Abstract
BackgroundBRCA1/2 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.MethodsA 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.ResultsLasso-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.ConclusionsThe 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.
Highlights
BRCA1/2 deleterious variants account for most of the hereditary breast and ovarian cancer cases
Higher empirical probability (EP) for identifying BRCA1/2 pathogenic variants was calculated, when the family history including the index case consisted of: i) at least one breast and one ovarian cancer case (48.4%), ii) at least 3 breast cancer cases, with two of them manifesting before the age of 51 (30.7%) iii) bilateral/contralateral breast cancer by the index case with the first tumor diagnosed before the age of 51 (24.8%) iv) at least 3 breast cancer cases regardless of the age at diagnosis (22.4%) [2]
The contribution of BRCA1 (13 of 16) and BRCA2 (3 of 16) pathogenic variants in Hereditary breast and ovarian cancer (HBOC) cases in the current study was not significantly different with that reported in literature (BRCA1: 66% and BRCA2: 34%) [49, 50]
Summary
BRCA1/2 deleterious variants account for most of the hereditary breast and ovarian cancer cases. The assessment of genetic cancer risk and subsequently the selection for genetic screening in Germany is based on guidelines and selection criteria that evaluate the empirical probability (EP) for the identification of BRCA1/2 variants. This is calculated by taking into consideration primarily the family history of breast and ovarian cancer, the age at disease onset and the identification of bilateral/contralateral breast tumors, and should exceed 10% [2, 5]. A number of prediction models have been developed to assess the likelihood of a BRCA1/2 variant detection, mainly by taking into consideration the family cancer history of an affected individual [9,10,11]. Information about family structure is often limited and genetic screening inclusion criteria are subjected to the personal judgment of clinicians often leading to exclusion of many affected individuals with genetic predisposition from testing [12, 13]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have