Breast MRI texture analysis for prediction of BRCA-associated genetic risk

Abstract

Background: BRCA1/2 deleterious variants account for most of the hereditary breast and ovarian cancer cases. Prediction models and guidelines for the assessment of genetic risk rely heavily on criteria with high variability such as family cancer history. Here we investigated the efficacy of MRI (magnetic resonance imaging) texture features as a predictor for BRCA mutation status. Methods: A total of 41 female breast cancer individuals at high genetic risk, sixteen with a BRCA1/2 pathogenic variant and twenty five controls were included. From each MRI 4225 computer-extracted voxels were analyzed. Non-imaging features including clinical, family cancer history variables and triple negative receptor status (TNBC) were complementarily used. Lasso-principal component regression (L-PCR) analysis was implemented to compare the predictive performance, assessed as area under the curve (AUC), when imaging features were used, and lasso logistic regression or conventional logistic regression for the remaining analyses. Results: Lasso-selected imaging principal components showed the highest predictive value (AUC 0.86), surpassing family cancer history. Clinical variables comprising age at disease onset and bilateral breast cancer yielded a relatively poor AUC (~0.56). Combination of imaging with the non-imaging variables led to an improvement of predictive performance in all analyses, with TNBC along with the imaging components yielding the highest AUC (0.94). Replacing family history variables with imaging components yielded an improvement of classification performance of~4%, suggesting that imaging compensates the predictive information arising from family cancer structure. Conclusions: The L-PCR model uncovered evidence for the utility of MRI texture features in distinguishing between BRCA1/2 positive and negative high-risk breast cancer individuals, which may suggest value to diagnostic routine. Integration of computer-extracted texture analysis from MRI modalities in prediction models and inclusion criteria might play a role in reducing false positives or missed cases especially when established risk variables such as family history are missing.

Comparing Characteristics of Pelvic High-grade Serous Carcinomas with and without Breast Cancer Gene Variants on MR Imaging

“…Finally, this study used ROI analysis, but since ovarian cancer is a heterogeneous tumor and the ROIs were set visually, the influence of the ROI settings on the results cannot be denied. For qualitative classification of ovarian tumors, the usefulness of new quantitative parameters of MRI, such as perfusion, 25 , 26 DWI, 27 and texture analysis, 13 , 28 has been reported, and further validation including these parameters is required in the future.…”

A nomogram model combining ultrasound-based radiomics features and clinicopathological factors to identify germline BRCA1/2 mutation in invasive breast cancer patients

“…Previous studies mainly focused on radiomics features of breast MR, which were found to be associated with gene mutations, e.g., HER-2, TP53, PI3K, to different degrees [ [34] , [35] , [36] , [37] ]. Vasileiou and colleagues [ 38 ] utilized 41 breast MRI data to construct a radiomics model for predicting BRCA1/2 mutation and achieved an AUC of 0.865. However, the small sample size indicated inevitable overfitting and relatively low credibility.…”

Expression of the Immunohistochemical Markers CK5, CD117, and EGFR in Molecular Subtypes of Breast Cancer Correlated with Prognosis

“…A pCR after neoadjuvant chemotherapy is associated with a longer event-free survival (EFS)-the length of time after primary treatment the patient Diagnostics 2023, 13, 372 2 of 15 remains free of disease recurrence-and overall survival (OS) [6,7]. As breast cancer treatment becomes increasingly personalized, artificial intelligence can allow early prediction of pCR through Magnetic Resonance Imaging (MRI) [8], and a hierarchical clustering procedure which offers valuable additional information about data-driven individualized therapies [9,10].…”