Preliminary exploration of radiomic mammographic analysis in triple negative breast cancer related to BRCA profile
Year: 2026
Type: article
Study design: Observational Study
Abstract: This retrospective study evaluated the applicability of radiomics analysis to mammographic images of patients with triple-negative breast cancer (TNBC) to identify features differentiating BRCA gene's mutational status. The mammographic images of 52 patients histologically diagnosed with TNBC, (13 BRCA-mutated patients and 39 BRCA wild-type ones), were included and 53 tumor lesions were manually segmented in the mammographic projection where they were better demarcable. An additional elliptical ROI of standard size was drawn in the most homogeneous area of the contralateral healthy gland, using the analogue mammographic projection of the same date or, if not available, of the corresponding bilateral mammographic investigation closer to the time of diagnosis. Lesions consisted of 36 masses, 2 pathological microcalcifications, and 15 masses with microcalcifications. Radiomic features were extracted using Pyradiomics-3D. Preliminary analysis confirmed feasibility and showed differences in texture features, particularly GLCM SumEntropy, between BRCA-mutated and non-mutated patients. Moreover, the study enhanced the role of healthy glandular tissue in distinguishing the two groups, supporting and reinforcing previous MRI-based radiomics findings in the same population. The study concludes that radiomics analysis of diagnostic mammograms in TNBC patients is feasible and may help build predictive models to discriminate between BRCA mutated and non-mutated patients.
Source: Scientific Reports
Authors: Annarita Pecchi, Giulia Sessa, Luca Nocetti, Cecilia Beretta, Chiara Bozzola, Erica Balboni, Giulia Besutti, Angela Toss, Laura Cortesi, Gabriele Guidi, Massimo Dominici, Pietro Torricelli
Language: English
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: gold
Estimated APC paid: $2,690
Funder: European Commission
Award: G1033601615
OpenAlex ID: W7128856277
