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

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.

Apparent diffusion coefficient map-based radiomics model for identifying the ischemic penumbra in acute ischemic stroke / 中华放射学杂志

Objective:To investigate the value of ADC map-based radiomics model for identifying the ischemic penumbra (IP) in acute ischemic stroke (AIS).Methods:From January 2014 to October 2019, data of 241 patients with AIS involving the anterior cerebral circulation within 24 h after stroke onset in the First People′s Hospital of Nantong City was analyzed retrospectively. All patients received routine T 1WI, T 2WI, DWI and dynamic susceptibility contrast-perfusion weighted imaging (DSC-PWI). Considering the PWI-DWI mismatch model as the gold standard for determining IP, patients were divided into the PWI-DWI mismatch (84 cases) and PWI-DWI non-mismatch (157 cases) groups. The ROI of the low signal area and the surrounding area was drawn by two doctors at the maximum level of the lesions on the ADC maps. Then the images were imported into AK analysis software to extract the features. Firstly, the inter-class correlation coefficient was used to screen out the features with high consistency, then the maximum relevance and minimum redundancy (mRMR) and least absolute shrinkage and selection operator (Lasso) regression analysis were used to screen the features. The selected features were used to construct their own radiomics model. ROC curve was used to evaluate the performance of the models, and Delong test was used to compare the area under the curve (AUC) of the two models. Results:After screening, 12 features (LongRunLowGreyLevelEmphasis_angle135_offset7, LongRunLowGreyLevelEmphasis_AllDirection_offset7, GLCMEntropy_AllDirection_offset4_SD, GLCMEnergy_angle45_offset1, ColGE_W11B25_16, ColGE_W11B25_24, HaraEntropy, SurfaceVolumeRatio, Sphericity, Quantile0.025, uniformity and Percentile75) were used to construct the radiomics model based on the low signal area of the ADC map. The area under the ROC curve in the training set was 0.900, and the sensitivity, specificity and accuracy were 84.5%, 81.4% and 83.4%, respectively. The area under the ROC curve in the validation set was 0.870, and the sensitivity, specificity and accuracy were 80.9%, 84.0% and 81.9%, respectively. Eleven features(RunLengthNonuniformity_AllDirection_offset1_SD, ShortRunLowGreyLevelEmphasis_angle45_offset1, HighGreyLevelRunEmphasis_AllDirection_offset1_SD, ShortRunLowGreyLevelEmphasis_AllDirection_offset7, HaralickCorrelation_AllDirection_offset4_SD, ClusterShade_angle45_offset7, InverseDifferenceMoment_AllDirection_offset7_SD, ColGE_W3B20_0, sumAverage, SurfaceVolumeRatio and VolumeMM) were used to construct the radiomics model based on the surrounding area of ADC map. The area under ROC curve in training set was 0.820, the sensitivity, specificity and accuracy were 80.5%, 80.2% and 80.4%, respectively; the area under ROC curve in validation set was 0.800, the sensitivity, specificity and accuracy were 78.7%, 80.0% and 79.2%, respectively. The AUC of the radiomics model based on the low signal area of the ADC map was larger than that based on the surrounding area of the ADC map (training set: Z=3.017, P=0.003; validation set: Z=0.604, P=0.002). Conclusion:The radiomics model based on ADC map has a good diagnostic efficacyin identifying the IP.

Predictive Value of the Texture Analysis of Enhanced Computed Tomographic Images for Preoperative Pancreatic Carcinoma Differentiation.

PURPOSE: To assess the utility of texture analysis for predicting the pathological degree of differentiation of pancreatic carcinoma (PC). METHODS: Eighty-three patients with PC who went through postoperative pathology diagnose and CT examination were selected at Anhui Provincial Hospital. Among them, 34 cases were moderately differentiated, 13 cases were poorly differentiated, and 36 cases were moderately poorly differentiated. The images in the arterial and venous phase (VP) with the lesions at their largest cross section were selected to manually outline the region of interest (ROI) to delineate lesions using open-source software. A total of 396 features were extracted from the ROI using AK software. Spearman correlation analysis and random forest selection by filter (rfSBF) in the caret package of R studio were used to select the discriminating features. The receiver operating characteristic ROC analysis was used to evaluate their discriminative performance. RESULTS: Twelve and six features were selected in the arterial and VPs, respectively. The areas under the ROC curve (AUC) in the arterial phase (AP) for diagnosing poorly differentiated, moderately differentiated and moderate-poorly differentiated cases were 0.80, 1, and 0.80 in the training group and 0.77, 1, and 0.77 in the test group; in the VP, the values were 0.81, 1, and 0.82 in the training group and 0.74, 1, and 0.74 in the test group. CONCLUSION: Texture analysis based on contrast-enhanced CT images can be used as an adjunct for the preoperative assessment of the pathological degrees of differentiation of PC.