The value of MRI in management of endometrial hyperplasia with atypia

A comparative study of mono-exponential and advanced diffusion-weighted imaging in differentiating stage IA endometrial carcinoma from benign endometrial lesions

PURPOSE

The purpose of the current investigation is to compare the efficacy of different diffusion models and diffusion kurtosis imaging (DKI) in differentiating stage IA endometrial carcinoma (IAEC) from benign endometrial lesions (BELs).

METHODS

Patients with IAEC, endometrial hyperplasia (EH), or a thickened endometrium confirmed between May 2016 and August 2022 were retrospectively enrolled. All of the patients underwent a preoperative pelvic magnetic resonance imaging (MRI) examination. The apparent diffusion coefficient (ADC) from the mono-exponential model, pure diffusion coefficient (D), pseudo-diffusion coefficient (D*), perfusion fraction (f) from the bi-exponential model, distributed diffusion coefficient (DDC), water molecular diffusion heterogeneity index from the stretched-exponential model, diffusion coefficient (Dk) and diffusion kurtosis (K) from the DKI model were calculated. Receiver operating characteristic (ROC) analysis was used to evaluate the diagnostic efficiency.

RESULTS

A total of 90 patients with IAEC and 91 patients with BELs were enrolled. The values of ADC, D, DDC and Dk were significantly lower and D* and K were significantly higher in cases of IAEC (p < 0.05). Multivariate analysis showed that K was the only predictor. The area under the ROC curve of K was 0.864, significantly higher compared with the ADC (0.601), D (0.811), D* (0.638), DDC (0.743) and Dk (0.675). The sensitivity, specificity and accuracy of K were 78.89%, 85.71% and 80.66%, respectively.

CONCLUSION

Advanced diffusion-weighted imaging models have good performance for differentiating IAEC from EH and endometrial thickening. Among all of the diffusion parameters, K showed the best performance and was the only independent predictor. Diffusion kurtosis imaging was defined as the most valuable model in the current context.

US, MRI, CT Performance and Interpretation of Uterine Masses

Uterine masses are commonly encountered as incidental findings during cross-sectional imaging or when individuals present with symptoms such as pain and bleeding. The World Health Organization categorizes tumors of the uterine corpus into 5 distinct groups: endometrial epithelial tumors and their precursors, tumor-like growths, mesenchymal uterine tumors, tumors with a combination of epithelial and mesenchymal elements, and various other types of tumors. The primary imaging method for assessing uterine abnormalities is transvaginal ultrasound. However, magnetic resonance imaging (MRI) can be employed to enhance the visualization of soft tissues, enabling a more detailed characterization of uterine masses. This article aims to outline the imaging features of both benign and malignant uterine masses using ultrasound, MRI, and computed tomography.

Diagnostic value of the apparent diffusion coefficient in differentiating malignant from benign endometrial lesions

Introduction

Magnetic resonance imaging (MRI) with its innovative techniques, such as diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC), increases the diagnostic accuracy in distinguishing between malignant and benign lesions of the endometrium. The aim of the study was MRI differentiation between malignant and benign endometrial lesions and correlation with histopathological findings with a special emphasis on quantitative analysis. An additional aim was to correlate the ADC values and histological tumor grades.

Methods

The prospective study included 119 female patients with or without vaginal bleeding and pathological values of endometrial thickness, who underwent MRI examinations. According to MRI reports the patients were divided into 45 suspicious malignant and 74 suspicious benign endometrial lesions. The radiological diagnosis was compared to the histopathological evaluation, which confirmed 37 malignant lesions while the rest were benign.

Results

The mean ADC value for malignant lesions was 0.761 ± 0.13×10^-3 mm²/s and for benign lesions was 1.318 ± 0.20×10^-3 mm²/s. The ADC values for malignant lesions were expectedly lower than those of benign lesions (p<0.001). The ADC cut-off value was 1.007×10^-3 mm²/s with a sensitivity of 100%, specificity of 92.7%, a positive predictive value of 60.3%, and a negative predictive value of 100%. In comparison with the histopathological findings, the sensitivity of MRI was 100%, specificity 90.2%, positive predictive value was 82.2%, and negative predictive value was 100%. Observing the histological grades 1, 2, and 3 of endometrial carcinoma, no statistically significant differences of mean ADC values were found. The mean ADC values for histological tumor grades 1,2 and 3 were 0.803 ± 0.13×10^-3 mm²/s, 0.754 ± 0.12×10^-3 mm²/s and 0.728 ± 0.13×10^-3 mm²/s, respectively.

Conclusion

DWI and ADC values represent clinically useful tools for the differentiation between malignant and benign endometrial lesions with high sensitivity and good specificity, but the results failed to demonstrate their usefulness in differentiating histological grades of endometrial cancer.

Multimodal MRI-Based Radiomics-Clinical Model for Preoperatively Differentiating Concurrent Endometrial Carcinoma From Atypical Endometrial Hyperplasia

Objectives

To develop and validate a radiomics model based on multimodal MRI combining clinical information for preoperative distinguishing concurrent endometrial carcinoma (CEC) from atypical endometrial hyperplasia (AEH).

Materials and Methods

A total of 122 patients (78 AEH and 44 CEC) who underwent preoperative MRI were enrolled in this retrospective study. Radiomics features were extracted based on T2-weighted imaging (T2WI), diffusion-weighted imaging (DWI), and apparent diffusion coefficient (ADC) maps. After feature reduction by minimum redundancy maximum relevance and least absolute shrinkage and selection operator algorithm, single-modal and multimodal radiomics signatures, clinical model, and radiomics-clinical model were constructed using logistic regression. Receiver operating characteristic (ROC) analysis, calibration curves, and decision curve analysis were used to assess the models.

Results

The combined radiomics signature of T2WI, DWI, and ADC maps showed better discrimination ability than either alone. The radiomics-clinical model consisting of multimodal radiomics features, endometrial thickness >11mm, and nulliparity status achieved the highest area under the ROC curve (AUC) of 0.932 (95% confidential interval [CI]: 0.880-0.984), bootstrap corrected AUC of 0.922 in the training set, and AUC of 0.942 (95% CI: 0.852-1.000) in the validation set. Subgroup analysis further revealed that this model performed well for patients with preoperative endometrial biopsy consistent and inconsistent with postoperative pathologic data (consistent group, F1-score = 0.865; inconsistent group, F1-score = 0.900).

Conclusions

The radiomics model, which incorporates multimodal MRI and clinical information, might be used to preoperatively differentiate CEC from AEH, especially for patients with under- or over-estimated preoperative endometrial biopsy.

Evaluation and Monitoring of Endometrial Cancer Based on Magnetic Resonance Imaging Features of Deep Learning

This study was aimed to compare and analyze the magnetic resonance imaging (MRI) manifestations and surgical pathological results of endometrial cancer (EC) and to explore the clinical research of MRI in the diagnosis and staging of EC. Methods. 80 patients with EC admitted to the hospital were selected as the research objects. The ResNet network was used to optimize the network. When the depth was added, the accuracy of the model was improved, the network parameters were iteratively updated, and the damage function of the minimized network was obtained. The recognition efficiency of MRI images was analyzed using three network modes: shallow CNN network, Res-Net network, and optimized network. The images of EC patients were analyzed, and a quantitative and timed MRI was achieved using simulated datasets in deep learning neural networks, which provided the basis for the formulation of single-scan MRI parameters. All patients underwent preoperative MRI examination using coronal and sagittal T1WI and T2WI imaging. The results showed that the accuracy and specificity of T2 weighted imaging and enhanced scanning in MRI were 88.75% and 95%, respectively. Sensitivity was 87.5%, negative predictive value was 93.75%, and positive predictive value was 86.25%. By MRI examination, 80 cases of EC in patients with stage I diagnosis were 72 cases, accounting for 90%, with endometrial thickening and uneven enhancement. In conclusion, the MRI manifestations of EC are diversified, and MRI has a high value for the staging of EC. MRI examination is conducive to improving diagnostic accuracy.

Risk of More Advanced Lesions at Hysterectomy after Initial Diagnosis of Non-Atypical Endometrial Hyperplasia in Patients with Postmenopausal Bleeding and Oral Anticoagulant Treatment

Background and Objectives: Endometrial hyperplasia (EH) is a precursor lesion to endometrial cancer (EC), and when cellular atypia is present, in 40% of cases, they are diagnosed with EC on hysterectomy. Usually, EH is clinically manifested by uterine bleeding. In patients with oral anticoagulant therapy (OAT), the uterus is the second most common source of bleeding. The aim of the study was to show that uterine bleeding in postmenopausal patients undergoing OAT may reveal precancerous endometrial lesions with atypia, or neoplastic lesions in patients with an initial diagnosis of endometrial hyperplasia without atypia (non-atypical endometrial hyperplasia, NAEH) on dilation and curettage (D&C). We will be able to estimate the risk of a postmenopausal female patient with uterine bleeding during an OAT to have a precancerous endometrial lesion. Materials and Methods: The subjects of the study were 173 female patients with uterine bleeding, who have had total hysterectomy with bilateral salpingoovarectomy, of whom 99 underwent an OAT. There were 101 female patients initially diagnosed with NAEH, of which 60 did not have anticoagulant treatment (mean age 57.36 ± 6.51) and 41 had anticoagulant treatment (mean age 60.39 ± 7.35) (p = 0.006). From the pathology diagnosis moment, the surgery was performed at 42.09 ± 14.54 days in patients without OAT and after 35.39 ± 11.29 days in those who received such treatment (p = 0.724). Results: Initial diagnosis of NAEH established at D&C was changed at the final diagnosis after hysterectomy in EH with cellular atypia (atypical endometrial hyperplasia AEH) or EC in 18.18% of patients without OAT, and in 40.54% of patients who received this treatment. Conclusions: Based on a logistic regression model, it is estimated that female patients with an initial histopathological diagnosis of NAEH and who underwent OAT have, on average, 4.85 times greater odds (OR = 4.85, 95% CI 1.79–14.06) than the others of being identified postoperatively with more advanced lesions.

Predictors of endometrial carcinoma in patients with atypical endometrial hyperplasia at a tertiary gynaecological cancer centre in Western Australia

AIM

Our objective was to assess clinical and pathological factors associated with a final diagnosis of endometrial carcinoma in patients with atypical endometrial hyperplasia with a particular emphasis on the grading of atypia.

MATERIALS AND METHODS

A retrospective review over five years on patients (N = 97) who underwent hysterectomy for a diagnosis of atypical endometrial hyperplasia at a statewide public tertiary gynaecologic oncology centre. Clinical and pathological characteristics were obtained.

RESULTS

The rate of concurrent endometrial carcinoma was 34% (n = 33) with most being stage 1A endometrioid. A significant group difference was reported for age at diagnosis (t = -2.20 P = 0.031 d = 0.43) with carcinoma patients on average older (M_age  = 60.2 (8.9) years) than patients without carcinoma (M_age  = 55.5 (12.3) years). No significant group differences were found for body mass index, endometrial thickness or time between diagnosis and treatment. Significantly higher rates of carcinoma were reported in patients with moderate atypical hyperplasia (27.6%) and severe atypical hyperplasia (66.7%), compared to mild atypical hyperplasia (7.1%). Only severe atypical hyperplasia (odds ratio (OR) = 21.5, 95% CI 2.8-163.1, P = 0.003) and postmenopausal status (OR = 13.2, 95% CI 1.3-139.0, P = 0.032) significantly increased the risk of carcinoma in a multivariate model.

CONCLUSION

Severe atypical hyperplasia and postmenopausal status were significant predictors of concurrent endometrial carcinoma in patients with atypical endometrial hyperplasia. The grading of atypical hyperplasia may be utilised by gynaecologic oncologists in the triage and referral process of managing these patients; however, the grading system requires external validation in larger prospective studies.