Abnormal Uterine Bleeding: Current Classification and Clinical Management

Development of MRI-based radiomics predictive model for classifying endometrial lesions

An unbiased and accurate diagnosis of benign and malignant endometrial lesions is essential for the gynecologist, as each type might require distinct treatment. Radiomics is a quantitative method that could facilitate deep mining of information and quantification of the heterogeneity in images, thereby aiding clinicians in proper lesion diagnosis. The aim of this study is to develop an appropriate predictive model for the classification of benign and malignant endometrial lesions, and evaluate potential clinical applicability of the model. 139 patients with pathologically-confirmed endometrial lesions from January 2018 to July 2020 in two independent centers (center A and B) were finally analyzed. Center A was used for training set, while center B was used for test set. The lesions were manually drawn on the largest slice based on the lesion area by two radiologists. After feature extraction and feature selection, the possible associations between radiomics features and clinical parameters were assessed by Uni- and multi- variable logistic regression. The receiver operator characteristic (ROC) curve and DeLong validation were employed to evaluate the possible predictive performance of the models. Decision curve analysis (DCA) was used to evaluate the net benefit of the radiomics nomogram. A radiomics prediction model was established from the 15 selected features, and were found to be relatively high discriminative on the basis of the area under the ROC curve (AUC) for both the training and the test cohorts (AUC = 0.90 and 0.85, respectively). The radiomics nomogram also showed good performance of discrimination for both the training and test cohorts (AUC = 0.91 and 0.86, respectively), and the DeLong test shows that AUCs were significantly different between clinical parameters and nomogram. The result of DCA demonstrated the clinical usefulness of this novel nomogram method. The predictive model constructed based on MRI radiomics and clinical parameters indicated a highly diagnostic efficiency, thereby implying its potential clinical usefulness for the precise identification and prediction of endometrial lesions.

Whole-lesion apparent diffusion coefficient (ADC) histogram as a quantitative biomarker to preoperatively differentiate stage IA endometrial carcinoma from benign endometrial lesions

BACKGROUND

To assess the value of whole-lesion apparent diffusion coefficient (ADC) histogram analysis in differentiating stage IA endometrial carcinoma (EC) from benign endometrial lesions (BELs) and characterizing histopathologic features of stage IA EC preoperatively.

METHODS

One hundred and six BEL and 126 stage IA EC patients were retrospectively enrolled. Eighteen volumetric histogram parameters were extracted from the ADC map of each lesion. The Mann-Whitney U or Student's t-test was used to compare the differences between the two groups. Models based on clinical parameters and histogram features were established using multivariate logistic regression. Receiver operating characteristic (ROC) analysis and calibration curves were used to assess the models.

RESULTS

Stage IA EC showed lower ADC_10th, ADC_90th, ADC_min, ADC_max, ADC_mean, ADC_median, interquartile range, mean absolute deviation, robust mean absolute deviation (rMAD), root mean squared, energy, total energy, entropy, variance, and higher skewness, kurtosis and uniformity than BELs (all p < 0.05). ADC_median yielded the highest area under the ROC curve (AUC) of 0.928 (95% confidence interval [CI] 0.895-0.960; cut-off value = 1.161 × 10^-3 mm²/s) for differentiating stage IA EC from BELs. Moreover, multivariate analysis demonstrated that ADC-score (ADC_10th + skewness + rMAD + total energy) was the only significant independent predictor (OR = 2.641, 95% CI 2.045-3.411; p < 0.001) for stage IA EC when considering clinical parameters. This ADC histogram model (ADC-score) achieved an AUC of 0.941 and a bias-corrected AUC of 0.937 after bootstrap resampling. The model performed well for both premenopausal (accuracy = 0.871) and postmenopausal (accuracy = 0.905) patients. Besides, ADC_min and ADC_10th were significantly lower in Grade 3 than in Grade 1/2 stage IA EC (p = 0.022 and 0.047). At the same time, no correlation was found between ADC histogram parameters and the expression of Ki-67 in stage IA EC (all p > 0.05).

CONCLUSIONS

Whole-lesion ADC histogram analysis could serve as an imaging biomarker for differentiating stage IA EC from BELs and assisting in tumor grading of stage IA EC, thus facilitating personalized clinical management for premenopausal and postmenopausal patients.

Subclinical Hypothyroidism in Perimenopausal Abnormal Uterine Bleeding Patients

Background 

Abnormal uterine bleeding (AUB) can be very troublesome and is common in women with thyroid dysfunction. The current study aimed to assess the incidence of subclinical hypothyroidism in women with perimenopausal AUB.

Methodology 

A cross-sectional study was conducted at Hayatabad Medical Complex (HMC), Peshawar, Pakistan, between September 2020 to February 2021. All outdoor female patients with complications in the obstetrics and gynecology department, aged between 40 to 55 years of age, and no obvious cervical and genital lesions were included in the study. Patients with a history of suspected inflammatory disease, use of oral contraceptives, and malignant lesions of the cervix were excluded from the study. All cases were evaluated for AUB and their thyroid profile was evaluated. Data regarding menstrual irregularities were recorded in a pre-defined proforma and clinical examination was performed.

Results

A total of 500 women were enrolled with a mean age of 47.2 ± 7.3 years. Of these, 234 (46.8%) women were overweight and the mean levels of the thyroid-stimulating hormone were 4.4 ± 2.5 mIU/L. The mean triiodothyronine and thyroxine were 3.2 ± 1.9 and 1.5 ± 0.7 pmol/L, respectively. The rate of subclinical hypothyroidism was 33%. It was shown that the body mass index was significantly correlated with subclinical hypothyroidism (p=0.03). Furthermore, the rate of oligomenorrhea was significantly higher in patients with subclinical hypothyroidism (p=0.05).

Conclusion 

This study highlights the association between thyroid dysfunction in women with menstrual disorders. Screening and surveillance of thyroid-related abnormalities are warranted in patients with menstrual irregularities to avoid complications of the disease.

Hysteroscopic endometrial resection vs. hysterectomy for abnormal uterine bleeding: impact on quality of life and sexuality. Evidence from a systematic review of randomized controlled trials

PURPOSE OF REVIEW

The aim of this systematic review is to summarize the current evidence regarding the effectiveness of hysterectomy and hysteroscopic endometrial resection in improving quality of life (QoL), sexual function and psychological wellbeing of women abnormal uterine bleeding.

RECENT FINDINGS

We performed a systematic literature search in PubMed/MEDLINE and Embase for original studies written in English (registered in PROSPERO 2019 CRD42019133632), using the terms 'endometrial ablation', 'endometrial destruction', 'endometrial resection', 'hysterectomy', 'menorrhagia', 'dysfunctional uterine bleeding', 'quality of life', 'sexuality' published up to April 2019. Our literature search produced 159 records. After exclusions, nine studies were included showing the following results: both types of treatment significantly improve QoL and psychological wellbeing; hysterectomy is associated with higher rates of satisfaction; hysterectomy is not associated with a significant deterioration in sexual function.

SUMMARY

Hysterectomy is currently more advantageous in terms of improving abnormal uterine bleeding and satisfaction rates than hysteroscopic endometrial destruction techniques. Furthermore, there is some evidence of a greater improvement in general health for women undergoing hysterectomy. However, high-quality prospective randomized controlled trials should be implemented to investigate the effectiveness of hysterectomy and endometrial ablation in the improvement of QoL outcomes in larger patient cohorts.

Deep learning model for classifying endometrial lesions

BACKGROUND

Hysteroscopy is a commonly used technique for diagnosing endometrial lesions. It is essential to develop an objective model to aid clinicians in lesion diagnosis, as each type of lesion has a distinct treatment, and judgments of hysteroscopists are relatively subjective. This study constructs a convolutional neural network model that can automatically classify endometrial lesions using hysteroscopic images as input.

METHODS

All histopathologically confirmed endometrial lesion images were obtained from the Shengjing Hospital of China Medical University, including endometrial hyperplasia without atypia, atypical hyperplasia, endometrial cancer, endometrial polyps, and submucous myomas. The study included 1851 images from 454 patients. After the images were preprocessed (histogram equalization, addition of noise, rotations, and flips), a training set of 6478 images was input into a tuned VGGNet-16 model; 250 images were used as the test set to evaluate the model's performance. Thereafter, we compared the model's results with the diagnosis of gynecologists.

RESULTS

The overall accuracy of the VGGNet-16 model in classifying endometrial lesions is 80.8%. Its sensitivity to endometrial hyperplasia without atypia, atypical hyperplasia, endometrial cancer, endometrial polyp, and submucous myoma is 84.0%, 68.0%, 78.0%, 94.0%, and 80.0%, respectively; for these diagnoses, the model's specificity is 92.5%, 95.5%, 96.5%, 95.0%, and 96.5%, respectively. When classifying lesions as benign or as premalignant/malignant, the VGGNet-16 model's accuracy, sensitivity, and specificity are 90.8%, 83.0%, and 96.0%, respectively. The diagnostic performance of the VGGNet-16 model is slightly better than that of the three gynecologists in both classification tasks. With the aid of the model, the overall accuracy of the diagnosis of endometrial lesions by gynecologists can be improved.

CONCLUSIONS

The VGGNet-16 model performs well in classifying endometrial lesions from hysteroscopic images and can provide objective diagnostic evidence for hysteroscopists.

Endometrial ablation or resection versus levonorgestrel intra-uterine system for the treatment of women with heavy menstrual bleeding and a normal uterine cavity: a systematic review with meta-analysis

BACKGROUND

Endometrial ablation/resection and the levonorgestrel intra-uterine system (LNG-IUS) are well-established treatment options for heavy menstrual bleeding to avoid more invasive alternatives, such as hysterectomy.

OBJECTIVE

The aim was to compare the efficacy and safety of endometrial ablation or resection with the LNG-IUS in the treatment of premenopausal women with heavy menstrual bleeding and to investigate sources of heterogeneity between studies.

SEARCH METHODS

We searched the databases MEDLINE, EMBASE, CENTRAL, Web of Science, Biosis and Google Scholar as well as citations and reference lists published up to August 2019. Two authors independently screened 3701 citations for eligibility. We included randomized controlled trials published in any language, comparing endometrial ablation or resection to the LNG-IUS in the treatment of premenopausal women with heavy menstrual bleeding and a normal uterine cavity.

OUTCOMES

Thirteen studies (N = 884) were eligible. Two independent authors extracted data and assessed the quality of included studies. Random effect models were used to compare the modalities and evaluate sources of heterogeneity. No significant differences were observed between endometrial ablation/resection and the LNG-IUS in terms of subsequent hysterectomy (primary outcome, risk ratio (RR) = 1.13, 95% CI 0.60 to 2.11, P = 0.71, I2 = 14%, 12 studies, 726 women), satisfaction, quality of life, amenorrhea and treatment failure. However, side effects were less common in women treated with endometrial ablation/resection compared to the LNG-IUS (RR = 0.52, 95% CI 0.37 to 0.71, P < 0.001, I2 = 0%, 10 studies, 580 women). Three complications were reported in the endometrial ablation/resection group and none in the LNG-IUS group (P = 0.25). Mean age of the studied populations was identified as a significant source of heterogeneity between studies in subgroup analysis (P = 0.01). In fact, endometrial ablation/resection was associated with a higher risk of subsequent hysterectomy compared to the LNG-IUS in younger populations (mean age ≤ 42 years old, RR = 5.26, 95% CI 1.21 to 22.91, P = 0.03, I2 = 0%, 3 studies, 189 women). On the contrary, subsequent hysterectomy seemed to be less likely with endometrial ablation/resection compared to the LNG-IUS in older populations (mean age > 42 years old), although the reduction did not reach statistical significance (RR = 0.51, 95% CI 0.21 to 1.24, P = 0.14, I2 = 0%, 5 studies, 297 women). Finally, sensitivity analysis taking into account the risk of bias of included studies and type of surgical devices (first and second generation) did not modify the results. Most of the included studies reported outcomes at up to 3 years, and the relative performance of endometrial ablation/resection and LNG-IUS remains unknown in the longer term.

WIDER IMPLICATIONS

Endometrial ablation/resection and the LNG-IUS are two excellent treatment options for heavy menstrual bleeding, although women treated with the LNG-IUS are at higher risk of experiencing side effects compared to endometrial ablation/resection. Otherwise, younger women seem to present a lower risk of eventually requiring hysterectomy when treated with the LNG-IUS compared to endometrial ablation/resection.

The surgical treatment of idiopathic abnormal uterine bleeding: An analysis of 88 000 patients from the French exhaustive national hospital discharge database from 2009 to 2015

Objective

The objective of the study was to compare success rates, complications and management costs of different surgical techniques for abnormal uterine bleeding (AUB).

Methods

This was a retrospective analysis of the French national hospital discharge database. All hospital stays with a diagnostic code for AUB and an appropriate surgical procedure code between 2009 and 2015 inclusive were identified, concerning 109,884 women overall. Outcomes were compared between second generation procedures (2G surgery), first-generation procedures (1G surgery), curettage and hysterectomy. Clinical outcomes were treatment failure and complications during the follow-up period. Costs were attributed using standard French hospital tariffs.

Results

7,863 women underwent a 2G procedure (7.2%), 39,935 a 1G procedure, (36.3%), 38,923 curettage (35.4%) and 23,163 hysterectomy (21.1%). Failure rates at 18 months were 9.9% for 2G surgery, 12.7% for 1G surgery, 20.6% for curettage and 2.8% for hysterectomy. Complication rates at 18 months were 1.9% for 2G surgery, 1.5% for 1G surgery, 1.4% for curettage and 5.3% for hysterectomy. Median 18-month costs were € 1 173 for 2G surgery, € 1 059 for 1G surgery, € 782 for curettage and € 3 090 for hysterectomy.

Conclusion

Curettage has the highest failure rate. Hysterectomy has the lowest failure rate but the highest complication rate and is also the most expensive. Despite good clinical outcomes and relatively low cost, 1G and 2G procedures are not widely used. Current guidelines for treatment of AUB are not respected, the recommended 2G procedures being only used in <10% of cases.