Application Values of 2D and 3D Radiomics Models Based on CT Plain Scan in Differentiating Benign from Malignant Ovarian Tumors

Abstract

Background: Accurate identification of ovarian tumors as benign or malignant is highly crucial. Radiomics is a new branch of imaging that has emerged in recent years to replace the traditional naked eye qualitative diagnosis.

Objective: This study is aimed at exploring the difference in the application potential of two- (2D) and three-dimensional (3D) radiomics models based on CT plain scan in differentiating benign from malignant ovarian tumors.

Method: A retrospective analysis was performed on 140 patients with ovarian tumors confirmed by surgery and pathology in our hospital from July 2017 to August 2020. These 140 patients were divided into benign group and malignant group according to the pathological results. The ITK-SNAP software was used to outline the regions-of-interest (ROI) of 2D or 3D tumors on the CT plain scan image of each patient; the texture features were extracted through analysis kit (AK), and the cases were randomly divided into training groups (n = 99) and validation group (n = 41) in a ratio of 7 : 3. The least absolute shrinkage and selection operator (LASSO) algorithm was used to perform dimensionality reduction, followed by the construction of the radiomics nomogram model using the logistic regression method. The receiver operating characteristic (ROC) curve was drawn, and the calibration curve and decision curve analysis (DCA) were used to evaluate and verify the results of the radiomics nomogram and compare the differences between 2D and 3D diagnostic performance.

Results: There were 396 quantitative radiomics feature parameters extracted from 2D group and the 3D group, respectively. The area under the curve (AUC) of the radiomics nomogram of the 2D training group and the validation group were 0.96 and 0.97, respectively. The accuracy, specificity, and sensitivity of the training set were 92.9%, 88.9%, and 96.3%, respectively, and those of the validation set were 90.2%, 82.6%, and 100.0%, respectively. The AUCs of the radiomics nomogram of the 3D training group and validation group were 0.96% and 0.99%, respectively. The accuracy, sensitivity, and specificity of the training set were 92.9%, 96.3%, and 88.9%, respectively, and those of the validation set were 97.6%, 95.7%, and 100.0%, respectively. DeLong's test indicated that there was no statistical significance between the two sets (P > 0.05).

Conclusions: For the differential diagnosis of benign and malignant ovarian tumors, the 2D and 3D radiomics nomogram models exhibited comparable diagnostic performance. Considering that the 2D model was cost-effective and time-efficient, it was more recommended to use 2D features in future research.

Figure 1

(a) Manual outline of the maximum diameter level of ovarian lesions. (b) Manual outline of the full-level ovarian lesions.

Figure 2

(a) ROC of 2D clinical, radiomics, and nomogram models to differentiate benign from malignant ovarian tumors. (b) ROC of 3D clinical, radiomics, and nomogram models to differentiate benign from malignant ovarian tumors. (c) AUC of 2D and 3D nomogram models to differentiate benign from malignant ovarian tumors (P < 0.05).

Figure 3

The feature selection process, selected radiomic features, and corresponding coefficients of radiomics model: (a) 2D model and (b) 3D model.

Figure 4

Radiomics nomogram ((a) 2D model and (b) 3D model).

Figure 5

DCA of (a) 2D and (b) 3D radiomics models and clinicopathological features (green, blue, and dark red lines correspond to clinical, radiomics, and nomogram model, respectively). Light gray lines show that all radiomics models, and clinicopathological features were related to hypotheses related to malignant ovarian tumors. Additionally, the dark red lines show that all radiomics models and clinicopathological features were related to hypotheses not related to malignant ovarian tumors.