[Borderline Ovarian Tumours: CNGOF Guidelines for Clinical Practice - Imaging]

Comparison of ultrasound-based ADNEX model with magnetic resonance imaging for discriminating adnexal masses: a multi-center study

Objectives

The ADNEX model offered a good diagnostic performance for discriminating adnexal tumors, but research comparing the abilities of the ADNEX model and MRI for characterizing adnexal tumors has not been reported to our knowledge. The aim of this study was to evaluate the diagnostic accuracy of the ultrasound-based ADNEX (Assessment of Different NEoplasias in the adneXa) model in comparison with that of magnetic resonance imaging (MRI) for differentiating benign, borderline and malignant adnexal masses.

Methods

This prospective study included 529 women with adnexal masses who underwent assessment via the ADNEX model and subjective MRI analysis before surgical treatment between October 2019 and April 2022 at two hospitals. Postoperative histological diagnosis was considered the gold standard.

Results

Among the 529 women, 92 (17.4%) masses were diagnosed histologically as malignant tumors, 67 (12.7%) as borderline tumors, and 370 (69.9%) as benign tumors. For the diagnosis of malignancy, including borderline tumors, overall agreement between the ADNEX model and MRI pre-operation was 84.9%. The sensitivity of the ADNEX model of 0.91 (95% confidence interval [CI]: 0.85-0.95) was similar to that of MRI (0.89, 95% CI: 0.84-0.94; P=0.717). However, the ADNEX model had a higher specificity (0.90, 95% CI: 0.87-0.93) than MRI (0.81, 95% CI: 0.77-0.85; P=0.001). The greatest sensitivity (0.96, 95% CI: 0.92-0.99) and specificity (0.94, 95% CI: 0.91-0.96) were achieved by combining the ADNEX model and subjective MRI assessment. While the total diagnostic accuracy did not differ significantly between the two methods (P=0.059), the ADNEX model showed greater diagnostic accuracy for borderline tumors (P<0.001).

Conclusion

The ultrasound-based ADNEX model demonstrated excellent diagnostic performance for adnexal tumors, especially borderline tumors, compared with MRI. Accordingly, we recommend that the ADNEX model, alone or with subjective MRI assessment, should be used for pre-operative assessment of adnexal masses.

The challenging management of borderline ovarian tumors (BOTs) in women of childbearing age

Borderline ovarian tumors (BOTs) account for approximately 15% of all epithelial ovarian cancers. In 80% of cases the diagnosis of BOTs is done at stage I and more than a third of BOTs occurs in women younger than 40 years of age wishing to preserve their childbearing potential; the issue of conservative surgical management (fertility-sparing treatment) is thus becoming of paramount importance. At early stages, the modalities of conservative treatment could range from mono-lateral cystectomy to bilateral salpingo-oophorectomy. Although cystectomy is the preferred method to promote fertility it can lead to an elevated risk of recurrence; therefore, an appropriate counseling about the risk of relapse is mandatory before opting for this treatment. Nevertheless, relapses are often benign and can be treated by repeated conservative surgery. Besides the stage of the disease, histological subtype is another essential factor when considering the proper procedure: as most mucinous BOTs (mBOTs) are more commonly unilateral, the risk of an invasive recurrence seems to be higher, compared to serous histotype, therefore unilateral salpingo-oophorectomy is recommended. In the appraisal of current literature, this review aims to gain better insight on the current recommendations to identify the right balance between an accurate staging and an optimal fertility outcome.

MRI-Based Multiple Instance Convolutional Neural Network for Increased Accuracy in the Differentiation of Borderline and Malignant Epithelial Ovarian Tumors

BACKGROUND

Preoperative differentiation of borderline from malignant epithelial ovarian tumors (BEOT vs. MEOT) is challenging and can significantly impact surgical management.

PURPOSE

To develop a multiple instance convolutional neural network (MICNN) that can differentiate BEOT from MEOT, and to compare its diagnostic performance with that of radiologists.

STUDY TYPE

Retrospective study of eight clinical centers.

SUBJECTS

Between January 2010 and June 2018, a total of 501 women (mean age, 48.93 ± 14.05 years) with histopathologically confirmed BEOT (N = 165) or MEOT (N = 336) were divided into the training (N = 342) and validation cohorts (N = 159).

FIELD STRENGTH/SEQUENCE

Three axial sequences from 1.5 or 3 T scanner were used: fast spin echo T2-weighted imaging with fat saturation (T2WI FS), echo planar diffusion-weighted imaging, and 2D volumetric interpolated breath-hold examination of contrast-enhanced T1-weighted imaging (CE-T1WI) with FS.

ASSESSMENT

Three monoparametric MICNN models were built based on T2WI FS, apparent diffusion coefficient map, and CE-T1WI. Based on these monoparametric models, we constructed an early multiparametric (EMP) model and a late multiparametric (LMP) model using early and late information fusion methods, respectively. The diagnostic performance of the models was evaluated using the receiver operating characteristic (ROC) curve and compared to the performance of six radiologists with varying levels of experience.

STATISTICAL TESTS

We used DeLong test, chi-square test, Mann-Whitney U-test, and t-test, with significance level of 0.05.

RESULTS

Both EMP and LMP models differentiated BEOT from MEOT, with an area under the ROC curve (AUC) of 0.855 (95% CI, 0.795-0.915) and 0.884 (95% CI, 0.831-0.938), respectively. The AUC of the LMP model was significantly higher than the radiologists' pooled AUC (0.884 vs. 0.797).

DATA CONCLUSION

The developed MICNN models can effectively differentiate BEOT from MEOT and the diagnostic performances (AUCs) were more superior than that of the radiologists' assessments.

LEVEL OF EVIDENCE

3 TECHNICAL EFFICACY STAGE: 2.

Validation of IOTA-ADNEX Model in Discriminating Characteristics of Adnexal Masses: A Comparison with Subjective Assessment

(1) Background: The aim of this study is to compare the IOTA-ADNEX (international ovarian tumor analysis–assessment of different neoplasias in the adnexa) model with gynecologic experts in differentiating ovarian diseases. (2) Methods: All participants in this prospective study underwent ultrasonography (US) equipped with the IOTA-ADNEX^TM model and subjective assessment by a sonographic expert. Receiver operating characteristic (ROC) curves were also generated to compare overall accuracies. The optimal cut-off value of the ADNEX model for excluding benign diseases was calculated. (3) Results: Fifty-nine participants were eligible: 54 and 5 underwent surgery and follow-up computed tomography (CT), respectively. Benign and malignant diseases were confirmed in 49 (83.1%) and 10 (16.9%) participants, respectively. The specificity of the ADNEX model was 0.816 (95% confidence interval (CI): 0.680–0.912) in all participants and 0.795 (95% CI, 0.647–0.902) in the surgical group. The area under the ROC curve of the ADNEX model (0.924) was not significantly different from that of subjective assessment (0.953 in all participants, 0.951 in the surgical group; p = 0.391 in all participants, p = 0.407 in the surgical group). The optimal cut-off point using the ADNEX model was 47.3%, with a specificity of 0.977 (95% CI: 0.880–0.999). (4) Conclusions: The IOTA-ADNEX model is equal to gynecologic US experts in excluding benign ovarian tumors. Subsequently, being familiar with this US software may help gynecologic beginners to reduce unnecessary surgery.