Preoperative prediction of high-risk endometrial cancer by expert and non-expert transvaginal ultrasonography, magnetic resonance imaging, and endometrial histology

Diagnostic Accuracy of Transvaginal Ultrasound and Magnetic Resonance Imaging for the Detection of Myometrial Infiltration in Endometrial Cancer: A Systematic Review and Meta-Analysis

In endometrial cancer (EC), deep myometrial invasion (DMI) is a prognostic factor that can be evaluated by various imaging methods; however, the best method of choice is uncertain. We aimed to compare the diagnostic performance of two-dimensional transvaginal ultrasound (TVS) and magnetic resonance imaging (MRI) in the preoperative detection of DMI in patients with EC. Pubmed, Embase and Cochrane Library were systematically searched in May 2023. We included original articles that compared TVS to MRI on the same cohort of patients, with final histopathological confirmation of DMI as reference standard. Several subgroup analyses were performed. Eighteen studies comprising 1548 patients were included. Pooled sensitivity and specificity were 76.6% (95% confidence interval (CI), 70.9-81.4%) and 87.4% (95% CI, 80.6-92%) for TVS. The corresponding values for MRI were 81.1% (95% CI, 74.9-85.9%) and 83.8% (95% CI, 79.2-87.5%). No significant difference was observed (sensitivity: p = 0.116, specificity: p = 0.707). A non-significant difference between TVS and MRI was observed when no-myometrium infiltration vs. myometrium infiltration was considered. However, when only low-grade EC patients were evaluated, the specificity of MRI was significantly better (p = 0.044). Both TVS and MRI demonstrated comparable sensitivity and specificity. Further studies are needed to assess the presence of myometrium infiltration in patients with fertility-sparing wishes.

A Transvaginal Ultrasound-Based Deep Learning Model for the Noninvasive Diagnosis of Myometrial Invasion in Patients with Endometrial Cancer: Comparison with Radiologists

RATIONALE AND OBJECTIVES

This study aimed to determine the feasibility of using the deep learning (DL) method to determine the degree (whether myometrial invasion [MI] >50%) of MI in patients with endometrial cancer (EC) based on ultrasound (US) images.

MATERIALS AND METHODS

From September 2017 to April 2023, 1289 US images of 604 patients with EC who underwent surgical resection at center 1, center 2 or center 3 were obtained and divided into a training set and an internal validation set. Ninety-five patients from center 4 and center 5 were randomly selected as the external testing set according to the same criteria as those for the primary cohort. This study evaluated three DL models trained on the training set and tested them on the validation and testing sets. The models' performance was analyzed based on accuracy, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC), and the performance of the models was subsequently compared with that of 15 radiologists.

RESULTS

In the final clinical diagnosis of MI in patients with EC, EfficientNet-B6 showed the best performance in the testing set in terms of area under the curve (AUC) [0.814, 95% CI (0.746-0.882]; accuracy [0.802, 95% CI (0.733-0.855]; sensitivity [0.623]; specificity [0.879]; positive likelihood ratio (PLR) [6.750]; and negative likelihood ratio (NLR) [0.389]. The diagnostic efficacy of EfficientNet-B6 was significantly better than that of the 15 radiologists, with an average diagnostic accuracy of 0.681, average AUC of 0.678, AUC of the best performance of 0.739, accuracy of 0.716, sensitivity of 0.806, specificity 0.672, PLR2.457, and NLR 0.289.

CONCLUSION

Based on the preoperative US images of patients with EC, the DL model can accurately determine the degree of endometrial MI; the performance of this model is significantly better than that of radiologists, and it can effectively assist in clinical treatment decisions.

A prospective comparison of the diagnostic accuracies of ultrasound and magnetic resonance imaging in preoperative staging of endometrial cancer

OBJECTIVE

To compare the diagnostic accuracies of ultrasound and magnetic resonance imaging (MRI) for deep (≥50%) myometrial invasion (DMI) and cervical stromal invasion (CSI) in women with endometrial cancer.

METHODS

This was a prospective study at a gynecology clinic for women with postmenopausal bleeding. Between October 2015-October 2018, consecutive women with suspected endometrial cancer based on ultrasound subjective pattern recognition were simultaneously assessed for DMI and CSI on ultrasound. Subsequently, they also underwent preoperative MRI. We compared the diagnostic accuracies of ultrasound and MRI in predicting DMI and CSI with the final histology as the gold standard.

RESULTS

We included 51 women. The prevalence of DMI and CSI were 22/51 (43%) and 7/51 (14%), respectively. The majority of malignancies were of endometrioid histological subtype (38/51, 75%) and FIGO stage 1 or 2 (40/51, 78%). Ultrasound diagnosed more cases of DMI compared to MRI (19/22 vs. 17/22), however, the difference was not statistically significant. The sensitivities and specificities of ultrasound and MRI for DMI were 86% vs. 77% and 66% vs. 76%, respectively. For CSI, ultrasound and MRI correctly diagnosed the same number of cases (5/7, 71%); their respective false-positive rates were low, 0/44 (0%) and 1/44 (2%). Ultrasound and MRI had a moderate agreement for DMI (ƙ=0.49; 95% confidence interval [CI]=0.26-0.73), whereas the agreement for CSI was substantial (ƙ=0.69; 95% CI=0.36-1.00).

CONCLUSION

Endometrial cancer can be simultaneously diagnosed and staged at women's initial ultrasound assessment. The accuracies of ultrasound for DMI and CSI are comparable to MRI.

TRIAL REGISTRATION

ISRCTN Identifier: ISRCTN24363390.

Efficacy of transvaginal ultrasound versus magnetic resonance imaging for preoperative assessment of myometrial invasion in patients with endometrioid endometrial cancer: a prospective comparative study

Background

We compared the accuracy of preoperative transvaginal ultrasound (TVUS) versus magnetic resonance imaging (MRI) for the assessment of myometrial invasion (MI) in patients with endometrial cancer (EC), while definitive histopathological diagnosis served as a reference method.

Patients and methods

Study performed at a single tertiary centre from 2019 to 2021, included women with a histopathological proven EC, hospitalized for scheduled surgery. TVUS and MRI were performed prior to surgical staging for assessment MI, which was estimated using two objective TVUS methods (Gordon’s and Karlsson’s) and MRI. Patients were divided into two groups, after surgery and histopathological assessment of MI: superficial (≤ 50%) and deep (> 50%).

Results

Sixty patients were eligible for the study. According to the reference method, there were 34 (56.7%) cases in the study with MI < 50%, and 26 (43.3%) with MI > 50%. Both objective TVUS methods and MRI showed no statistical significant differences in overall diagnostic performance for the preoperative assessment of MI. The concordance coefficient between both TVUS methods, MRI and histopathology was statistically significant (p < 0.001). Gordon’s method calculating MI reached a positive predictive value (PPV) of 83%, negative predictive value (NPV) of 83%, 77% sensitivity, 88% specificity, and 83% overall accuracy. Karlsson’s method reached PPV of 82%, NPV of 79%, 69% sensitivity, 88% specificity, and 80% overall accuracy. Accordingly, MRI calculating MI reached PPV of 83%, NPV of 97%, 97% sensitivity, 85% specificity, and 90% overall accuracy.

Conclusions

We found that objective TVUS assessment of myometrial invasion was performed with a diagnostic accuracy comparable to that of MRI in women with endometrial cancer.