OBJECTIVE: To summarize and compare the accuracy of transvaginal ultrasound (TVS), 3D-TVS, and sonohysterography (SHG) for the diagnosis of intrauterine adhesions (IUA).
METHODS: The computer searches databases such as web of science, Medline, EMBASE, and PubMed collecting diagnostic studies of IUA via ultrasound. The retrieval time was included from inception to January 1, 2023. Two researchers independently screened the literature, extracted information, and used RevMan 5.3 to complete an assessment of the risk of bias in the included literature. Meta-analysis of included studies using Stata 16.0 and Meta Disc 1.4 software.
RESULTS: Thirteen studies were included. The analysis results of 2D-TVS are The sensitivity (SEN): 0.54 (95% CI [0.28078]), specificity (SPE): 0.96 (95% CI [0.78, 0.99]), and the area (AUC) under the operating characteristic curve (SROC): 0.83 (95% CI [0.80, 0.86]); the SEN, SPE, and AUC of 3D-TVS are: 0.96 (95% CI [0.90, 0.98]), 0.84 (95% CI [0.68, 0.93]), 0.97 (95% CI [0.95, 0.98]); and the SEN, SPE, and AUC of SHG are: 0.74 (95% CI [0.53, 0.88]), 0.97 (95% CI [0.94, 0.99]), 0.95 (95% CI [0.93, 0.97]).
CONCLUSIONS: The current results show that the diagnostic value of 3D-TVS for IUA is better than SHG and significantly higher than that of 2D-TVS. However, the analysis of subgroups is still limited by the number of included studies. In order to better explore the application of ultrasound in intrauterine adhesion, more high-quality studies are needed in the future.

Automated perimetrium segmentation of transvaginal ultrasound images is an important process for computer-aided diagnosis of uterine diseases. However, ultrasound images often contain various structures and textures, and these structures have different shapes, sizes, and contrasts; therefore, accurately segmenting the parametrium region of the uterus in transvaginal uterine ultrasound images is a challenge. Recently, many fully supervised deep learning-based methods have been proposed for the segmentation of transvaginal ultrasound images. Nevertheless, these methods require extensive pixel-level annotation by experienced sonographers. This procedure is expensive and time-consuming. In this paper, we present a bidirectional copy-paste Mamba (BCP-Mamba) semi-supervised model for segmenting the parametrium. The proposed model is based on a bidirectional copy-paste method and incorporates a U-shaped structure model with a visual state space (VSS) module instead of the traditional sampling method. A dataset comprising 1940 transvaginal ultrasound images from Tongji Hospital, Huazhong University of Science and Technology is utilized for training and evaluation. The proposed BCP-Mamba model undergoes comparative analysis with two widely recognized semi-supervised models, BCP-Net and U-Net, across various evaluation metrics including Dice, Jaccard, average surface distance (ASD), and Hausdorff_95. The results indicate the superior performance of the BCP-Mamba semi-supervised model, achieving a Dice coefficient of 86.55%, surpassing both U-Net (80.72%) and BCP-Net (84.63%) models. The Hausdorff_95 of the proposed method is 14.56. In comparison, the counterparts of U-Net and BCP-Net are 23.10 and 21.34, respectively. The experimental findings affirm the efficacy of the proposed semi-supervised learning approach in segmenting transvaginal uterine ultrasound images. The implementation of this model may alleviate the expert workload and facilitate more precise prediction and diagnosis of uterine-related conditions.

BACKGROUND: Conjoined twins are a rare twin malformation commonly presenting as single amniotic sac twinning, with double amniotic sac twinning being extremely rare and poorly reported. Most conjoined twins are females.
METHODS: A woman of childbearing age conceived naturally, and at 8 wk of gestation, transvaginal ultrasonography showed an embryo and cardiac tube pulsation in both amniotic sacs. On dynamic observation, the two embryos were connected in the lower abdomen, with restricted movement. A repeat transvaginal ultrasound at 11 wk showed that the intestinal tubes of both fetuses were connected in the lower abdomen. The pregnancy was terminated and labor was induced.
CONCLUSIONS: Transvaginal ultrasound may detect conjoined twin malformations in an early stage. Our case provides diagnostic insights for ultrasonographers and can help develop early therapeutic interventions.

BACKGROUND: Pelvic floor myofascial pain is one of the pelvic floor dysfunction diseases disturbing women after delivery. There is a lack of objective standardization for the diagnosis of pelvic floor myofascial pain due to the various symptoms and the dependence on the palpating evaluation. Ultrasound imaging has the advantages of safety, simplicity, economy and high resolution, which makes it an ideal tool for the assistant diagnosis of pelvic floor myofascial pain and evaluation after treatment.
METHODS: This is a retrospective case-control study including women accepting evaluation of pelvic floor function at 6 weeks to 1 year postpartum. They were divided into pelvic floor myofascial pain group and normal control group. A BCL 10-5 biplane transducer was applied to observed their puborectalis. The length, minimum width, area, deficiency, deficiency length, deficiency width, deficiency area, rate of deficiency area, local thickening,angle between the tendinous arch of levator ani muscle and puborectalis of corresponding puborectalis in different groups were observed and measured.
RESULTS: A total of 220 postpartum women participated in the study, with 77 in the pelvic floor myofascial pain group and 143 in the normal control group. The Intraclass correlation coefficient value was over 0.750, and Kappa ranged from 0.600 to 0.800. puborectalis deficiency (adjusted odds ratio = 11.625, 95% confidence interval = 4.557-29.658) and focal thickening (adjusted odds ratio = 16.891, 95% confidence interval = 1.819-156.805) were significantly associated with higher odds of having postpartum pelvic floor myofascial pain. Grayscale or the angle between the arch tendineus levator ani and puborectalis measurements on the pain side tended to be smaller than on the non-pain side in patients with unilateral puborectalis or iliococcygeus pain (P < 0.05).
CONCLUSIONS: This study demonstrated that transvaginal ultrasound was a potentially efficient technique for evaluating postpartum pelvic floor myofascial pain due to its ability to assess various sonographic characteristics of the levator ani muscles.

OBJECTIVE: To investigate the immediate effects of electro-acupuncture (EA) on endometrial blood flow among recurrent implantation failure (RIF) patients.
METHODS: Eighty RIF patients, enrolled from March 2022 to December 2022, were randomly allocated into either the EA group (40 cases) or the waiting-list (WL) group (40 cases) by using a random number table. The EA group underwent acupuncture at points of Shenting (GV 24), Baihui (GV 4), Benshen (GB 13), bilateral Zigong (EX-CA 1), Huangshu (KI 16), Sanyinjiao (SP 6) and Xuehai (SP10), and electric acupuncture apparatus was connected to EX-CA 1, KI 16, SP 6, and SP 10 with disperse-dense waves at 4/20 Hz frequencies for 30 min after transvaginal ultrasound, while the WL group received no intervention. The primary outcome measured was the endometrial volume blood flow. The secondary outcomes included the bilateral uterine artery index, endometrial volume, endometrial blood flow type, vascular distribution index (VIMV) for endometrial and ovary, clinical pregnancy rate, and embryo implantation rate.
RESULTS: In the EA group, there was a notable decrease in the bilateral pulsatility index and a significant improvement in the endometrial blood flow type post-EA (P<0.05). Both the endometrial blood flow type and VIMV for the endometrium and right ovary were markedly higher in the EA group compared to the WL group post-treatment (P<0.05). Conversely, no significant disparities were observed in vascular index, flow index, vascular blood flow index, uterine arterial blood flow indices, endometrial volume, clinical pregnancy rate and embryo implantation rate between the two groups after treatment (P>0.05). Besides, no adverse events related to EA were observed.
CONCLUSIONS: EA can promptly ameliorate VIMV for the endometrial and right ovary, and endometrial blood flow type. Future randomized controlled trials are warranted to investigate the long-term effects of EA on blood flow of RIF patients and its implications for pregnancy outcomes. (Trial registration No. ChiCTR2200057377).

A rare case of unicornuate uterus with interstitial ectopic pregnancy was diagnosed using three-dimensional transvaginal ultrasound (3D-TVUS). The ultrasound revealed a \"lancet-shaped\" endometrial corona, a gestational sac near the uterus base extending toward the uterine serosa, and visible interstitial lines. The patient underwent laparoscopic surgery for a lesion in the right fallopian tube. 3D-TVUS was crucial in precisely locating the gestational sac, aiding in effective treatment. Interstitial ectopic pregnancies risk severe hemorrhaging upon rupture. Rapid, accurate diagnosis is vital for lifesaving treatment and preventing critical complications.

There is no clear evidence of clinical significance of endometrial compaction, which can be measured by a reduction in endometrial thickness (EMT) during the follicular-luteal transition before the day of embryo transfer. In this study, we aim to determine whether endometrial compaction has an effect on in vitro fertilization (IVF) success.
We searched PubMed, Cochrane, Embase, and Web of Science electronic databases for studies published in English up to March 2023. Heterogeneity between studies was assessed using the I2 statistic. The random effects model and fixed effects model was used to pool the risk ratio (RR) with a corresponding 95% confidence interval (CI). A subgroup analysis was performed based on different methods of ultrasonic measurement and different endometrial compaction rates (ECR). Stata 17.0 software was used for meta-analysis. Pregnancy outcomes, which included clinical pregnancy rate, ongoing pregnancy rate, live birth rate, and spontaneous abortion rate, were evaluated.
In this study, 18 cohort studies were included, involving 16,164 embryo transfer cycles. Pooled results indicated that there was no significant difference between the endometrial compaction group and the non-compaction group in terms of clinical pregnancy rate (RR [95% CI]=0.98 [0.90,1.08]; I2 = 69.76%), ongoing pregnancy rate (RR [95% CI]=1.18 [0.95,1.47]; I2 = 78.77%), live birth rate (RR [95% CI]= 0.97 [0.92,1.02]; I2 = 0.00%) or spontaneous abortion rate (RR [95% CI]= 1.07[0.97,1.26]; I2 = 0.00%). According to the subgroup analysis of ultrasonic measurement methods, in the transvaginal ultrasound (TVUS) combined with abdominal ultrasonography (AUS) cycles of the endometrial compaction group, the rate of ongoing pregnancy (RR [95% CI] = 1.69 [1.26, 2.26]; I2 = 29.27%) and live birth (RR [95% CI] = 1.27 [1.00,1.61]; I2 = 62.28%) was significantly higher than that of the non-compaction group. Additionally, subgroup analysis based on ECR revealed a significantly higher rate of ongoing pregnancy when ECR ≥ 15% (RR [95% CI] = 1.99 [1.61, 2.47]; I2 = 0.00%).
Endometrial compaction has no adverse effect on clinical pregnancy rate, ongoing pregnancy rate, live birth rate, or spontaneous abortion rate. A possible explanation for the contradictory findings of previous studies lies in the method by which the EMT is measured.
https://www.crd.york.ac.uk/prospero/display_record.php?ID=CRD42023430511, identifier CRD42023430511.

OBJECTIVE: Ultrasound imaging is the preferred method for the early diagnosis of endometrial diseases because of its non-invasive nature, low cost, and real-time imaging features. However, the accurate evaluation of ultrasound images relies heavily on the experience of radiologist. Therefore, a stable and objective computer-aided diagnostic model is crucial to assist radiologists in diagnosing endometrial lesions.
METHODS: Transvaginal ultrasound images were collected from multiple hospitals in Quzhou city, Zhejiang province. The dataset comprised 1875 images from 734 patients, including cases of endometrial polyps, hyperplasia, and cancer. Here, we proposed a based self-supervised endometrial disease classification model (BSEM) that learns a joint unified task (raw and self-supervised tasks) and applies self-distillation techniques and ensemble strategies to aid doctors in diagnosing endometrial diseases.
RESULTS: The performance of BSEM was evaluated using fivefold cross-validation. The experimental results indicated that the BSEM model achieved satisfactory performance across indicators, with scores of 75.1%, 87.3%, 76.5%, 73.4%, and 74.1% for accuracy, area under the curve, precision, recall, and F1 score, respectively. Furthermore, compared to the baseline models ResNet, DenseNet, VGGNet, ConvNeXt, VIT, and CMT, the BSEM model enhanced accuracy, area under the curve, precision, recall, and F1 score in 3.3-7.9%, 3.2-7.3%, 3.9-8.5%, 3.1-8.5%, and 3.3-9.0%, respectively.
CONCLUSIONS: The BSEM model is an auxiliary diagnostic tool for the early detection of endometrial diseases revealed by ultrasound and helps radiologists to be accurate and efficient while screening for precancerous endometrial lesions.

UNASSIGNED: The purpose of this study was to assess the diagnostic efficacy of the vascular index (VI) on superb microvascular imaging (SMI) in distinguishing normal uterine cervical epithelium, high-grade cervical intraepithelial neoplasia (CIN), and cervical cancer.
UNASSIGNED: The retrospective study included women with pathology-confirmed CIN or cervical cancer, who underwent transvaginal ultrasound and SMI between April 2021 and October 2022. The SIM manifestations of normal cervix and cervical lesions were reviewed. SIM were measured and converted into vascular index (VI) which compared between cervical lesions and control groups. We have retrospectively compared ultrasound features of cervical lesions and characteristics of patients. Measurement reliability was evaluated by intra class correlation coefficient (ICC).
UNASSIGNED: A total of 235 consecutive females were enrolled, comprising 38 with high-grade CIN, 96 with cervical cancer, and 101 with a normal uterine cervix. The microvascular architecture exhibited significant variations between premalignant and malignant cervical lesions. Branch-like patterns were predominantly observed in high-grade CIN, while crab claw-like and fireball-like patterns were more commonly associated with cervical cancer. The median VI of cervical cancer (34.7 ± 10.3) was significantly higher than that of high-grade CIN (17.6 ± 4.2) (P < 0.001). Moreover, the VI values of cervical cancer differed significantly among different FIGO stages and pathological types (P < 0.001 and P = 0.003, respectively). The VI demonstrated superior diagnostic performance for cervical lesions compared to vascular patterns (AUC = 0.974 and 0.969, respectively). Using a cut-off value of 25.5, the VI yielded a sensitivity of 82.3% and a specificity of 99.3% for cervical lesion detection.
UNASSIGNED: The SMI parameter (VI) exhibited a significantly higher value in cervical cancer compared to high-grade CIN, with a high level of agreement among observers. These findings suggest that quantitative SMI holds promise as an imaging technique for the detection and characterization of cervical lesions.

To prospectively assess the diagnostic accuracy of MRI and transvaginal ultrasound (TVS) as well as the prognostic value of MRI for intrauterine adhesions (IUAs), using hysteroscopy as the reference standard.
Prospective observational study.
Tertiary medical centre.
Ninety-two women with amenorrhea, hypomenorrhea, subfertility, or recurrent pregnancy loss who underwent MRI and in whom Asherman\'s syndrome was suspected upon TVS.
MRI and TVS were conducted approximately 1 week before hysteroscopy.
Ninety-two patients suspected of having Asherman\'s syndrome were examined by MRI and TVS within 7 days of an upcoming hysteroscopy. All hysteroscopy procedures were performed during the early proliferative phase of the menstrual cycle. All hysteroscopic diagnoses were performed by an experienced expert. All MRIs were read by 2 experienced, blinded radiologists.
MRI was highly accurate (94.57%), sensitive (98.8%), and specific (42.9%) for diagnosing IUAs with a positive predictive value of 95.5% and a negative predictive value of 75%. The diagnostic values of MRI and TVS were significantly different according to McNemar tests. Junctional zone signal and junctional zone alterations correlated with the stage of IUAs.
MRI is markedly superior to TVS in terms of diagnostic accuracy for IUAs, with total agreement with hysteroscopic findings. However, the main advantage of MRI is that, unlike TVS and hysterosalpingography, it can be used to assess the risk of hysteroscopy and to predict postoperative recovery and future pregnancy based on the uterine junctional zone.