Transvaginal Ultrasound Imaging Research Articles

Comprehensive Management of Bowel Endometriosis: Surgical Techniques, Outcomes, and Best Practices

Bowel endometriosis is a complex condition predominantly impacting women in their reproductive years, which may lead to chronic pain, gastrointestinal symptoms, and infertility. This review highlights current approaches to the diagnosis and management of bowel endometriosis, emphasizing a multidisciplinary strategy. Diagnostic methods include detailed patient history, physical examination, and imaging techniques like transvaginal ultrasound (TVUS) and magnetic resonance imaging (MRI), which aid in preoperative planning. Management options range from hormonal therapies for symptom relief to minimally invasive surgical techniques. Surgical interventions, categorized as shaving excision, disc excision, or segmental resection, depend on factors such as lesion size, location, and depth. Shaving excision is preferred for its minimal invasiveness and lower complication rates, while segmental resection is reserved for severe cases. This review also explores nerve-sparing strategies to reduce surgical morbidity, particularly for deep infiltrative cases close to the rectal bulb, anal verge, and rectosigmoid colon. A structured, evidence-based approach is recommended, prioritizing conservative surgery to avoid complications and preserve fertility as much as possible. Comprehensive management of bowel endometriosis requires expertise from both gynecologic and gastrointestinal specialists, aiming to improve patient outcomes while minimizing long-term morbidity.

Utilizing MV-FLOW™ and multidimensional ultrasound characteristics for prognosticating FET outcomes in RIF patients: Study Protocol for a cross-sectional study.

Recurrent implantation failure (RIF) is a common issue in frozen-thawed embryo transfer (FET). Prior to transfer, uterine endometrial receptivity of FET patients can be assessed using multimodal transvaginal ultrasound indicators to predict the success rate of the current FET cycle. Endometrial blood flow is a crucial element in evaluating endometrial receptivity. MV-FLOW™ is an advanced two-dimensional superb microvascular imaging technology that can detect and display blood flow in micro-vessels. The data for this study were obtained from an ongoing cross-sectional study comprising 323 RIF patients and 323 first implantation (FI) patients, who underwent transvaginal ultrasound before FET. We collected basic clinical data and multimodal ultrasound data from these patients as predictive features, with clinical pregnancy as the predictive label, for model training. Based on the above, this study aims to establish and validate a clinical prediction model for FET outcomes using support vector classification (SVC) algorithms, based on MV-FLOW™ and multidimensional transvaginal ultrasound imaging features. The objective is to determine the predictive role of multimodal transvaginal ultrasound in embryo transfer outcomes and provide evidence for the clinical application of MV-FLOW™. Trial registration: Trial Registration: ChiCTR2400086401.

Intra- and interobserver agreement of proposed objective transvaginal ultrasound image-quality scoring system for use in artificial intelligence algorithm development.

The development of valuable artificial intelligence (AI) tools to assist with ultrasound diagnosis depends on algorithms developed using high-quality data. This study aimed to test the intra- and interobserver agreement of a proposed image-quality scoring system to quantify the quality of gynecological transvaginal ultrasound (TVS) images, which could be used in clinical practice and AI tool development. A proposed scoring system to quantify TVS image quality was created following a review of the literature. This system involved a score of 1-4 (2 = poor, 3 = suboptimal and 4 = optimal image quality) assigned by a rater for individual ultrasound images. If the image was deemed inaccurate, it was assigned a score of 1, corresponding to 'reject'. Six professionals, including two radiologists, two sonographers and two sonologists, reviewed 150 images (50 images of the uterus and 100 images of the ovaries) obtained from 50 women, assigning each image a score of 1-4. The review of all images was repeated a second time by each rater after a period of at least 1 week. Mean scores were calculated for each rater. Overall interobserver agreement was assessed using intraclass correlation coefficient (ICC), and interobserver agreement between paired professionals and intraobserver agreement for all professionals were assessed using weighted Cohen's kappa and ICC. Poor levels of interobserver agreement were obtained between the six raters for all 150 images (ICC, 0.480 (95% CI, 0.363-0.586)), as well as for assessment of the uterine images only (ICC, 0.359 (95% CI, 0.204-0.523)). Moderate agreement was achieved for the ovarian images (ICC, 0.531 (95% CI, 0.417-0.636)). Agreement between the paired sonographers and sonologists was poor for all images (ICC, 0.336 (95% CI, -0.078 to 0.619) and 0.425 (95% CI, 0.014-0.665), respectively), as well as when images were grouped into uterine images (ICC, 0.253 (95% CI, -0.097 to 0.577) and 0.299 (95% CI, -0.094 to 0.606), respectively) and ovarian images (ICC, 0.400 (95% CI, -0.043 to 0.669) and 0.469 (95% CI, 0.088-0.689), respectively). Agreement between the paired radiologists was moderate for all images (ICC, 0.600 (95% CI, 0.487-0.693)) and for their assessment of uterine images (ICC, 0.538 (95% CI, 0.311-0.707)) and ovarian images (ICC, 0.621 (95% CI, 0.483-0.728)). Weak-to-moderate intraobserver agreement was seen for each of the raters with weighted Cohen's kappa ranging from 0.533 to 0.718 for all images and from 0.467 to 0.751 for ovarian images. Similarly, for all raters, the ICC indicated moderate-to-good intraobserver agreement for all images overall (ICC ranged from 0.636 to 0.825) and for ovarian images (ICC ranged from 0.596 to 0.862). Slightly better intraobserver agreement was seen for uterine images, with weighted Cohen's kappa ranging from 0.568 to 0.808 indicating weak-to-strong agreement, and ICC ranging from 0.546 to 0.893 indicating moderate-to-good agreement. All measures were statistically significant (P < 0.001). The proposed image quality scoring system was shown to have poor-to-moderate interobserver agreement and mostly weak-to-moderate levels of intraobserver agreement. More refinement of the scoring system may be needed to improve agreement, although it remains unclear whether quantification of image quality can be achieved, given the highly subjective nature of ultrasound interpretation. Although some AI systems can tolerate labeling noise, most will favor clean (high-quality) data. As such, innovative data-labeling strategies are needed. © 2025 The Author(s). Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

Ultrasound-based geometric modeling of the human ovary with applications to cryopreservation.

Successful cryopreservation of the whole ovary outside of the body, while a woman undergoes cancer treatments, may help preserving fertility and regaining hormone balance during recovery. One of the key challenges in whole ovary cryopreservation is adequately loading the organ with cryoprotective agents (CPAs). Another notable challenge in developing the application is the lack of geometric data needed for designing matching thermal protocols. The objective of the current study is twofold: (i) to develop an effective geometric reconstruction method for the ovary, based on transvaginal ultrasound (TVUS) data, and (ii) to perform a pilot study on the thermal effects associated with CPA loading with application to vitrification. This study includes screening of 127 TVUS imaging datasets of ovaries from healthy ovulatory participants, reconstruction of 14 geometric models, and thermally analyzing two representative geometric models of low and high mature follicles-to-organ volume ratios. Results of this study demonstrate that the proposed reconstruction method is faster and more accurate than that facilitated by commercially available software (SonoAVC, GE Healthcare). Two extremes were investigated: (1) complete vitrification of the ovary, and (2) crystallization of mature follicles while the remaining ovarian stroma vitrifies. CPA loading into the mature follicles is considered an outstanding cryopreservation challenge, but with very little impact on long-term fertility preservation. Results of this study suggest that ovarian preservation by vitrification is feasible when sufficient CPA loading is achieved, while identifying the most suitable CPA for the task remains a challenge beyond the scope of the current study.

Current surgical treatment of uterine isthmocele: an update of existing literature.

The prevalence of uterine isthmocele, also known as a uterine niche, has risen in parallel with increasing cesarean section (CS) rates, affecting approximately 60% of women depending on their history of cesarean deliveries. This condition, now categorized as cesarean scar disorder (CSD) by the "Delphi consensus," is characterized by one primary or two secondary symptoms. Diagnosis can be made through transvaginal ultrasound, sonohysterography, hysteroscopy, or magnetic resonance imaging (MRI). Management of isthmocele may involve pharmacological or surgical interventions. This review aims to provide a thorough analysis of the surgical management options, focusing on postoperative symptom relief, intraoperative and postoperative complications, length of hospital stay, and impact on secondary infertility. PubMed was comprehensively searched for observational studies from inception to 07.08.2024. Surgical treatments include hysteroscopic resection, laparoscopic procedures, and vaginal approaches, all of which offer comparable symptom relief. However, the vaginal approach is associated with a longer hospital stay. The robotic-assisted approach shows promising results but lacks extensive data. Among surgical options, hysteroscopic treatment has the fewest complications but is generally avoided when residual myometrial thickness (RMT) is less than 3mm. While many CSDs remain asymptomatic, and some women with uterine isthmocele may not wish to conceive, symptomatic patients or those desiring to conceive may benefit from surgical intervention. The choice of procedure should be based on individual patient characteristics, particularly RMT, to define the most appropriate surgical approach.

Relationship Between Ultrasound Diagnosis, Symptoms and Pain Scale Score on Examination in Patients with Uterosacral Ligament Endometriosis.

Background/Objectives: This study investigated patient pain descriptors for transvaginal ultrasound (TVS) diagnostic evaluation of endometriosis for uterosacral ligaments (USLs), including correlation between USL thickness and site-specific tenderness (SST). It further investigated if SST could positively assist diagnosing endometriosis on TVS. Methods: TVS images and SST pain descriptors were collected from 42 patients. SST was evaluated by applying sonopalpation during TVS. The images were presented to six observers for diagnosis based on established USL criteria. Following this, they were given the SST pain scores and asked to reevaluate their diagnosis to assess if the pain scores impacted their decision. Results: An independent t-test showed that the patients with an endometriosis history had higher pain scores overall (7.2 ± 0.59) compared to the patients with no history (0.34 ± 0.12), t (40) = 8.8673. Spearman's correlation showed a strong correlation to the pain scale score for clinical symptoms (r = 0.74), endometriosis diagnosis (r = 0.78), USL thickness (r = 0.74), and when USL nodules were identified (r = 0.70). Paired t-tests showed that the observers demonstrated a higher ability to correctly identify endometriosis with the pain scale information (33 ± 8.83) as opposed to not having this information (29.67 ± 6.31), which was a statistically significant change of 3.33, t (5) = 2.7735. Conclusions: Patients with an endometriosis history have significantly higher pain scores on TVS compared to patients with no endometriosis history. A strong correlation was shown between SST pain scores and patient symptoms, USL thickness, and USL nodules. Inclusion of SST alongside TVS imaging shows promise, with these results demonstrating a higher ability to diagnose endometriosis with additional SST pain scale information.

Detection of Ovarian Tumors Using TVUS Imaging and Segmentation Techniques

Ovarian most cancers remains a giant health subject due to its regularly asymptomatic development until superior stages, where treatment options are confined. Early detection is critical for enhancing affected person outcomes and survival costs. This observe proposes a comprehensive technique leveraging superior photograph processing techniques for the early detection and category of ovarian tumors the usage of trans vaginal ultrasound (TVUS) snap shots. The method starts with preprocessing steps which include median filtering to do away with noise artifacts inclusive of salt and pepper noise from ultrasound photos. Ultimately, picture enhancement techniques are applied to enhance contrast and intensity, observed through binary sample evaluation to signify texture features vital for tumor identification. Photo segmentation is performed the use of okay- manner clustering and gray degree Co-prevalence Matrix (GLCM) analysis to isolate and analyze areas of interest within the ovarian photos. A Convolutional Neural community (CNN) is then hired for correct classification of ovarian tumors as regular, benign, or malignant primarily based on the extracted functions. This approach not handiest enhances the diagnostic accuracy but also minimizes affected person publicity to ionizing radiation, making it appropriate for ordinary medical applications. The proposed methodology represents a considerable advancement within the discipline of ovarian cancer detection, presenting a non-invasive and green way to evaluate ovarian health and facilitate timely intervention. Destiny research directions include refining the set of rules’s performance with large datasets and exploring additional imaging modalities for complete ovarian fitness evaluation.

Artificial intelligence model for enhancing the accuracy of transvaginal ultrasound in detecting endometrial cancer and endometrial atypical hyperplasia

ObjectivesTransvaginal ultrasound is typically the initial diagnostic approach in patients with postmenopausal bleeding for detecting endometrial atypical hyperplasia/cancer. Although transvaginal ultrasound demonstrates notable sensitivity, its specificity remains limited. The objective...

Coexistence of uterine adenosarcoma and endometrioid endometrial carcinoma: A case report and literature review.

Uterine adenosarcoma coexisting with endometrial carcinoma is a very rare disease. Herein, we reported the case of uterine adenosarcoma coexisting with endometrioid endometrial carcinoma. Transvaginal ultrasound, computed tomography, and magnetic resonance imaging examinations all indicated a space-occupying lesion in the uterine cavity, and initially was considered endometrial carcinoma. Subsequently, total hysterectomy combined with bilateral salpingo-oophorectomy, pelvic lymphadenectomy, and para-aortic lymphadenectomy were performed. The coexistence of uterine adenosarcoma and endometrioid endometrial carcinoma was histologically confirmed postoperatively. The patient recovered well after surgery and was discharged on postoperative day 7. At a follow-up examination 10 months after surgery, we found no evidence of discomforting symptoms and recurrence or metastasis. Since the coexistence of uterine adenosarcoma and endometrial carcinoma is rare, it is easy to be overlooked the presence of uterine adenosarcoma on imaging or morphology, and thus be misdiagnosed as a more common disease, namely endometrial carcinoma. Observing the cystic structure within the lesion on magnetic resonance imaging is helpful for the diagnosis of uterine adenosarcoma. This article summarizes the imaging characteristics, clinicopathological features, molecular correlation, treatment, and prognosis of the disease.

DC-UNet: Looking for follicles in the ovarian ultrasound images

The auspicious initiation of human reproduction starts by releasing the ovum through ovulation within the ovary. Ceaseless monitoring of the female reproductive organs has now become essential for combating fertility-related issues and for successful assisted reproduction. Cases of infertility and demands for assisted reproduction in our modern liberated society are rapidly increasing. External or Transvaginal ultrasound imaging of the ovary provides us with vital information about the number, size, and position of the follicles in the ovary and their cumulative response to biological stimuli. Manual screening of thousands of USG images having lacs of follicles is an extremely strenuous job and prone to humane error. This paper propounded a new deep-learning architecture named Double Contraction-UNet (DC-UNet) which makes follicle segmentation fully automatic. This model restructured the U-Net architecture by introducing two contracting paths to segment the follicular object with higher accuracy. The model was trained and tested on approximately forty two thousand annotated ovarian 2D ultrasonography images extracted from USOVA3D Training Set 1. The proposed model outperforms the other U-Net-based state-of-the-art models when trained and tested on the same dataset. The proposed model has achieved an accuracy rate of 97.82%, a precision rate of 97.54%, a Recall value of 94.34%, an F1 Score of 95.91%, a Dice Score of 0.76, and a Jaccard Similarity Index of 0.59.

Optimizing evaluation of endometrial receptivity in recurrent pregnancy loss: a preliminary investigation integrating radiomics from multimodal ultrasound via machine learning.

Recurrent pregnancy loss (RPL) frequently links to a prolonged endometrial receptivity (ER) window, leading to the implantation of non-viable embryos. Existing ER assessment methods face challenges in reliability and invasiveness. Radiomics in medical imaging offers a non-invasive solution for ER analysis, but complex, non-linear radiomic-ER relationships in RPL require advanced analysis. Machine learning (ML) provides precision for interpreting these datasets, although research in integrating radiomics with ML for ER evaluation in RPL is limited. To develop and validate an ML model that employs radiomic features derived from multimodal transvaginal ultrasound images, focusing on improving ER evaluation in RPL. This retrospective, controlled study analyzed data from 346 unexplained RPL patients and 369 controls. The participants were divided into training and testing cohorts for model development and accuracy validation, respectively. Radiomic features derived from grayscale (GS) and shear wave elastography (SWE) images, obtained during the window of implantation, underwent a comprehensive five-step selection process. Five ML classifiers, each trained on either radiomic, clinical, or combined datasets, were trained for RPL risk stratification. The model demonstrating the highest performance in identifying RPL patients was selected for further validation using the testing cohort. The interpretability of this optimal model was augmented by applying Shapley additive explanations (SHAP) analysis. Analysis of the training cohort (242 RPL, 258 controls) identified nine key radiomic features associated with RPL risk. The extreme gradient boosting (XGBoost) model, combining radiomic and clinical data, demonstrated superior discriminatory ability. This was evidenced by its area under the curve (AUC) score of 0.871, outperforming other ML classifiers. Validation in the testing cohort of 215 subjects (104 RPL, 111 controls) confirmed its accuracy (AUC: 0.844) and consistency. SHAP analysis identified four endometrial SWE features and two GS features, along with clinical variables like age, SAPI, and VI, as key determinants in RPL risk stratification. Integrating ML with radiomics from multimodal endometrial ultrasound during the WOI effectively identifies RPL patients. The XGBoost model, merging radiomic and clinical data, offers a non-invasive, accurate method for RPL management, significantly enhancing diagnosis and treatment.

AI-based automated segmentation for ovarian/adnexal masses and their internal components on ultrasound imaging.

Segmentation of ovarian/adnexal masses from surrounding tissue on ultrasound images is a challenging task. The separation of masses into different components may also be important for radiomic feature extraction. Our study aimed to develop an artificial intelligence-based automatic segmentation method for transvaginal ultrasound images that (1)outlines the exterior boundary of adnexal masses and (2)separates internal components. A retrospective ultrasound imaging database of adnexal masses was reviewed for exclusion criteria at the patient, mass, and image levels, with one image per mass. The resulting 54 adnexal masses (36 benign/18 malignant) from 53 patients were separated by patient into training (26 benign/12 malignant) and independent test (10 benign/6 malignant) sets. U-net segmentation performance on test images compared to expert detailed outlines was measured using the Dice similarity coefficient (DSC) and the ratio of the Hausdorff distance to the effective diameter of the outline ( ) for each mass. Subsequently, in discovery mode, a two-level fuzzy c-means (FCM) unsupervised clustering approach was used to separate the pixels within masses belonging to hypoechoic or hyperechoic components. The DSC (median [95% confidence interval]) was 0.91 [0.78, 0.96], and was 0.04 [0.01, 0.12], indicating strong agreement with expert outlines. Clinical review of the internal separation of masses into echogenic components demonstrated a strong association with mass characteristics. A combined U-net and FCM algorithm for automatic segmentation of adnexal masses and their internal components achieved excellent results compared with expert outlines and review, supporting future radiomic feature-based classification of the masses by components.

Deep learning-based automated measurement of cervical length in transvaginal ultrasound images of pregnant women.

Cervical length (CL) measurement using transvaginal ultrasound is an effective screening tool to assess the risk of preterm birth. An adequate assessment of CL is crucial, however, manual sonographic CL measurement is highly operator-dependent and cumbersome. Therefore, a reliable and reproducible automatic method for CL measurement is in high demand to reduce inter-rater variability and improve workflow. Despite the increasing use of artificial intelligence techniques in ultrasound, applying deep learning (DL) to analyze ultrasound images of the cervix remains a challenge due to low signal-to-noise ratios and difficulties in capturing the cervical canal, which appears as a thin line and with extremely low contrast against the surrounding tissues. To address these challenges, we have developed CL-Net, a novel DL network that incorporates expert anatomical knowledge to identify the cervix, similar to the approach taken by clinicians. CL-Net captures anatomical features related to CL measurement, facilitating the identification of the cervical canal. It then identifies the cervical canal and automatically provides reproducible and reliable CL measurements. CL-Net achieved a success rate of 95.5% in recognizing the cervical canal, comparable to that of human experts (96.4%). Furthermore, the differences between the CL measurements of CL-Net and ground truth were considerably smaller than those made by non-experts and were comparable to those made by experts (median 1.36 mm, IQR 0.87-2.82 mm, range 0.06-6.95 mm for straight cervix; median 1.31 mm, IQR 0.61-2.65 mm, range 0.01-8.18 mm for curved one).

From Imaging to Visualization: Seeing the Future of Endometriosis Care

ObjectiveTo describe how the knowledge from standard imaging practices can be translated into three-dimensional visualization techniques and utilized in the surgical planning and management of endometriosis. SettingTertiary care academic centre. ParticipantsTwo case studies of patients with endometriosis are described. InterventionsTransvaginal ultrasound (1), magnetic resonance imaging, three-dimensional printing (2), and three-dimensional virtual reality modeling (3) were utilized during patient workup and preparation. Three-dimensional modeling was performed by a virtual reality technician and verified for accuracy by a fellowship trained radiologist. Surgical management for endometriosis was performed. ConclusionWhile expert transvaginal ultrasound and/or magnetic resonance imaging suffice for the majority of cases, three-dimensional printing and virtual reality modeling are a novel adjunct to standard imaging modalities. Rendering two-dimensional images into a three-dimensional representation allows users to interact with the anatomy and is particularly useful when distorted by complex pathology. These techniques contributed to improved patient understanding and experience, and helped medical learners better grasp regular imaging techniques and its translation to pelvic anatomy. Last, it augmented surgeon comprehension of the relationship between the pelvic structures, allowing for enhanced surgical planning and intraoperative decision making. Further study is being performed to quantify these effects.

The importance of the 'uterine factor' in recurrent pregnancy loss: a retrospective cohort study on women screened through 3D transvaginal ultrasound.

What is the prevalence of congenital and acquired anomalies of the uterus in women with recurrent pregnancy loss (RPL) of unknown etiology examined using 3D transvaginal ultrasound (US)? Depending on the adopted diagnostic criteria, the prevalence of partial septate uterus varies between 7% and 14% and a T-shaped uterus is 3% or 4%, while adenomyosis is 23%, at least one of type 0, type 1 or type 2 myoma is 4%, and at least one endometrial polyp is 4%. ESHRE and the Royal College of Obstetricians and Gynaecologists guidelines on RPL recommend the adoption of the 3D transvaginal US to evaluate the 'uterine factor'. Nevertheless, there are no published studies reporting the prevalence of both congenital and acquired uterine anomalies as assessed by 3D transvaginal US and diagnosed according to the criteria proposed by the most authoritative panels of experts in a cohort of women with RPL. This was a retrospective cohort study including 442 women with at least two previous first-trimester spontaneous pregnancy losses (i.e. non-viable intrauterine pregnancies), who referred to the obstetrics and gynecology unit of two university hospitals between July 2020 and July 2023. Records of eligible women were reviewed. Women could be included in the study if: they were between 25 and 42 years old; they had no relevant comorbidities; they were not affected by infertility, and they had never undergone ART; they and their partner tested negative to a comprehensive RPL diagnostic work-up; and they had never undergone metroplasty, myomectomy, minimally invasive treatments for uterine fibroids or adenomyomectomy. Expert sonographers independently re-analyzed the stored 2- and 3D transvaginal US images of all included patients. Congenital uterine anomalies (CUAs) were reported according to the American Society for Reproductive Medicine (ASRM) 2021, the ESHRE/European Society for Gynaecological Endoscopy (ESGE) and the Congenital Uterine Malformation by Experts (CUME) criteria. Acquired uterine anomalies were reported according to the International Federation of Gynecology and Obstetrics (FIGO) and the Morphological Uterus Sonographic Assessment (MUSA) criteria. The partial septate uterus was diagnosed in 60 (14%; 95% CI: 11-17%), 29 (7%; 95% CI: 5-9%), and 47 (11%; 95% CI: 8-14%) subjects, according to the ESHRE/ESGE, the ASRM 2021, and the CUME criteria, respectively. The T-shaped uterus was diagnosed in 19 women (4%; 95% CI: 3-7%) according to the ESHRE/ESGE criteria and in 13 women (3%; 95% CI: 2-5%) according to the CUME criteria. The borderline T-shaped uterus (diagnosed when two out of three CUME criteria for T-shaped uterus were met) was observed in 16 women (4%; 95% CI: 2-6%). At least one of FIGO type 0, type 1, or type 2 myoma was detected in 4% of included subjects (95% CI: 3-6%). Adenomyosis was detected in 100 women (23%; 95% CI: 19-27%) and was significantly more prevalent in women with primary RPL and in those with three or more pregnancy losses. At least one endometrial polyp was detected in 4% of enrolled women (95% CI: 3-7%). The absence of a control group prevented us from investigating the presence of an association between both congenital and acquired uterine anomalies and RPL. Second, the presence as well as the absence of both congenital and acquired uterine anomalies detected by 3D US was not confirmed by hysteroscopy. Finally, the results of the present study inevitably suffer from the intrinsic limitations of the adopted classification systems. The prevalence of CUAs in women with RPL varies depending on the classification system used. For reasons of clarity, the US reports should always state the name of the uterine anomaly as well as the adopted classification and diagnostic criteria. Adenomyosis seems to be associated with more severe forms of RPL. The prevalence rates estimated by our study as well as the replicability of the adopted diagnostic criteria provide a basis for the design and sample size calculation of prospective studies. No specific funding was used. The authors have no conflicts of interest to declare. N/A.

Bidirectional Copy-Paste Mamba for Enhanced Semi-Supervised Segmentation of Transvaginal Uterine Ultrasound Images.

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.

High-Fidelity Simulation with Transvaginal Ultrasound in the Emergency Department.

Intern and junior emergency medicine residents. Abdominal pain and vaginal bleeding in the first trimester of pregnancy are common presentations to the emergency department (ED).1 Formal transvaginal ultrasound (TVUS) is considered the test of choice for evaluation of first trimester pregnancy due to its high sensitivity and specificity for identifying intrauterine and ectopic pregnancies.1 Additionally, TVUS can evaluate for various uterine and ovarian pathology as well as identify other non-gynecologic conditions and is within the scope of practice for the emergency physician.2 Given the emergent and time sensitive nature of certain obstetric and gynecologic conditions, formal transvaginal ultrasound imaging may not be feasible. A rapid assessment with transvaginal point-of-care ultrasound (TVPOCUS) can be utilized by emergency medicine physicians (EMP) to confirm intrauterine pregnancies (IUP) and identify any associated complications. There are multiple advantages to TVPOCUS including reduced cost and length of stay, patient satisfaction, and improved resource utilization.1,3 Additionally, multiple studies demonstrate that EMPs can learn this skill and perform TVPOCUS accurately and safely.1,3 Developing the skills and comfort with TVPOCUS in a simulation setting during residency is beneficial and can have important implications in future practice. By the end of the session, learners should be able to 1) recognize the clinical indications for transvaginal ultrasound in the ED, 2) practice the insertion, orientation, and sweeping motions used to perform a TVPOCUS study, 3) interpret transvaginal ultrasound images showing an IUP or alternative pathologies, and 4) understand proper barrier, disinfection, and storage techniques for endocavitary probes. This session included three high-fidelity simulation cases that allowed participants to utilize TVPOCUS in a safe and conducive environment. There was a total of 32 emergency medicine (EM) residents who participated. The simulation sessions were divided into two separate rooms and included four learners for each session that actively managed the patient, for a total of 12 active participants. The 20 remaining residents were observers. Participants learned evidence-based indications, performance, and interpretation of transvaginal ultrasound. Three cases were reviewed and included IUP, ruptured ectopic pregnancy with hemorrhagic shock, and appendicitis in pregnancy. The cases were followed by a debriefing session and discussion regarding the evidence behind bedside transvaginal ultrasound, its incorporation into EM workflow, and practice-based learning. The educational content and efficacy were evaluated by oral feedback in a debriefing session after the workshop. Additionally, pre-simulation and post-simulation surveys were sent to participants to assess prior ultrasound experience and confidence on the indications, performance, and interpretation of transvaginal ultrasound. Responses were collected using a Likert scale of 1 to 5, with 1 being "not at all confident" and 5 being "very confident." Ten learners responded to the survey consisting of EM residents in a three-year EM residency program. Prior to the workshop, the median reported confidence level across all questions was "1- not at all confident" for the PGY-1 class, and "3-neutral" for the PGY-2 and PGY-3 classes. Following the workshop, all median scores across all classes were "4-confident," demonstrating an increase in confidence scoring across all measurements and participants. Incorporating transvaginal ultrasound into clinical workflow demonstrated the largest increase in confidence score (median 1.5 to 4), followed by insertion/orientation of the endocavitary probe (median 2.5 to 5). This high-fidelity simulation familiarized learners with transvaginal ultrasound and how it can be appropriately utilized for a variety of high-yield clinical scenarios that present regularly to the ED. Given the variation in ultrasound training among residency programs, and the lack of specific simulation content addressing this modality, it is important to implement scenarios that improve learner comfort with TVPOCUS. Overall, this workshop resulted in an increase in confidence scores of participants in the indication, performance, and interpretation of TVPOCUS in the ED. Transvaginal ultrasound, POCUS, intrauterine pregnancy, ectopic pregnancy, hemorrhagic shock, appendicitis in pregnancy, abdominal pain, emergency medicine.

The Impact of Maternal BMI on Time of Transvaginal Cervical Imaging

Introduction: Ultrasound is an integral part of obstetrical care and obesity has been shown to decrease the accuracy of ultrasound examination in high-risk pregnancy (Tsai et al, 2015). Obesity decreases the fidelity of ultrasound, as decreased visualization is seen with increasing depth of abdominal adipose tissue (Paladini, 2009). While maternal obesity has been shown to detrimentally impact anatomical ultrasound, the effects of obesity on the performance of transvaginal ultrasound are unclear. Our aim was to evaluate if obesity has an effect on the time required to obtain transvaginal cervical length. Methods: Retrospective chart review between January 2016-January 2022 identified patients with cervical shortening (&lt;2.5 cm) at the time of mid-trimester anatomical ultrasound scans. Scans were performed at the Maternal Fetal Medicine Department at Promedica Toledo Hospital between 16- and 24-weeks gestation. Patient BMI was recorded at the time of ultrasound and divided into obese (BMI ≥ 30 kg/m²) and non-obese (BMI ≤ 30 kg/m²) categories. Time to complete transvaginal ultrasound imaging was recorded in both patient populations and compared. Results: 216 patients met study criteria. Out of the 216, 89 (41%) were obese and 127 (59%) were non-obese. Average BMI of all participants was 29.2 ± 7.4 kg/m². Average time spent on ultrasound for patients with BMI &lt;30 was 13:36 ± 01:28 and for BMI &gt;30 15:34 ± 01:48 (p=0.46). There was no statistical difference between obese and non-obese patients and transvaginal scanning time &gt; 10 minutes (OR 1.24, 95% CI 0.719-2.13, p=0.44) Discussion: Our results suggest that the time to obtain cervical length measurements via transvaginal ultrasounds is similar between obese and non-obese patients. Time necessary to perform endovaginal ultrasonography of the cervix does not appear to be affected by maternal BMI. Since length of time necessary to complete transvaginal cervical length measurement does not appear to be affected by maternal BMI, our results suggest that additional scheduling time does not need to be allocated for obese patients. Other investigators have shown that early incorporation of transvaginal assessment of fetal anatomy in obese women improved the rate of survey completion and demonstrated earlier completion of the fetal anatomic evaluation (Toscano et al, 2021). This study encourages the further use of transvaginal ultrasound in obese, obstetrical patients.

Feasibility of Intraoperative Proctosigmoidoscopy After Discoid Bowel Resection for Deep Infiltrating Endometriosis: A Pilot Multicenter Study

Although surgery is the gold standard treatment for pain refractory to medical management or partial occlusion owing to rectosigmoid endometriosis, surgical resection can be associated with major perioperative complications. From general surgery experience, intraoperative proctosigmoidoscopy has shown encouraging results as a feasible, safe, and effective technique in reducing the risk of complications related to intestinal anastomosis after segmental resection. Unfortunately, there are no studies evaluating its role after discoid resection for rectosigmoid endometriosis. A pilot, multicentric, observational, prospective, cohort study. Two academic hospitals, from March 1 to December 31, 2022. We enrolled all consecutive fertile-age patients affected by symptomatic endometriosis scheduled for laparoscopic discoid bowel resection. Inclusion criteria were (1) age between 18 and 50 years, (2) diagnosis of rectosigmoid endometriosis performed by transvaginal ultrasound and/or magnetic resonance imaging, and (3) women scheduled for laparoscopic discoid bowel resection of endometriosis at low risk of segmental resection. During data analysis, enrolled patients were divided into 2 study groups for comparisons based on whether or not the intraoperative proctosigmoidoscopy was performed upon surgeons' discretion after discoid resection for treating endometriosis, in addition to standard integrity tests. Primary outcome was the rate of intraoperative proctosigmoidoscopy success. Secondary study outcomes were the differences between the intraoperative proctosigmoidoscopy group and the nonintraoperative proctosigmoidoscopy group in (1) mean of total operative time and (2) rate of perioperative complications. A total of 28 patients were enrolled and equally distributed in the 2 groups. The rate of intraoperative proctosigmoidoscopy success was 86%. No significant difference was reported between the 2 groups in terms of total operative time (p = .1) and intraoperative and postoperative complications (p = .5 and p = 1, respectively), with no surgical complication related to intraoperative proctosigmoidoscopy. Intraoperative proctosigmoidoscopy seems as a feasible and non-time-consuming intraoperative procedure in women undergone discoid resection for rectosigmoid endometriosis. Larger studies with longer follow-up period are necessary to confirm our findings and assess clinical benefits over standard procedure.

Comparison of Myometrial Invasion Depth Examination Methods in Endometrial Cancer

Background: Endometrial cancer (EC) is often presents in the postmenopausal period. Among the risk elements are obesity, early menarche, late menopause, unopposed estrogen exposure associated with nulliparity, diabetes, advanced age (&gt;55 years), and tamoxifen use. Endometrial biopsy is the gold standard diagnostic method. The typical surgical process comprises a complete removal of the uterus, a bilateral salpingo-oophorectomy, and cytological examination of peritoneal washing. Invasion of the myometrium (MI) is intricately linked to lymph node metastasis, which is observed in approximately 20% of deep MI cases and in 5% of cases with superficial MI. Therefore, a comprehensive assessment of women with EC, especially those with MI, is important before treatment. The assessment for myometrial invasion (MI) and cervical stromal invasion often involves the use of transvaginal ultrasound (TVUS). The diagnostic accuracy of TVUS varies in reported studies, and some findings are comparable to those obtained through magnetic resonance imaging (MRI). The size of intraoperative tumors and MI is provided to surgeons by frozen section examination, offering crucial information. This study aimed to compare the preoperative TVUS and MRI findings, intraoperative frozen sections, and postoperative final results for 321 patients diagnosed with EC. Methods: Individuals who underwent surgery at the third-stage tertiary gynecologic-oncology clinic for EC were included in the study. The study excluded cases lacking preoperative biopsy, TVUS, and magnetic resonance imaging (MRI), as well as cases featuring obvious extrauterine lesions. Non-endometrioid cases, endometrial hyperplasia, and cases with an identification of organ involvement outside the uterus during surgery were also excluded. The TVUS and MRI findings were compared with the intraoperative frozen sections using McNemar’s test. The concordance of the assessments was determined using the kappa coefficient. The statistical significance level, represented by alpha (α), was set at p &lt; 0.05. Results: The sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and kappa values for TVUS were 100%, 94.3%, 21.7%, 100%, and 0.34, respectively. For MRI, these values were 100%, 97.8%, 41.7%, 100%, and 0.579, and for frozen section, they were 100%, 99.7%, 83.3%, 100%, and 0.908, respectively. Conclusions: In addition to the gold standard frozen section, TVUS and MRI played an important preoperative role in determining the depth of invasion. While MRI is expensive, TVUS stands out for its practical nature and easy accessibility. In the preoperative examination, TVUS provided acceptable results in guiding intraoperative decisions for lymphadenectomy, with similar sensitivity to MRI and frozen sections.