Repository logo
 

3D DCE-MRI Radiomic Analysis for Malignant Lesion Prediction in Breast Cancer Patients.

Accepted version
Peer-reviewed

Type

Article

Change log

Authors

Militello, Carmelo 
Dimarco, Mariangela 
Orlando, Alessia 

Abstract

RATIONALE AND OBJECTIVES: To develop and validate a radiomic model, with radiomic features extracted from breast Dynamic Contrast-Enhanced Magnetic Resonance Imaging (DCE-MRI) from a 1.5T scanner, for predicting the malignancy of masses with enhancement. Images were acquired using an 8-channel breast coil in the axial plane. The rationale behind this study is to show the feasibility of a radiomics-powered model that could be integrated into the clinical practice by exploiting only standard-of-care DCE-MRI with the goal of reducing the required image pre-processing (ie, normalization and quantitative imaging map generation). MATERIALS AND METHODS: 107 radiomic features were extracted from a manually annotated dataset of 111 patients, which was split into discovery and test sets. A feature calibration and pre-processing step was performed to find only robust non-redundant features. An in-depth discovery analysis was performed to define a predictive model: for this purpose, a Support Vector Machine (SVM) was trained in a nested 5-fold cross-validation scheme, by exploiting several unsupervised feature selection methods. The predictive model performance was evaluated in terms of Area Under the Receiver Operating Characteristic (AUROC), specificity, sensitivity, PPV and NPV. The test was performed on unseen held-out data. RESULTS: The model combining Unsupervised Discriminative Feature Selection (UDFS) and SVMs on average achieved the best performance on the blinded test set: AUROC = 0.725±0.091, sensitivity = 0.709±0.176, specificity = 0.741±0.114, PPV = 0.72±0.093, and NPV = 0.75±0.114. CONCLUSION: In this study, we built a radiomic predictive model based on breast DCE-MRI, using only the strongest enhancement phase, with promising results in terms of accuracy and specificity in the differentiation of malignant from benign breast lesions.

Description

Keywords

Breast cancer, Dynamic contrast-enhanced magnetic resonance imaging, machine learning, Radiomics, unsupervised feature selection, Support vector machines, Breast, Breast Neoplasms, Female, Humans, Magnetic Resonance Imaging, ROC Curve, Retrospective Studies, Support Vector Machine

Journal Title

Acad Radiol

Conference Name

Journal ISSN

1076-6332
1878-4046

Volume Title

Publisher

Elsevier BV
Sponsorship
Cancer Research UK (C96/A25177)
This study has received funding by the GeSeTon project (Italian MISE Grant No. 489 of 21/02/2018). This study has also been partially supported by The Mark Foundation for Cancer Research and Cancer Research UK Cambridge Centre [C9685/A25177] and by the Royal Society for the International Exchanges 2020 Cost Share with the Italian CNR (project No. IEC/R2/202313). Additional support was also provided by the National Institute of Health Research (NIHR) Cambridge Biomedical Research Centre. The views expressed are those of the authors and not necessarily those of the NHS, the NIHR, or the Department of Health and Social Care.