Improved automated early detection of breast cancer based on high resolution 3D micro-CT microcalcification images

BMC Cancer

Jan Cornelis¹  Redona Brahimetaj¹  Bart Jansen²  Ramses Forsyth³  Johan De Mey⁴  Inneke Willekens⁴  Annelien Massart⁴ 

[1] Department of Electronics and Informatics (ETRO), Vrije Universiteit Brussel (VUB), Pleinlaan 2, B-1050, Brussels, Belgium;Department of Electronics and Informatics (ETRO), Vrije Universiteit Brussel (VUB), Pleinlaan 2, B-1050, Brussels, Belgium;IMEC, Kapeldreef 75, B-3001, Leuven, Belgium;Pathology Department, Universitair Ziekenhuis (UZ) Brussels, Laarbeeklaan 101, 1090, Brussels, Belgium;Radiology Department, Universitair Ziekenhuis (UZ) Brussels, Laarbeeklaan 101, 1090, Brussels, Belgium;

关键词: Breast Cancer;    Microcalcifications;    Computer aided detection and diagnosis systems;    X-ray micro-CT;    Radiomics;    Machine learning;   

DOI  :  10.1186/s12885-021-09133-4

来源: Springer

【 摘 要 】

BackgroundThe detection of suspicious microcalcifications on mammography represents one of the earliest signs of a malignant breast tumor. Assessing microcalcifications’ 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’ potential to diagnose benign/malignant patients.MethodsBiopsy 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.ResultsWe 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%.ConclusionsBy studying microcalcifications’ 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’s texture features extracted in transform domains, have higher discriminating power to classify benign/malignant individual microcalcifications and samples compared to pure shape-features.

【 授权许可】

CC BY