Cargando…
Breast Cancer Classification on Multiparametric MRI – Increased Performance of Boosting Ensemble Methods
Introduction: This study aims to assess the utility of Boosting ensemble classification methods for increasing the diagnostic performance of multiparametric Magnetic Resonance Imaging (mpMRI) radiomic models, in differentiating benign and malignant breast lesions. Methods: The dataset includes mpMR...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
SAGE Publications
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8966070/ https://www.ncbi.nlm.nih.gov/pubmed/35341421 http://dx.doi.org/10.1177/15330338221087828 |
_version_ | 1784678575231729664 |
---|---|
author | Vamvakas, Alexandros Tsivaka, Dimitra Logothetis, Andreas Vassiou, Katerina Tsougos, Ioannis |
author_facet | Vamvakas, Alexandros Tsivaka, Dimitra Logothetis, Andreas Vassiou, Katerina Tsougos, Ioannis |
author_sort | Vamvakas, Alexandros |
collection | PubMed |
description | Introduction: This study aims to assess the utility of Boosting ensemble classification methods for increasing the diagnostic performance of multiparametric Magnetic Resonance Imaging (mpMRI) radiomic models, in differentiating benign and malignant breast lesions. Methods: The dataset includes mpMR images of 140 female patients with mass-like breast lesions (70 benign and 70 malignant), consisting of Dynamic Contrast Enhanced (DCE) and T2-weighted sequences, and the Apparent Diffusion Coefficient (ADC) calculated from the Diffusion Weighted Imaging (DWI) sequence. Tumor masks were manually defined in all consecutive slices of the respective MRI volumes and 3D radiomic features were extracted with the Pyradiomics package. Feature dimensionality reduction was based on statistical tests and the Boruta wrapper. Hierarchical Clustering on Spearman's rank correlation coefficients between features and Random Forest classification for obtaining feature importance, were implemented for selecting the final feature subset. Adaptive Boosting (AdaBoost), Gradient Boosting (GB), Extreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM) classifiers, were trained and tested with bootstrap validation in differentiating breast lesions. A Support Vector Machine (SVM) classifier was also exploited for comparison. The Receiver Operator Characteristic (ROC) curves and DeLong's test were utilized to evaluate the classification performances. Results: The final feature subset consisted of 5 features derived from the lesion shape and the first order histogram of DCE and ADC images volumes. XGboost and LGBM achieved statistically significantly higher average classification performances [AUC = 0.95 and 0.94 respectively], followed by Adaboost [AUC = 0.90], GB [AUC = 0.89] and SVM [AUC = 0.88]. Conclusion: Overall, the integration of Ensemble Learning methods within mpMRI radiomic analysis can improve the performance of computer-assisted diagnosis of breast cancer lesions. |
format | Online Article Text |
id | pubmed-8966070 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | SAGE Publications |
record_format | MEDLINE/PubMed |
spelling | pubmed-89660702022-03-31 Breast Cancer Classification on Multiparametric MRI – Increased Performance of Boosting Ensemble Methods Vamvakas, Alexandros Tsivaka, Dimitra Logothetis, Andreas Vassiou, Katerina Tsougos, Ioannis Technol Cancer Res Treat Original Article Introduction: This study aims to assess the utility of Boosting ensemble classification methods for increasing the diagnostic performance of multiparametric Magnetic Resonance Imaging (mpMRI) radiomic models, in differentiating benign and malignant breast lesions. Methods: The dataset includes mpMR images of 140 female patients with mass-like breast lesions (70 benign and 70 malignant), consisting of Dynamic Contrast Enhanced (DCE) and T2-weighted sequences, and the Apparent Diffusion Coefficient (ADC) calculated from the Diffusion Weighted Imaging (DWI) sequence. Tumor masks were manually defined in all consecutive slices of the respective MRI volumes and 3D radiomic features were extracted with the Pyradiomics package. Feature dimensionality reduction was based on statistical tests and the Boruta wrapper. Hierarchical Clustering on Spearman's rank correlation coefficients between features and Random Forest classification for obtaining feature importance, were implemented for selecting the final feature subset. Adaptive Boosting (AdaBoost), Gradient Boosting (GB), Extreme Gradient Boosting (XGBoost) and Light Gradient Boosting Machine (LightGBM) classifiers, were trained and tested with bootstrap validation in differentiating breast lesions. A Support Vector Machine (SVM) classifier was also exploited for comparison. The Receiver Operator Characteristic (ROC) curves and DeLong's test were utilized to evaluate the classification performances. Results: The final feature subset consisted of 5 features derived from the lesion shape and the first order histogram of DCE and ADC images volumes. XGboost and LGBM achieved statistically significantly higher average classification performances [AUC = 0.95 and 0.94 respectively], followed by Adaboost [AUC = 0.90], GB [AUC = 0.89] and SVM [AUC = 0.88]. Conclusion: Overall, the integration of Ensemble Learning methods within mpMRI radiomic analysis can improve the performance of computer-assisted diagnosis of breast cancer lesions. SAGE Publications 2022-03-28 /pmc/articles/PMC8966070/ /pubmed/35341421 http://dx.doi.org/10.1177/15330338221087828 Text en © The Author(s) 2022 https://creativecommons.org/licenses/by-nc/4.0/This article is distributed under the terms of the Creative Commons Attribution-NonCommercial 4.0 License (https://creativecommons.org/licenses/by-nc/4.0/) which permits non-commercial use, reproduction and distribution of the work without further permission provided the original work is attributed as specified on the SAGE and Open Access page (https://us.sagepub.com/en-us/nam/open-access-at-sage). |
spellingShingle | Original Article Vamvakas, Alexandros Tsivaka, Dimitra Logothetis, Andreas Vassiou, Katerina Tsougos, Ioannis Breast Cancer Classification on Multiparametric MRI – Increased Performance of Boosting Ensemble Methods |
title | Breast Cancer Classification on Multiparametric MRI – Increased Performance of Boosting Ensemble Methods |
title_full | Breast Cancer Classification on Multiparametric MRI – Increased Performance of Boosting Ensemble Methods |
title_fullStr | Breast Cancer Classification on Multiparametric MRI – Increased Performance of Boosting Ensemble Methods |
title_full_unstemmed | Breast Cancer Classification on Multiparametric MRI – Increased Performance of Boosting Ensemble Methods |
title_short | Breast Cancer Classification on Multiparametric MRI – Increased Performance of Boosting Ensemble Methods |
title_sort | breast cancer classification on multiparametric mri – increased performance of boosting ensemble methods |
topic | Original Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8966070/ https://www.ncbi.nlm.nih.gov/pubmed/35341421 http://dx.doi.org/10.1177/15330338221087828 |
work_keys_str_mv | AT vamvakasalexandros breastcancerclassificationonmultiparametricmriincreasedperformanceofboostingensemblemethods AT tsivakadimitra breastcancerclassificationonmultiparametricmriincreasedperformanceofboostingensemblemethods AT logothetisandreas breastcancerclassificationonmultiparametricmriincreasedperformanceofboostingensemblemethods AT vassioukaterina breastcancerclassificationonmultiparametricmriincreasedperformanceofboostingensemblemethods AT tsougosioannis breastcancerclassificationonmultiparametricmriincreasedperformanceofboostingensemblemethods |