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.

Artificial intelligence performance in image-based ovarian cancer identification: A systematic review and meta-analysis

“… Incomplete ultrasound, MRI, or pathological data; combined with severe organic diseases, such as coagulation dysfunction, renal insufficiency, heart failure, and other surgical contraindications; history of ovarian surgery; combined with other pelvic diseases, such as endometrial cancer and rectal cancer. 207 NR Li et al, 34 2022 a Patients with ovarian tumor confirmed by histopathology; no history of malignant tumors other than ovarian tumor; patients who were undergoing pelvic CT examination within half a month before surgery. Those who had received radiotherapy, chemotherapy, or radiotherapy–chemotherapy before CT examination; patients diagnosed with inflammatory diseases; patients with low image quality.…”

“… 3663/100 2015.01–2020.12 No Guo et al, 33 2022 a Retrospective study, data from Qilu Hospital. 138/69 2018.04–2021.04 No Li et al, 34 2022 a Retrospective study, data from the First Affiliated Hospital of Nanchang Medical College. 99/41 2017–2020 No Wang et al, 35 2021 a Retrospective study, data from Tianjin Medical University Cancer Institute and Hospital.…”

Non-Invasive Prediction of Survival Time of Midline Glioma Patients Using Machine Learning on Multiparametric MRI Radiomics Features

“…All images were saved as Digital Imaging and Communications in Medicine (DICOM) and imported into the ITK-SNAP software (version 3.8.0, http://www.itksnap.org ) for segmentation. Some studies have shown that one slice (2D) with the largest cross-section of the tumor and the entire tumor volume (3D) for segmentation has comparable diagnostic performance, and there are also some studies that use one slice for tumor segmentation ( 17 – 20 ). So, in this study, the regions of interest (ROIs) were manually segmented ( Figure 2 ) on the axial slice with the largest cross-section of the tumors on T2w, T2 FLAIR, and T1c images by two authors (S Wu and P He, with 4 and 6 years of diagnostic experience in neuroradiology, respectively) who were blinded to histological results.…”

Computed Tomographic Radiomics in Differentiating Histologic Subtypes of Epithelial Ovarian Carcinoma

“…32 In recent years, a number of CT radiomics studies were conducted to predict the clinicopathological characteristics of ovarian tumors, including discriminating malignant from borderline or benign ovarian masses, differentiating primary and secondary EOC, as well as predicting nodal or abdominopelvic metastases in ovarian cancer. [33][34][35][36][37] Histologic subtype is an important tumor characteristic that affects clinical management of EOC. Excellent performance of CT radiomics was found in our multicenter study.…”