Prediction of BRCA gene mutation status in epithelial ovarian cancer by radiomics models based on 2D and 3D CT images

Abstract

Background The objective of this study is to explore the value of two-dimensional (2D) and three-dimensional (3D) radiomics models based on enhanced computed tomography (CT) images in predicting BRCA gene mutations in patients with epithelial ovarian cancer. Methods The clinical and imaging data of 106 patients with ovarian cancer confirmed by surgery and pathology were retrospectively analyzed and genetic testing was performed. Radiomics features extracted from the 2D and 3D regions of interest of the patients’ primary tumor lesions were selected in the training set using the maximum correlation and minimum redundancy method. Then, the best features were selected through Lasso tenfold cross-validation. Feature subsets were employed to establish a radiomics model. The model’s performance was evaluated via area under the receiver operating characteristic curve analysis and its clinical validity was assessed by using the model’s decision curve. Results On the validation set, the area under the curve values of the 2D, 3D, and 2D + 3D combined models were 0.78 (0.61–0.96), 0.75 (0.55–0.92), and 0.82 (0.61–0.96), respectively. However, the DeLong test P values between the three pairs of models were all > 0.05. The decision curve analysis showed that the radiomics model had a high net benefit across all high-risk threshold probabilities. Conclusions The three radiomics models can predict the BRCA gene mutation in ovarian cancer, and there were no statistically significant differences between the prediction performance of the three models.

CT-Based Radiomics and Deep Learning for BRCA Mutation and Progression-Free Survival Prediction in Ovarian Cancer Using a Multicentric Dataset

“…Regarding BRCA, to the best of our knowledge, the only study that proposed a radiomic model with good performance (AUC = 0.82) in predicting BRCA status is that by Mingzhu et al [ 21 ]. They included different phases of post-contrast CTs in the analysis, enlarging the set of possibly correlated features.…”

“…Recently, some studies have investigated the radiomic approach in ovarian cancer, discovering a correlation with metastatic [ 13 ] and lymph node [ 14 ] involvement using regularized logistic regression models, residual tumor after surgery by means of Kaplan-Meier analysis [ 15 ], progression-free survival (PFS) using Cox proportional hazards and logistic regression models [ 15 , 16 , 17 , 18 , 19 ], overall survival (OS) [ 20 ], genetic mutations including BRCA [ 17 , 21 ] and proteomic profile [ 22 ] of the tumor. However, almost all these studies were performed in a single center, many had small datasets, and robust external validation of findings is still missing.…”

The Potential and Emerging Role of Quantitative Imaging Biomarkers for Cancer Characterization

“…Radiogenomic analyses have already been very successful in identifying various mutations [ 95 ]. Some examples of studies for the linking of radiomics and genetics are the detection of BRCA gene status in epithelial ovarian cancer [ 96 ], p53 and PD-L1 status in pancreatic cancer [ 97 ], the detection of p53 and IDH mutations in gliomas [ 98 , 99 ], the detection of EGFR status in brain metastases of lung adenocarcinoma [ 100 ], and KRAS status in rectal cancer [ 101 ]. Similar to radiogenomics, imaging-based deep learning and genetics have been linked, too.…”

Prognostic and predictive value of radiomics features at MRI in nasopharyngeal carcinoma

“…Radiomics features were extracted from tumors and normal masticatory muscles of 37 patients on the T2WI/FS and CE-T1W images, respectively. Based on the fact that the possible influence on the analysis of differential expression features caused by the separate radiomics features extraction on 3D tumor volume and on 2D masticatory muscle is acceptable [11,12]. We performed the Wilcoxon signed-rank test [13] with P < 0.01, on all but 28 shape-related features for the purpose to select features, respectively.…”