In this study we propose a Computer Aided Detection and Diagnosis System to detect breast cancer based on characteristics of individual microcalcifications (main indicators of an early breast cancer) by scanning breast tissue with micro-CT, a high resolution 3D imaging modality. By integrating supervised machine learning techniques with feature extraction and feature selection methods, we are able to classify MCs as benign or malignant with 75.88% accuracy, 62.13% sensitivity and 86.39% specificity, outperforming the state of the art.
Brahimetaj, R, Papavasileiou, E, Temmermans, F, Cornelis, B, Willekens, I, De Mey, J & Jansen, B 2019, 'Computer Aided Detection and Diagnosis System for Breast Cancer Detection Based on High Resolution 3D micro-CT Breast Microcalcifications', 31st Benelux Conference on Artificial Intelligence and the 28th Belgian Dutch Conference on Machine Learning, BNAIC/BENELEARN 2019, Brussels, Belgium, 6/11/19 - 8/11/19.
Brahimetaj, R., Papavasileiou, E., Temmermans, F., Cornelis, B., Willekens, I., De Mey, J., & Jansen, B. (2019). Computer Aided Detection and Diagnosis System for Breast Cancer Detection Based on High Resolution 3D micro-CT Breast Microcalcifications. Poster session presented at 31st Benelux Conference on Artificial Intelligence and the 28th Belgian Dutch Conference on Machine Learning, BNAIC/BENELEARN 2019, Brussels, Belgium.
@conference{1e09525dc7d04b5993afd0ac24dbc7c5,
title = "Computer Aided Detection and Diagnosis System for Breast Cancer Detection Based on High Resolution 3D micro-CT Breast Microcalcifications",
abstract = "In this study we propose a Computer Aided Detection and Diagnosis System to detect breast cancer based on characteristics of individual microcalcifications (main indicators of an early breast cancer) by scanning breast tissue with micro-CT, a high resolution 3D imaging modality. By integrating supervised machine learning techniques with feature extraction and feature selection methods, we are able to classify MCs as benign or malignant with 75.88% accuracy, 62.13% sensitivity and 86.39% specificity, outperforming the state of the art.",
keywords = "Breast cancer, Computer aided detection and diagnosis system, Machine learning, Microcalcifications, Radiomics",
author = "Redona Brahimetaj and Evgenia Papavasileiou and Frederik Temmermans and Bruno Cornelis and Inneke Willekens and {De Mey}, Johan and Bart Jansen",
year = "2019",
language = "English",
note = "31st Benelux Conference on Artificial Intelligence and the 28th Belgian Dutch Conference on Machine Learning, BNAIC/BENELEARN 2019 ; Conference date: 06-11-2019 Through 08-11-2019",
}