The detection of suspicious microcalcifications on mammography represents one of the earliest signs of a malignant breast tumor. Assessing microcalcifications{\textquoteright} characteristics based on their appearance on 2D breast imaging modalities is in many cases challenging for radiologists. The aims of this study were to: (a) analyse the association of shape and texture properties of breast microcalcifications (extracted by scanning breast tissue with a high resolution 3D scanner) with malignancy, (b) evaluate microcalcifications{\textquoteright} potential to diagnose benign/malignant patients.Biopsy samples of 94 female patients with suspicious microcalcifications detected during a mammography, were scanned using a micro-CT scanner at a resolution of 9 μm. Several preprocessing techniques were applied on 3504 extracted microcalcifications. A high amount of radiomic features were extracted in an attempt to capture differences among microcalcifications occurring in benign and malignant lesions. Machine learning algorithms were used to diagnose: (a) individual microcalcifications, (b) samples. For the samples, several methodologies to combine individual microcalcification results into sample results were evaluated.We could classify individual microcalcifications with 77.32% accuracy, 61.15% sensitivity and 89.76% specificity. At the sample level diagnosis, we achieved an accuracy of 84.04%, sensitivity of 86.27% and specificity of 81.39%.By studying microcalcifications{\textquoteright} characteristics at a level of details beyond what is currently possible by using conventional breast imaging modalities, our classification results demonstrated a strong association between breast microcalcifications and malignancies. Microcalcification{\textquoteright}s texture features extracted in transform domains, have higher discriminating power to classify benign/malignant individual microcalcifications and samples compared to pure shape-features.
Brahimetaj, R, Willekens, I, Massart, A, Forsyth, R, Cornelis, JPH, De Mey, J & Jansen, B 2022, 'Improved automated early detection of breast cancer based on high resolution 3D micro-CT microcalcification images', BMC Cancer, vol. 22, no. 1, 162, pp. 162. https://doi.org/10.1186/s12885-021-09133-4
Brahimetaj, R., Willekens, I., Massart, A., Forsyth, R., Cornelis, J. P. H., De Mey, J., & Jansen, B. (2022). Improved automated early detection of breast cancer based on high resolution 3D micro-CT microcalcification images. BMC Cancer, 22(1), 162. Article 162. https://doi.org/10.1186/s12885-021-09133-4
@article{37e02c307ac04be88d87708f2a75d3e9,
title = "Improved automated early detection of breast cancer based on high resolution 3D micro-CT microcalcification images",
abstract = "The detection of suspicious microcalcifications on mammography represents one of the earliest signs of a malignant breast tumor. Assessing microcalcifications{\textquoteright} characteristics based on their appearance on 2D breast imaging modalities is in many cases challenging for radiologists. The aims of this study were to: (a) analyse the association of shape and texture properties of breast microcalcifications (extracted by scanning breast tissue with a high resolution 3D scanner) with malignancy, (b) evaluate microcalcifications{\textquoteright} potential to diagnose benign/malignant patients.Biopsy samples of 94 female patients with suspicious microcalcifications detected during a mammography, were scanned using a micro-CT scanner at a resolution of 9 μm. Several preprocessing techniques were applied on 3504 extracted microcalcifications. A high amount of radiomic features were extracted in an attempt to capture differences among microcalcifications occurring in benign and malignant lesions. Machine learning algorithms were used to diagnose: (a) individual microcalcifications, (b) samples. For the samples, several methodologies to combine individual microcalcification results into sample results were evaluated.We could classify individual microcalcifications with 77.32% accuracy, 61.15% sensitivity and 89.76% specificity. At the sample level diagnosis, we achieved an accuracy of 84.04%, sensitivity of 86.27% and specificity of 81.39%.By studying microcalcifications{\textquoteright} characteristics at a level of details beyond what is currently possible by using conventional breast imaging modalities, our classification results demonstrated a strong association between breast microcalcifications and malignancies. Microcalcification{\textquoteright}s texture features extracted in transform domains, have higher discriminating power to classify benign/malignant individual microcalcifications and samples compared to pure shape-features.",
keywords = "Breast Cancer, Microcalcifications, Computer aided detection and diagnosis systems, X-ray micro-CT, Radiomics, Machine learning",
author = "Redona Brahimetaj and Inneke Willekens and Annelien Massart and Ramses Forsyth and Cornelis, {Jan Paul Herman} and {De Mey}, Johan and Bart Jansen",
year = "2022",
month = feb,
day = "11",
doi = "10.1186/s12885-021-09133-4",
language = "English",
volume = "22",
pages = "162",
journal = "BMC Cancer",
issn = "1471-2407",
publisher = "BioMed Central",
number = "1",
}