MB
        • Rudnicki WR
        Feature selection with the Boruta package.
        J Stat Softw. 2010; 36: 1-13
        • Chawla NV
        • Bowyer KW
        • Hall LO
        • Kegelmeyer WP
        SMOTE: synthetic minority over-sampling technique.
        J Artif Intell Res. 2002; 16: 321-357
        • Liu Z
        • Li R
        • Liang K
        • et al.
        Value of digital mammography in predicting lymphovascular invasion of breast cancer.
        BMC Cancer. 2020; 20: 274
        • Uematsu T
        • Kasami M
        • Watanabe J
        Is evaluation of the presence of prepectoral edema on T2-weighted with fat-suppression 3 T breast MRI a simple and readily available noninvasive technique for estimation of prognosis in patients with breast cancer?.
        Breast Cancer. 2014; 21: 684-692
        • Cheon H
        • Kim HJ
        • Lee SM
        • et al.
        Preoperative MRI features associated with lymphovascular invasion in node-negative invasive breast cancer: a propensity-matched analysis.
        J Magn Reson Imaging. 2017; 46: 1037-1044
        • Macchini M
        • Ponziani M
        • Iamurri AP
        • et al.
        Role of DCE-MR in predicting breast cancer subtypes.
        Radiol Med. 2018; 123: 753-764
        • Komatsu S
        • Lee CJ
        • Ichikawa D
        • et al.
        Predictive value of the time-intensity curves on dynamic contrast-enhanced magnetic resonance imaging for lymphatic spreading in breast cancer.
        Surg Today. 2005; 35: 720-724
        • Igarashi T
        • Furube H
        • Ashida H
        • Ojiri H
        Breast MRI for prediction of lymphovascular invasion in breast cancer patients with clinically negative axillary lymph nodes.
        Eur J Radiol. 2018; 107: 111-118
        • Mori N
        • Mugikura S
        • Takasawa C
        • et al.
        Peritumoral apparent diffusion coefficients for prediction of lymphovascular invasion in clinically node-negative invasive breast cancer.
        Eur Radiol. 2016; 26: 331-339
        • Ni-Jia-Ti MYL
        • Ai-Hai-Ti DLARM
        • Huo-Jia ASKEJ
        • et al.
        Development of a risk-stratification scoring system for predicting lymphovascular invasion in breast cancer.
        BMC Cancer. 2020; 20: 94
        • Ya G
        • Wen F
        • Xing-Ru L
        • Zhuan-Zhuan G
        • Jun-Qiang L
        Difference of DCE-MRI parameters at different time points and their predictive value for axillary lymph node metastasis of breast cancer.
        Acad Radiol. 2021; (S1076-6332(21)00022-2. https://doi.org/10.1016/j.acra.2021.01.013. Epub ahead of print. PMID: 33504446)
        • Ramakrishnan R
        • Khan SA
        • Badve S
        Morphological changes in breast tissue with menstrual cycle.
        Mod Pathol. 2002; 15: 1348-1356
        • Aleskandarany MA
        • Vandenberghe ME
        • Marchiò C
        • Ellis IO
        • Sapino A
        • Rakha EA
        Tumour heterogeneity of breast cancer: from morphology to personalised medicine.
        Pathobiology. 2018; 85: 23-34
        • Boros M
        • Moncea D
        • Moldovan C
        • Podoleanu C
        • Georgescu R
        • Stolnicu S
        Intratumoral heterogeneity for Ki-67 index in invasive breast carcinoma: a study on 131 consecutive cases.
        ApplImmunohistochemMol Morphol. 2017; 25: 338-340
        • Liang C
        • Cheng Z
        • Huang Y
        • et al.
        An MRI-based radiomics classifier for preoperative prediction of Ki-67 status in breast cancer.
        Acad Radiol. 2018; 25: 1111-1117
        • Ding J
        • Chen S
        • Serrano Sosa M
        • et al.
        Optimizing the peritumoral region size in radiomics analysis for sentinel lymph node status prediction in breast cancer.
        Acad Radiol. 2020; (S1076-6332(20)30602-4. https://doi.org/10.1016/j.acra.2020.10.015. Epub ahead of print. PMID: 33160860)
        • Cui X
        • Wang N
        • Zhao Y
        • et al.
        Preoperative prediction of axillary lymph node metastasis in breast cancer using radiomics features of DCE-MRI.
        Sci Rep. 2019; 9: 2240
        • Tan H
        • Gan F
        • Wu Y
        • et al.
        Preoperative prediction of axillary lymph node metastasis in breast carcinoma using radiomics features based on the fat-suppressed T2 sequence.
        Acad Radiol. 2020; 27: 1217-1225
      3. Zhan C, Hu Y, Wang X, Liu H, Xia L, Ai T. Prediction of axillary lymph node metastasis in breast cancer using intra-peritumoral textural transition analysis based on dynamic contrast-enhanced magnetic resonance imaging. Acad Radiol 202;S1076-6332.

        • de Figueiredo EHMSG
        • Borgonovi AFNG
        • Doring TM
        Basic concepts of MR imaging, diffusion MR imaging, and diffusion tensor imaging.
        Magn Reson Imaging Clin N Am. 2011; 19: 1-22
        • Choi BB
        Associations between apparent diffusion coefficient values and the prognostic factors of breast cancer.
        J Comput Assist Tomogr. 2019; 43: 931-936
        • Luo Y
        • Mei D
        • Gong J
        • Zuo M
        • Guo X
        Multiparametric MRI-based radiomics nomogram for predicting lymphovascular space invasion in endometrial carcinoma.
        J Magn Reson Imaging. 2020; 52: 1257-1262
        • Yardımcı AH
        • Koçak B
        • Bektaş CT
        • et al.
        Tubular gastric adenocarcinoma: machine learning-based CT texture analysis for predicting lymphovascular and perineural invasion.
        DiagnInterv Radiol. 2020; 26: 515
        • Chen X
        • Chen G
        • Pu H
        • et al.
        DWI and T2-weighted MRI volumetry in resectable rectal cancer: correlation with lymphovascular invasion and lymph node metastases.
        Am J Roentgenol. 2019; 212: 1271-1278
        • Mann RM
        • Cho N
        • Moy L
        Breast MRI: state of the art.
        Radiology. 2019; 292: 520-536