Article Text
PDF
Abstract
Introduction/Background Current indications for BRCA 1/2 testing based on a priori BRCA probability thresholds are ineffective as most of the carriers remain undiagnosed. Data regarding the cost-effectiveness of a population-based BRCA mutation screening are still controversial. Radiomics is an emerging tool for large scale quantitative analysis of features from standard diagnostic imaging and has been applied also to identify gene mutational status.
Our group already showed the feasibility of performing a radiomic analysis of US images of normal ovaries to predict germline BRCA 1/2 genes status. Models performances on the testing set were reasonably encouraging.
Moreover, we performed a cost-effective analysis showing that combining clinical criteria with the radiogenomic model would have a massive effect after only one generation in detecting carriers in the general population with only a small cost increment. The present study aims at improving the preprocessing pipeline on a larger internal dataset and at cross-validating the predictive model on US images acquired prospectively in an observational multicenter study (NCT05769517).
PROBE II
Methodology We will conduct a multicenter observational study involving 14 international centers. The study is composed of:
- A retrospective phase aimed at defining and implementing a proper and fine-tuned image preprocessing pipeline on the existing dataset and enlarging dataset size (at least 300 patients) with new real images and apply data augmentation techniques, deep neural network models combined with the aforementioned handcrafted imaging features from radiomics analysis.
- A prospective phase aimed at further cross-validating the predictive model on US images acquired prospectively in an observational multicenter study. 1.000 patients are expected to be enrolled.
Results Results are expected by the end of 2026.
Conclusion If validated as a reliable model, the integration of this radiogenomic model with current clinical/familiar criteria could represent an innovative, cost-effective approach towards ovarian cancer prevention across generations.
Disclosures The authors declare no disclosures.