Predictive value of live birth rate based on different intrauterine adhesion evaluation systems following TCRA

Visualized hysteroscopic artificial intelligence fertility assessment system for endometrial injury: an image-deep-learning study

OBJECTIVE

Asherman's syndrome (AS) is a significant cause of subfertility in women from developing countries. Over 80% of AS cases in these regions are linked to dilation and curettage (D&C) procedures following pregnancy. The incidence of AS in patients with infertility and recurrent miscarriage can be as high as 10%, while the pregnancy rate in cases of moderate to severe adhesions can be as low as 34%. We aimed to establish a hysteroscopic artificial intelligence system using image-deep-learning algorithms for fertility assessment.

METHODS

This diagnostic study included 555 cases with 4922 hysteroscopic images from a Chinese intrauterine adhesions cohort clinical database (NCT05381376). The study evaluated two image-deep-learning algorithms' effectiveness in predicting pregnancy within one year, using AUCs and decision curve analysis. The models' performance was evaluated for two-year prediction via concordance index and cumulative time-dependent ROC. A quantifiable visualization panel of the system was established.

RESULTS

The proportional hazard CNN system accurately predicted conception, with AUCs of 0.982, 0.992, and 0.990 in three randomly assigned datasets, superior to the InceptionV3 framework, and achieved a net benefit of 69.4% for subfertility assessment. The system fitted well with c-indexes of 0.920-0.940 and was time-stable. The quantifiable visualization panel displayed four intrauterine pathologies intuitively. The performance was comparable to senior hysteroscopists, with a kappa value of 0.84-0.89.

CONCLUSIONS

The CNN based on the proportional hazard approach accurately assesses fertility postoperatively. The quantifiable visualization panel could assist in intrauterine pathologies assessment, optimize treatment strategies, and achieve individualized and cost-efficient practices.

Effectiveness of degradable polymer film in the management of severe or moderate intrauterine adhesions (PREG-2): a randomized, double-blind, multicenter, stratified, superiority trial

OBJECTIVE

To study the effectiveness of a new intrauterine degradable polymer film (Womed Leaf) in the management of moderate to severe intrauterine adhesions (IUA).

DESIGN

PREG-2 study was a multicenter, double-blind, randomized, controlled, stratified, two-arm superiority clinical trial conducted in 16 centers in seven countries.

SETTING

Not applicable.

PATIENT(S)

Patients ≥18 years scheduled for hysteroscopic adhesiolysis because of symptomatic severe or moderate adhesions (according to American Fertility Society [AFS] IUA score) were considered eligible for the study.

INTERVENTION(S)

After adhesiolysis, patients were randomized at a 1:1 ratio to either have a Womed Leaf film inserted (intervention group) or not (control group).

MAIN OUTCOME MEASURE(S)

The primary effectiveness endpoint of the study was the change in AFS IUA score on second-look hysteroscopy (SLH), assessed by an independent evaluator, and compared with baseline. Information on the rate of no IUA and responder rate was collected as secondary effectiveness outcomes, while reported adverse events and patient-reported outcomes as safety and tolerability measures.

RESULT(S)

Between October 26, 2021, and September 28, 2023, a total of 160 women were randomized (Womed Leaf: n = 75 and controls: n = 85). The reduction in IUA AFS score on SLH was significantly higher in the intervention compared with the control group (mean 5.2 ± 2.8 vs. 4.2 ± 3.2). Similarly, the absence of adhesions on SLH was significantly higher in the intervention group (41% vs. 24%; odds ratio, 2.44; confidence interval, 1.161-5.116). None of the reported adverse events were serious or considered related to the device.

CONCLUSION(S)

Womed Leaf is effective and safe in the management of symptomatic severe or moderate IUAs.

CLINICAL TRIAL REGISTRATION NUMBER

Clinicaltrials.gov identifier: NCT04963179.

Multimodal learning system integrating electronic medical records and hysteroscopic images for reproductive outcome prediction and risk stratification of endometrial injury: a multicenter diagnostic study

OBJECTIVE

To develop a multimodal learning application system that integrates electronic medical records (EMR) and hysteroscopic images for reproductive outcome prediction and risk stratification of patients with intrauterine adhesions (IUAs) resulting from endometrial injuries.

MATERIALS AND METHODS

EMR and 5014 revisited hysteroscopic images of 753 post hysteroscopic adhesiolysis patients from the multicenter IUA database we established were randomly allocated to training, validation, and test datasets. The respective datasets were used for model development, tuning, and testing of the multimodal learning application. MobilenetV3 was employed for image feature extraction, and XGBoost for EMR and image feature ensemble learning. The performance of the application was compared against the single-modal approaches (EMR or hysteroscopic images), DeepSurv and ElasticNet models, along with the clinical scoring systems. The primary outcome was the 1-year conception prediction accuracy, and the secondary outcome was the assisted reproductive technology (ART) benefit ratio after risk stratification.

RESULTS

The multimodal learning system exhibited superior performance in predicting conception within 1-year, achieving areas under the curves of 0.967 (95% CI: 0.950-0.985), 0.936 (95% CI: 0.883-0.989), and 0.965 (95% CI: 0.935-0.994) in the training, validation, and test datasets, respectively, surpassing single-modal approaches, other models and clinical scoring systems (all P<0.05). The application of the model operated seamlessly on the hysteroscopic platform, with an average analysis time of 3.7±0.8 s per patient. By employing the application's conception probability-based risk stratification, mid-high-risk patients demonstrated a significant ART benefit (odds ratio=6, 95% CI: 1.27-27.8, P=0.02), while low-risk patients exhibited good natural conception potential, with no significant increase in conception rates from ART treatment (P=1).

CONCLUSIONS

The multimodal learning system using hysteroscopic images and EMR demonstrates promise in accurately predicting the natural conception of patients with IUAs and providing effective postoperative stratification, potentially contributing to ART triage after IUA procedures.

Artificial intelligence-driven prognostic system for conception prediction and management in intrauterine adhesions following hysteroscopic adhesiolysis: a diagnostic study using hysteroscopic images

Introduction

Intrauterine adhesions (IUAs) caused by endometrial injury, commonly occurring in developing countries, can lead to subfertility. This study aimed to develop and evaluate a DeepSurv architecture-based artificial intelligence (AI) system for predicting fertility outcomes after hysteroscopic adhesiolysis.

Methods

This diagnostic study included 555 intrauterine adhesions (IUAs) treated with hysteroscopic adhesiolysis with 4,922 second-look hysteroscopic images from a prospective clinical database (IUADB, NCT05381376) with a minimum of 2 years of follow-up. These patients were randomly divided into training, validation, and test groups for model development, tuning, and external validation. Four transfer learning models were built using the DeepSurv architecture and a code-free AI application for pregnancy prediction was also developed. The primary outcome was the model's ability to predict pregnancy within a year after adhesiolysis. Secondary outcomes were model performance which evaluated using time-dependent area under the curves (AUCs) and C-index, and ART benefits evaluated by hazard ratio (HR) among different risk groups.

Results

External validation revealed that using the DeepSurv architecture, InceptionV3+ DeepSurv, InceptionResNetV2+ DeepSurv, and ResNet50+ DeepSurv achieved AUCs of 0.94, 0.95, and 0.93, respectively, for one-year pregnancy prediction, outperforming other models and clinical score systems. A code-free AI application was developed to identify candidates for ART. Patients with lower natural conception probability indicated by the application had a higher ART benefit hazard ratio (HR) of 3.13 (95% CI: 1.22-8.02, p = 0.017).

Conclusion

InceptionV3+ DeepSurv, InceptionResNetV2+ DeepSurv, and ResNet50+ DeepSurv show potential in predicting the fertility outcomes of IUAs after hysteroscopic adhesiolysis. The code-free AI application based on the DeepSurv architecture facilitates personalized therapy following hysteroscopic adhesiolysis.

Human umbilical cord-derived mesenchymal stem cells and auto-crosslinked hyaluronic acid gel complex for treatment of intrauterine adhesion

OBJECTIVE

The purpose of this study was to explore the therapeutic characteristics of mesenchymal stem cells generated from human umbilical cord (hUC-MSCs) when utilized in conjunction with auto-crosslinked hyaluronic acid gel (HA-gel) for the management of intrauterine adhesion (IUA). The goal was to see how this novel therapy could enhance healing and improve outcomes for IUA patients.

METHODS

In this study, models of intrauterine adhesion (IUA) were established in Sprague-Dawley (SD) rats, which were then organized and divided into hUC-MSCs groups. The groups involved: hUC-MSCs/HA-gel group, control group, and HA-gel group. Following treatment, the researchers examined the uterine cavities and performed detailed analyses of the endometrial tissues to determine the effectiveness of the interventions.

RESULTS

The results indicated that in comparison with to the control group, both HA-gel, hUC-MSCs, and hUC-MSCs/HA-gel groups showed partial repair of IUA. However, in a more notable fashion transplantation of hUC-MSCs/HA-gel complex demonstrated significant dual repair effects. Significant outcomes were observed in the group treated with hUC-MSCs and HA-gel, they showed thicker endometrial layers, less fibrotic tissue, and a higher number of endometrial glands. This treatment strategy also resulted in a significant improvement in fertility restoration, indicating a profound therapeutic effect.

CONCLUSIONS

The findings of this study suggest that both HA-gel, hUC-MSCs, and hUC-MSCs/HA-gel complexes have the potential for partial repair of IUA and fertility restoration caused by endometrium mechanical injury. Nonetheless, the transplantation of the hUC-MSCs/HA-gel complex displayed exceptional dual healing effects, combining effective anti-adhesive properties with endometrial regeneration stimuli.

Developing and validating a prediction model of live birth in patients with moderate-to-severe intrauterine adhesions: a new approach with endometrial morphology measurement by 3D transvaginal ultrasound

Background

There is no reliable method to predict the live birth rate among patients with moderate-to-severe intrauterine adhesions (IUA) after second-look hysteroscopy. Therefore, we aimed to construct a practical prediction model mainly based on the features of 3D transvaginal ultrasound (3D-TVUS). and other clinical characteristics.

Methods

From January 2018 to February 2020, a total of 870 IUA patients with fertility requirements were retrospectively enrolled based on the same method. First, the predictors were screened by logistic regression analysis. A nomogram was constructed based on the screened predictive factors in the derivation cohort. Next, receiver operating characteristic (ROC), calibration curve, and decision curve analysis (DCA) were used to assess the predictive accuracy and discriminability of the model. Finally, correlation analysis was performed to analyze the correlation between the results of 3D-TVUS and second-look hysteroscopy.

Results

A total of 558 (64.14%) participants had live births. Age, endometrial thickness, assisted reproductive technology, a homogeneous endometrial echo, a lower segment of scar contraction, and upper segmentation of the endometrial absence were included in the model. The predictive model showed good predictive performance in the derivation cohort (area under the curve, 0.837) and validation cohort (0.857). DCA demonstrated its clinical utility. A homogeneous endometrial echo was related to no segmentation of scar contraction (r=0.219; P<0.001) or no segmentation of the endometrial absence (r=0.226; P<0.001). Thicker endometrium was associated with no segmentation of the endometrial absence (r=-0.145; P=0.007).

Conclusions

The proposed method can effectively predict live birth. 3D-TVUS should be an important means for evaluating the endometrium of moderate-to-severe patients with IUA preparing for pregnancy after operation.

The effect of the combined use of an intrauterine device and a Foley balloon in the prevention of adhesion following hysteroscopic adhesiolysis

The aim of this study was to determine whether intrauterine device (IUD) combined with Foley balloon could obtain better efficacy in preventing re-adhesion for patients with intrauterine adhesions (IUAs). The data of 89 patients with IUAs, who underwent transcervical resection of adhesion (TCRA) operation, were retrospectively collected. According to the method used for preventing re-adhesion of the uterine cavity after TCRA, the enrolled patients were divided into IUD group, Foley balloon group and the combined group. The second-look hysteroscopy was carried out at 3 months after TCRA surgery. The severity and extent of IUA were scored by American Fertility Society (AFS) scoring system. The endometrial thickness (EMT) was measured by ultrasound. Furthermore, the menstruation and pregnancy outcomes were also assessed. Our results showed that the postoperative decrease in AFS score was significantly greater in the combined group than in the IUD group or in the Foley balloon group. The increase in menstrual score among the 3 groups was not significantly different. The difference between preoperative and postoperative values of EMT was greater in the combined group than in the other 2 groups. In conclusion, the effect of a Foley balloon combined with IUD in preventing re-adhesion after TCRA might be better than that of IUD or Foley balloon alone.

Impact of concomitant intrauterine adhesions on pregnancy outcomes and obstetric complications in women with a septate uterus

OBJECTIVE

To explore the impact of concomitant intrauterine adhesions (IUAs) on pregnancy outcomes and obstetric complications in women with a septate uterus.

METHODS

This retrospective cohort included women with a septate uterus, with or without IUAs, between 2015 and 2019 in our hospital. The main outcomes were clinical pregnancy rate, live-birth rate, and obstetric complications.

RESULTS

A total of 336 women with a septate uterus-105 women (31.3%) with IUAs and 231 (68.7%) women without IUAs-were analyzed. The rates of clinical pregnancy and live birth among women with moderate-to-severe IUAs were significantly decreased compared with those among women without IUAs (69.9% vs. 76.6%, odds ratio [OR] 0.51; 95% confidence interval [CI] 0.27-0.99, P = 0.046, and 57.0% vs. 67.1%, OR 0.53; 95% CI 0.30-0.95, P = 0.032, respectively). However, these rates were similar between women with mild IUAs and women without IUAs. Women with moderate-to-severe IUAs had a higher incidence of abnormal placentation than women with a septum only (13.2% vs. 1.3%, P = 0.001).

CONCLUSION

Concomitant moderate-to-severe IUAs significantly reduce the rates of clinical pregnancy and live birth and increase the risk of abnormal placentation in subsequent pregnancies in women with a septate uterus.

In vitro fertilization and embryo transfer may improve live birth rate for patients with intrauterine adhesions after hysteroscopic adhesiolysis

OBJECTIVES

The prevalence of intrauterine adhesion (IUA) increased gradually, which seriously affected female reproductive health and fertility. This study aims to analyze the clinical features of pre-, intra-, and post hysteroscopic adhesiolysis (HA) and to identify the main risk factors for non-live birth and other factors affecting pregnancy outcome in patients with IUA.

METHODS

A total of 486 IUA patients with reproductive needs, who underwent HA in the third Xiangya Hospital of Central South University from January 2017 to May 2018, were retrospectively included. The follow-up period was 2-3 years after operation. Univariate analysis and multivariate logistic regression analysis were used to explore the relationship between clinical features and live birth rate in patients with IUA. Pre-operative clinical indicators included age, gravidity, parity, abortion, IUA recurrence, menstrual patterns, and disease course. Intraoperative clinical features assessed in the last operation were uterine cavity length, IUA appearance, IUA area, number of visible uterine cornua, number of visible tubal ostia, and American Fertility Society (AFS) scores. The relationship between clinical indicators and postoperative live birth rate was investigated by univariate analysis and multivariate logistic regression analysis. Pregnancy pattern was the main variable.

RESULTS

Among the 486 IUA patients included in this study, there were 256 (52.67%) live births and 230 (47.33%) non-live births. Univariate analysis and multivariate logistic regression showed that the live birth rate of in vitro fertilization and embryo transfer (IVF-ET) after HA was higher than that of spontaneous pregnancy (OR=0.557, 95% CI 0.361 to 0.861, P=0.008). When the bilaterally fallopian tube ostia were invisible in the last operation (OR=0.322, 95% CI 0.104 to 0.997, P=0.049), patients were more likely to have live birth. The older the patient was, the lower the live birth rate was (OR=1.081, 95% CI 1.034 to 1.131, P<0.001). The live birth rate would be low when the last AFS score was moderate (OR=2.973, 95% CI to 1.541 to 5.738, P<0.010).

CONCLUSIONS

Based on the outcome of the first pregnancy after HA, IUA patients' pregnancy patterns, age, number of visible tubal ostia, and AFS scores noted by a second-look hysteroscopy, are the factors influencing the prognosis for the live birth rate in IUA patients. IVF-ET may improve live birth rate for patients with IUA after HA.

Uterine Cavity Parameters Evaluated by Hysteroscopy can Predict the Live Birth Rate For Intrauterine Adhesion Patients

We aim to establish an objective and accurate prediction model by evaluating the uterine cavity and correlate these key factors with the live birth rate after hysteroscopic adhesiolysis (HA). A total of 457 intrauterine adhesions (IUA) patients were retrospectively enrolled in this study. The participants underwent HA and second-look hysteroscopy at the Third Xiangya Hospital of Central South University. Pregnancy outcomes, including spontaneous live births and no live births (miscarriages and infertility), were followed. Clinical parameters, containing the number of visible uterine horns and tubal ostia, the length of the uterine cavity, among others, were measured and analyzed to determine the dominant variables in an attempt to establish the live birth rate, prediction models. Women in the no live birth group were older than that in the live birth group (P = 0.0002, OR = 0.895, 95% CI: 0.844–0.949) and were more likely to be 2 gravidity (P = 0.0136, OR = 2.558, 95% CI: 1.213–5.394). Uterine cavity length in pre-HA hysteroscopy was longer in the live birth group (P = 0.0018, OR = 1.735, 95% CI: 1.227–2.453), and adhesion scores in pre-HA hysteroscopy were more frequently above 6 (P = 0.0252, OR = 0.286, 95% CI: 0.096–0.856) in the no live birth group. During the second-look, hysteroscopy, visible bilateral fallopian tube ostia were more frequently observed in the live birth group (P = 0.0339, OR = 11.76, 95% CI: 1.207–114.611), and adhesion scores were 4–6 (P < 0.0001, OR = 0.032, 95% CI: 0.007–0.146) and above 6 (P < 0.0001, OR = 0.012, 95% CI: 0.002–0.073) in the no live birth group. The areas under the curves (AUCs) of the pre-HA and second-look hysteroscopy prediction models were 0.7552 and 0.8484, respectively. We established an objective and accurate method for evaluating the uterine cavity by hysteroscopy, and second-look hysteroscopy is more valuable than the fist hysteroscopy in predicting the live birth rate following HA. Visible bilateral fallopian tube ostia or adhesion scores were <4 in the second-look hysteroscopy might predict live birth after surgery.

Correlative study of preoperative three-dimensional transvaginal ultrasound findings and ongoing pregnancy/live birth in patients with intrauterine adhesions following hysteroscopic adhesiolysis: a retrospective study

BACKGROUND

Three-dimensional transvaginal ultrasound (3D-TVUS) has recently been adopted in the gynecological sciences as it provides an accurate illustration of adhesions and the extent of cavity damage, and hence, can be used as an essential tool for the prognosis of intrauterine adhesions (IUA). This study aims to demonstrate whether preoperative 3D-TVUS features are relevant to ongoing pregnancy and live births in patients with IUA following hysteroscopic adhesiolysis (HA).

METHODS

From February 22, 2018, to October 31, 2018, a total of 401 patients with moderate to severe IUA and underwent HA were retrospectively enrolled. Preoperative 3D-TVUS diagnosed data and the patients' basic information were collected, and patients were followed up over 2 years after HA for reproductive outcomes. The correlation between each imaging variable and ongoing pregnancy or live birth was analyzed by binary logistic regression.

RESULTS

Among the 401 patients, 143 had live births, 41 patients had abortions, and 217 patients were infertile. Thick endometrium was found to be favorable for ongoing pregnancy (ongoing pregnancy group =5.4±1.95 mm, no-ongoing pregnancy group =4.7±2.24 mm, P=0.0095) and live birth (live birth group=5.6±1.92 mm, no-live birth group =4.7±2.20 mm, P=0.0029). Scar contraction was not conducive for pregnancy, while the lower segmentation was not a risk factor for ongoing pregnancy (P=0.0003). It also was a risk factor for ongoing pregnancy (P<0.0001) and live birth (P<0.0001) when the segmentation of the endometrial absence was mainly in the upper and middle segments of the uterine cavity. The area under the curves (AUCs) of the prediction model for ongoing pregnancy and live birth were 0.9116 and 0.8751, respectively, based on the meaningful variables above combined with other clinical characteristics.

CONCLUSIONS

Preoperative 3D-TVUS features have a close correlation with ongoing pregnancy and live births in patients with IUA following HA, and can be applied for predicting ongoing pregnancy and live births in IUA patients post-HA.

Pregnancy Patterns Impact Live Birth Rate for Patients With Intrauterine Adhesions After Hysteroscopic Adhesiolysis: A Retrospective Cohort Study

Objective

The pregnancy patterns and other factors of live birth for patients with intrauterine adhesions (IUAs) were identified by analyzing the clinical features of pre-, intra-, and post-hysteroscopic adhesiolysis (HA).

Design

A total of 742 patients with IUAs who wanted to become pregnant underwent HA from January 2017 to May 2018 at the Third Xiangya Hospital of Central South University. The patient follow-up period was 2 years post-HA. A logistic regression was performed to analyze the clinical characteristics associated with a live birth for patients with IUAs. Pre-operative clinical indicators included age, gravidity, parity, abortion, IUA recurrence, menstrual patterns, disease course. Intraoperative clinical features assessed in the last operation were uterine cavity length, IUA appearance, IUA area, number of visible uterine cornua, number of visible tubal ostia, AFS scores. Pregnancy patterns were post-hysteroscopic adhesiolysis features.

Results

Among the 742 IUA patients, 348 (46.9%) had a live birth and 394 (53.1%) did not. A bivariate and binary logistic regression analysis showed that IUA patients’ pregnancy patterns, age, number of visible tubal ostia noted by a second-look hysteroscopy, and American Fertility Society (AFS) scores were significantly related to the live birth rate (P < 0.05).

Conclusions

Pregnancy patterns, age, number of visible tubal ostia, and AFS scores were significantly related to the live birth rate and may be considered potential predictors of the live birth rate in IUA patients. The indications of assisted reproductive technology (ART) might be a better choice for patients with recurrent IUAs.

EndMT: New findings on the origin of myofibroblasts in endometrial fibrosis of intrauterine adhesions

BACKGROUND

Intrauterine adhesion (IUA) is one of the leading causes of infertility and the main clinical challenge is the high recurrence rate. The key to solving this dilemma lies in elucidating the mechanisms of endometrial fibrosis. The aim of our team is to study the mechanism underlying intrauterine adhesion fibrosis and the origin of fibroblasts in the repair of endometrial fibrosis.

METHODS

Our experimental study involving an animal model of intrauterine adhesion and detection of fibrosis-related molecules. The levels of molecular factors related to the endothelial-to-mesenchymal transition (EndMT) were examined in a rat model of intrauterine adhesion using immunofluorescence, immunohistochemistry, qPCR and Western blot analyses. Main outcome measures are levels of the endothelial marker CD31 and the mesenchymal markers alpha-smooth muscle actin (α-SMA) and vimentin.

RESULTS

Immunofluorescence co-localization of CD31 and a-SMA showed that 14 days after moulding, double positive cells for CD31 and a-SMA could be clearly observed in the endometrium. Decreased CD31 levels and increased α-SMA and vimentin levels indicate that EndMT is involved in intrauterine adhesion fibrosis.

CONCLUSIONS

Endothelial cells promote the emergence of fibroblasts via the EndMT during the endometrial fibrosis of intrauterine adhesions.

Hysteroscopic management of retained products of conception: A systematic review

BACKGROUND

The management of retained products of conception (RPOC) is not well standardised due to a lack of evidence-based guidelines. Hysteroscopic resection has been proven to be safe and is hypothesised to have lower risk than dilation and curettage, but data comparing the two directly are limited.

AIM

The aim of this study is to evaluate the outcomes for hysteroscopic resection for the management of RPOC in comparison to current standard management techniques.

METHODS

A literature search was conducted in September 2019 using MEDLINE, Scopus, The Cochrane Library and Web of Science. The key search terms were 'hysteroscopy'/'hysteroscopic resection' and 'retained products of conception'/'RPOC'. Both prospective and retrospective studies were included. A total of 19 studies were included (n = 2314). Due to a critical risk of bias in all studies with a comparison arm, a meta-analysis was not performed. Meta-analysis techniques were still used to provide summary estimates for primary and secondary outcomes, including conception rate, time to conception, live birth rate, intrauterine adhesions (IUAs), surgical complications and future pregnancy complications.

RESULTS

The overall conception rate for hysteroscopic resection was 81.1% (live birth rate 87.3%) compared to 65.4% for non-hysteroscopic management (live birth rate 93.8%). After hysteroscopic resection the overall complication rate was 1.9% and the IUA rate was 6.8%.

CONCLUSIONS

Due to the poor quality and overall scarcity of comparative data, the question whether hysteroscopic resection is superior to traditional curettage for the management of RPOC remains unanswered. This review provides summary data, which will enable the design of adequately powered future studies.

Endometrial Perivascular Progenitor Cells and Uterus Regeneration

Ovarian steroid-regulated cyclical regeneration of the endometrium is crucial for endometrial receptivity and embryo implantation, and it is dependent on the dynamic remodeling of the endometrial vasculature. Perivascular cells, including pericytes surrounding capillaries and microvessels and adventitial cells located in the outermost layer of large vessels, show properties of mesenchymal stem cells, and they are thus promising candidates for uterine regeneration. In this review, we discuss the structure and functions of the endometrial blood vasculature and their roles in endometrial regeneration, the main biomarkers and characteristics of perivascular cells in the endometrium, and stem cell-based angiogenetic therapy for Asherman's syndrome.