Incidental Ovarian and Uterine Findings on Cross-sectional Imaging

A CT-based radiomics nomogram for differentiating ovarian cystadenomas and endometriotic cysts

AIM

To construct and validate a computed tomography (CT)-based radiomics nomogram integrating radiomics signature and clinical factors to distinguish ovarian cystadenomas and endometriotic cysts.

MATERIALS AND METHODS

A total of 287 patients with ovarian cystadenomas (n=196) or endometriotic cysts (n=91) were divided randomly into a training cohort (n=200) and a validation cohort (n=87). Radiomics features based on the portal venous phase of CT images were extracted by PyRadiomics. The least absolute shrinkage and selection operation regression was applied to select the significant features and develop the radiomics signature. A radiomics score (rad-score) was calculated. The clinical model was built by the significant clinical factors. Multivariate logistic regression analysis was employed to construct the radiomics nomogram based on significant clinical factors and rad-score. The diagnostic performances of the radiomics nomogram, radiomics signature, and clinical model were evaluated and compared in the training and validation cohorts. Diagnostic confusion matrices of these models were calculated for the validation cohort and compared with those of the radiologists.

RESULTS

Seventeen radiomics features from CT images were used to build the radiomics signature. The radiomics nomogram incorporating cancer antigen 125 (CA-125) level and rad-score showed the best performance in both the training and validation cohorts with AUCs of 0.925 (95% confidence interval [CI]: 0.885-0.965), and 0.942 (95% CI: 0.891-0.993), respectively. The accuracy of radiomics nomogram in the confusion matrix outperformed the radiologists.

CONCLUSIONS

The radiomics nomogram performed well for differentiating ovarian cystadenomas and endometriotic cysts, and may help in clinical decision-making process.

Spectrum of Ovarian Incidentalomas: Diagnosis and Management

Incidental ovarian lesions are asymptomatic lesions that are accidentally discovered during a CT or MRI examinations that involves the pelvic cavity or during a routine obstetric ultrasound study. Incidental ovarian masses are usually benign with a very low risk of malignancy yet underlying malignant pathology may be discovered during the diagnostic work-up of these lesions. Suspicion of malignancy is directly correlating with the increase in the patient's age, the increase in the size of the lesion, the presence of the solid components or thick septa and a high color scale of the ovarian mass. Following standard reporting and management protocols are essential to choose the proper work-up of these lesions to avoid unnecessary additional imaging and operative intervention. In this article, we will provide a review of the characteristic imaging features of some incidental and yet commonly encountered ovarian lesions. We will also summarize the recently published algorithms that are important for consistent reporting and standard management of these lesions.