PDF(901 KB)
PDF(901 KB)
PDF(901 KB)
宫腔镜技术的现状与展望
Situation and prospect of hysteroscopic technique
经历了200年的发展,现代宫腔镜技术以阴道内镜技术为划时代的变化,开创了门诊宫腔镜“即诊即治”的理念,国际上各大协会的严格培训制度使宫腔镜的普及更为安全和有效。未来的宫腔镜包括数字化宫腔镜、三维宫腔镜、机器人宫腔镜和人工智能(AI)技术辅助的宫腔镜。宫腔镜技术作为妇科内镜技术的一个亚专科,因其良好的视觉效果、令人满意的诊疗结果,其检查结果成为了诊断子宫内病变的金标准。
After 200 years of development,modern hysteroscopy technology,with vaginoscopic technology as a groundbreaking change,has pioneered the concept of“see and treatment”for outpatient hysteroscopy.The strict training system of major international associations has made hysteroscopy safer and more effective in its popularization.Future hysteroscopy include digital hysteroscopy,3D hysteroscopy,robotic hysteroscopy,and AI-assisted hysteroscopy.Hysteroscopy,as a sub-specialty of gynecological endoscopy,has become the gold standard for intrauterine lesions due to its excellent visual effects and satisfactory diagnosis and treatment results.
| [1] |
|
| [2] |
|
| [3] |
|
| [4] |
|
| [5] |
|
| [6] |
|
| [7] |
The aim of this study was to evaluate treatment efficacy and patient acceptability of a new bipolar probe used during office hysteroscopic treatment of benign intrauterine pathologies.In this observational clinical study, 501 women were treated for benign intrauterine pathologies using an office hysteroscopic procedure, without analgesia or anaesthesia. A Versapoint 5 Fr. bipolar electrical generator was used to treat endometrial polyps ranging between 0.5 and 4.5 cm, as well as submucosal and partially intramural myomas between 0.6 and 2.0 cm. Treatment efficacy and patient compliance were evaluated.At follow-up, the uterine cavity was normal in all patients without any recurrence or persistence of the pathology. One focal adenocarcinoma was discovered at histology in an endometrial polyp of a menopausal patient. Patient acceptance was satisfactory; 47.6-79.3% of the patients underwent the procedure without discomfort.The combination of a new generation small diameter hysteroscope and a new bipolar 5 Fr. electrode enables the gynaecologist to treat intrauterine pathologies in an office setting without anaesthesia. Experimentation of a special set-up of the electrical generator reduced patient discomfort during the operative part of the hysteroscopic procedure.
|
| [8] |
李奇迅, 徐云, 郭蕾, 等. 阴道内镜技术在宫腔镜检查中的临床应用研究[J]. 中国实用妇科与产科杂志, 2017, 33(1):118-121.DOI: 10.19538/j.fk2017010128.
|
| [9] |
张浩, 魏莉, 冯力民. 阴道内镜技术中国专家推荐意见[J]. 中国医刊, 2022, 57(2):129-133.DOI: 10.3969/j.issn.1008-1070.2022.02.004.
|
| [10] |
|
| [11] |
Changes in hysteroscopic capabilities have been preceded by technological advances that have enabled them. Modern operative hysteroscopes rely on a variety of different-sized optical, inflow, outflow, and working channels to enable clear visualization of the endometrial cavity as well as the surgical removal of intracavitary lesions such as polyps and myomas. This review examines the relative merits of various hysteroscopic treatment options with a focus on the most recent operative hysteroscopic technique, hysteroscopic morcellation, and how this new technology fits into the armamentarium of the gynecologist.
|
| [12] |
To evaluate whether hysteroscopic morcellation or bipolar electrosurgical resection is more favorable for removing endometrial polyps in an office setting in terms of feasibility, speed, pain, and acceptability.A multicenter, single-blind, randomized, controlled trial of office hysteroscopic morcellation compared with electrosurgical resection was conducted. A total of 121 women were randomly allocated to polyp removal by one of the two methods in an office setting. The outcomes assessed were time taken to complete the endometrial polypectomy, defined as the time from insertion to removal of vaginal instrumentation, completeness of polyp removal, acceptability, and pain measured on a 100-mm visual analog scale.The median time taken to complete the procedure was 5 minutes and 28 seconds for morcellation compared with 10 minutes and 12 seconds for electrosurgical resection (P<.001). The polyps were completely removed in 61 out of 62 (98%) women assigned to morcellation compared with 49 out of 59 (83%) women treated with electrosurgical resection (odds ratio 12.5; 95% confidence interval [CI] 1.5-100.6; P=.02). The mean pain scores during the procedure favored morcellation by 16.1 points on average (35.9 compared with 52.0; 95% CI for difference, -24.7 to -7.6; P<.001). Overall, 99% of women found office polypectomy to be acceptable, with only one woman in the electrosurgical resection group considering the procedure unacceptable.In comparison to electrosurgical resection during hysteroscopic polypectomy, morcellation was significantly quicker, less painful, more acceptable to women, and more likely to completely remove endometrial polyps compared with electrosurgical resection.ClinicalTrials.gov, www.clinicaltrials.gov, NCT01509313.
|
| [13] |
|
| [14] |
This randomized, double blind, placebo-controlled study compared the usefulness of danazol 400mg vaginally versus 600mg orally in women as a preoperative preparation for hysteroscopic surgery. Ninety-one fertile women were randomly allocated to Group A (46 patients received 400mg of danazol placed into the posterior vaginal fornix and three oral tablets of commercially available folic acid as a placebo), and Group B [45 women treated with 600mg of danazol orally (200mg three times daily) and two vaginal tablets of Lactobacillus rhamnosus as a placebo]. The patients underwent an operative hysteroscopy, transvaginal sonography, blood tests, and a histological assay. A visual analog scale (VAS) score to compute the degree of the surgeon's satisfaction was used. The outcome measures were as follows: an evaluation of the changes in the endometrial thickness, the prevalence of endometrial atrophy, changes in the blood tests, any collateral effects, the degree of difficulty and view, the duration of the surgical procedure, any complications during the operative hysteroscopy and associated side effects, and the surgeon's satisfaction with the endometrial preparation. The vaginal administration route was associated with a more pronounced effect on the endometrial thickness. Significantly more patients receiving vaginal danazol (45/46) had a hypotrophic endometrium than those receiving oral danazol (37/45, P<0.01). In addition, the patients receiving danazol vaginally had a shorter operating time, lower infusion volume, fewer side effects, and a higher surgeon satisfaction. Vaginal danazol adequately prepares the endometrium for an operative hysteroscopy by thinning the endometrium effectively with few side effects and little impact on the metabolic parameters.Copyright © 2012 Elsevier Inc. All rights reserved.
|
| [15] |
Operative hysteroscopy in a hospital setting has revolutionized surgical treatment of benign uterine disorders. It is minimally invasive, cost‐ and time‐effective, and may spare patients major surgical interventions. Operative hysteroscopy in a day‐case hospital setting is regarded as a safe and well‐tolerated procedure with low complication rates. However, prevention of adverse events is crucial in daily practice to optimize patient care. Complications in operative hysteroscopy can be divided into early complications, including bleeding, uterine perforation, infection and fluid overload, or late complications and suboptimal outcomes, such as incomplete resection and intrauterine adhesions. Awareness and knowledge of management of adverse events as well as the use of possible preventative measures will increase the quality and safety of hysteroscopic surgery. The present commentary focuses on these issues as an up‐to‐date basis for everyday clinical practice.
|
| [16] |
|
| [17] |
The success rate of in-vitro fertilisation (IVF) remains low and many women undergo multiple treatment cycles. A previous meta-analysis suggested hysteroscopy could improve outcomes in women who have had recurrent implantation failure; however, studies were of poor quality and a definitive randomised trial was needed. In the TROPHY trial we aimed to assess whether hysteroscopy improves the livebirth rate following IVF treatment in women with recurrent failure of implantation.We did a multicentre, randomised controlled trial in eight hospitals in the UK, Belgium, Italy, and the Czech Republic. We recruited women younger than 38 years who had normal ultrasound of the uterine cavity and history of two to four unsuccessful IVF cycles. We used an independent web-based trial management system to randomly assign (1:1) women to receive outpatient hysteroscopy (hysteroscopy group) or no hysteroscopy (control group) in the month before starting a treatment cycle of IVF (with or without intracytoplasmic sperm injection). A computer-based algorithm minimised for key prognostic variables: age, body-mass index, basal follicle-stimulating hormone concentration, and the number of previous failed IVF cycles. The order of group assignment was masked to the researchers at the time of recruitment and randomisation. Embryologists involved in the embryo transfer were masked to group allocation, but physicians doing the procedure knew of group assignment and had hysteroscopy findings accessible. Participants were not masked to their group assignment. The primary outcome was the livebirth rate (proportion of women who had a live baby beyond 24 weeks of gestation) in the intention-to-treat population. The trial was registered with the ISRCTN Registry, ISRCTN35859078.Between Jan 1, 2010, and Dec 31, 2013, we randomly assigned 350 women to the hysteroscopy group and 352 women to the control group. 102 (29%) of women in the hysteroscopy group had a livebirth after IVF compared with 102 (29%) women in the control group (risk ratio 1·0, 95% CI 0·79-1·25; p=0·96). No hysteroscopy-related adverse events were reported.Outpatient hysteroscopy before IVF in women with a normal ultrasound of the uterine cavity and a history of unsuccessful IVF treatment cycles does not improve the livebirth rate. Further research into the effectiveness of surgical correction of specific uterine cavity abnormalities before IVF is warranted.European Society of Human Reproduction and Embryology, European Society for Gynaecological Endoscopy.Copyright © 2016 Elsevier Ltd. All rights reserved.
|
| [18] |
|
| [19] |
李奇迅, 徐云, 郭蕾, 等. 改良子宫内膜采集器在阴道内镜下的临床应用[J]. 中国妇产科临床杂志, 2017, 18(2):134-136.DOI: 10.13390/j.issn.1672-1861.2017.02.012.
 目的 评价改良子宫内膜采集器联合阴道内镜检查诊断子宫内膜病变的临床应用价值。方法 2015年5月至2015年10月对74例可疑宫腔病变患者应用改良子宫内膜采集器(改良采集器组)通过阴道内镜检查评估宫腔状态后采集子宫内膜组织送病理学检查,并与宫腔镜检查定位诊断性刮宫(诊刮组)结果进行比较。结果 子宫内膜采集器及宫腔镜定位诊断性刮宫标本满意率均为94.59%(70/74)。74例患者中,改良采集器组确诊为子宫内膜恶性病变7例,其特异度为98.41%(62/63),灵敏度为63.64%(7/11),诊刮组确诊为子宫内膜恶性病变11例,两种方法的符合率为93.24%(69/74),Kappa值为0.699,ROC曲线下面积为0.810。结论 使用改良子宫内膜采集器可在阴道内镜检查后直接进行内膜活检,并且可获取较满意标本。
|
| [20] |
To compare three types of biopsy forceps for hysteroscopic endometrial biopsy in postmenopausal women.
|
| [21] |
|
| [22] |
To propose a new classification system (Urman‐Vitale Classification System) for intrauterine adhesions (IUAs) and to evaluate anatomical and fertility outcomes after hysteroscopic adhesiolysis accordingly.
|
| [23] |
Background: Hysteroscopic septum dissection (HSD) is thought to improve fertility and pregnancy outcomes. However, the available literature suggests that uterine surgery can cause placental abnormalities in subsequent pregnancies. Methods: A case–control study was performed at the University Medical Center of Ljubljana, Department of Human Reproduction, from 1 January 2016 to 31 December 2018. The primary outcome was the association between HSD and the occurrence of placental abnormalities. We included women who underwent HSD due to infertility. Age-matched women who underwent hysteroscopic surgery for other issues were considered as controls. In addition, we divided the groups according to conception method. Only singleton pregnancies and first delivery were considered. Results: A total of 1286 women (746 who underwent HSD and 540 controls) were included in the analysis. HSD had no influence on placental abnormalities since the ratio was comparable regardless of the method of conception (113/746 vs. 69/540; p = 0.515). Infertile women who conceived naturally after HSD had a normal placentation rate comparable to women who did not undergo HSD (380/427 vs. 280/312; p = 0.2104). The rate of placental abnormalities in women who achieved pregnancy with IVF/ICSI procedures following HSD was comparable to that of women who did not undergo HSD (52/319 vs. 33/228; p = 0.5478). Placenta previa occurred significantly more often in infertile women without HSD after IVF/ICSI compared to natural conception (2/312 vs. 7/228; p = 0.0401). Conclusions: HSD was not associated with higher rate of placental abnormalities in the first singleton pregnancy compared with other hysteroscopic procedures. A higher rate of placenta previa in pregnancies following IVF/ICSI procedures, which was shown by our research, is corroborated by previous research findings.
|
| [24] |
The goal of this paper is to assess the concordance between the clinical diagnosis of Endometrial Hyperplasia (EH), suspected by senior gynecologists throughout outpatient office hysteroscopy, and the results from histopathological examination, in order to evaluate hysteroscopic accuracy for EH. A prospective cohort study was done at a Tertiary University Hospital. From January to December 2018, we enrolled women with the following criteria: abnormal uterine bleeding in post-menopause and endometrial thickening in pre-or post-menopause. Patients underwent office hysteroscopy with a 5 mm continuous-flow hysteroscope, and endometrial biopsies were taken using miniaturized instruments. Senior operators had to foresee histopathological diagnosis using a questionnaire. Histopathological examination was conducted to confirm the diagnosis. This study was approved by the local ethical and registered in the ClinicalTrials.gov registry (ID no. NCT03917147). In 424 cases, 283 clinical diagnoses of EH were determined by senior surgeons. A histopathological diagnosis was then confirmed in 165 cases (58.3%; p = 0.0001). Furthermore, 14 endometrial carcinoma and atypical hyperplasia were found. The sensitivity, positive predictive value, and negative predictive values for EH were, respectively, 90.4, 58.4, and 86.6%. Subdivided by clinical indication, the sensitivity was higher in patients with post-menopause endometrial thickening. The diagnostic accuracy of office hysteroscopy in the diagnosis and prediction of endometrial hyperplasia was high. Senior operators could foresee EHs in more than half the cases.
|
| [25] |
|
| [26] |
Introduction: This study aimed to assess the feasibility and efficacy of office hysteroscopy to diagnose and treat the specific uterine pathologies frequently diagnosed and thought to be associated with female infertility. Material and methods: Using office hysteroscopy, we examined the uterine cavity in women with primary or secondary infertility and evaluated the reproductive outcomes of those affected by one or more pathologies, including cervico-isthmic adhesions, intrauterine polyps and intrauterine adhesions. Additional patient characteristics considered were age and parity, uterine pathology, pain during hysteroscopy, and outcomes including spontaneous pregnancies achieved and time between treatment and pregnancy. Results: Reproductive outcomes of 200 patients affected by one or more uterine pathologies were evaluated. Cervico-isthmic adhesions were the most frequent findings in older women, with nearly 80% of them achieving pregnancy sooner than the others in our study. Spontaneous pregnancy rates following office hysteroscopy were 76%, 53% and 22% in women with cervico-isthmic adhesions, polyps (< 5 mm) and intrauterine adhesions, respectively. Conclusions: Office hysteroscopy is a feasible and highly effective diagnostic and therapeutic procedure for cervico-isthmic and intrauterine adhesions, as well as for small polyps, allowing the resolution of female infertility related to these pathologies, without trauma and with only minimal discomfort.
|
| [27] |
To analyze the cost‐effectiveness of virtual sonographic hysteroscopy (VSH) performed before in vitro fertilization (IVF) (Scenario 1), frozen embryo transfer (Scenario 2), and oocyte donation (Scenario 3) attempts.
|
| [28] |
|
| [29] |
In this case report we describe the first two surgeries conducted with the 19 Fr. IBS®. The indication for operative hysteroscopy in both patients was the removal of polyps. The size of the polyps was between 15 mm and 20 mm with a mean resection time of 40 seconds. Normal saline solution (500 ml) was used with a negative fluid loss (100 ml). Both operations were successfully performed under general anaesthesia and no speculum, no tenaculum and no dilatation of the cervical canal were necessary.
|
| [30] |
|
| [31] |
|
| [32] |
To describe the performance curve of hysteroscopy-naïve probands repeatedly working through a surgery algorithm on a hysteroscopy trainer.We prospectively recruited medical students to a 30min demonstration session teaching a standardized surgery algorithm. Subjects subsequently performed three training courses immediately after training (T1) and after 24h (T2) and 48h (T3). Skills were recorded with a 20-item Objective Structured Assessment of Technical Skills (OSATS) at T1, T2, and T3. The presence of a sustained OSATS score improvement from T1 to T3 was the primary outcome. Performance time (PT) and self assessment (SA) were secondary outcomes. Statistics were performed using paired T-test and multiple linear regression analysis.92 subjects were included. OSATS scores significantly improved over time from T1 to T2 (15.21±1.95 vs. 16.02±2.06, respectively; p<0.0001) and from T2 to T3 (16.02±2.06 vs. 16.95±1.61, respectively; p<0.0001). The secondary outcomes PT (414±119s vs. 357±88s vs. 304±91s; p<0.0001) and SA (3.02±0.85 vs. 3.80±0.76 vs. 4.41±0.67; p<0.0001) also showed an improvement over time with quicker performance and higher confidence. SA, but not PT demonstrated construct validity. In a multiple linear regression analysis, gender (odds ratio (OR) 0.96; 95% confidence interval (CI) 0.35-2.71; p=0.9) did not independently influence the likelihood of OSATS score improvement.In a hysteroscopy-naïve population, there is a continuous and sustained improvement of surgical proficiency and confidence after multiple training courses on a hysteroscopy trainer. Serial hysteroscopy trainings may be helpful for teaching hysteroscopy skills.Copyright © 2014 Elsevier Ireland Ltd. All rights reserved.
|
| [33] |
|
| [34] |
Training in hysteroscopy can be challenging, especially in conscious women as an office procedure.To develop a realistic hysteroscopy training model for residents using human uteri.Human uterine specimens were acquired immediately after hysterectomy, before they were sent for histological analysis and were used as a training model for hysteroscopy.We describe this new technique, which we have used for one year in our resident training programme. Each resident performs at least 20 simulated diagnostic hysteroscopies in extirpated uteri, before performing procedures on women in the operating room.Simulating hysteroscopy on human uterine models offers a novel and realistic way of training novices prior to conducting procedures under supervision on live patients.This is a novel model for training and offers a much more realistic training opportunity.Copyright © 2020 Facts, Views & Vision.
|
| [35] |
Structured laparoscopic training courses are important in surgical education. Different programmes have been proposed, but there is currently no evidence available comparing the performance of specialists versus residents in Obstetrics and Gynaecology at these courses.To evaluate the impact of the laparoscopic component of Gynaecological Endoscopic Surgical Education and Assessment (GESEA) Training and Certification courses in two different populations.Prospective cohort study. Two groups were analysed - participants of the Residents' Courses and participants of the Annual Francophone GESEA Diploma Course. Both groups were evaluated using the GESEA Level 1 laparoscopic standardised exercises and carried out in the International Center of Endoscopic Surgery (CICE), Clermont Ferrand, France in 2019.57 French residents and 69 participants of the Annual GESEA Diploma were evaluated. The average age of participants in the Residents' Course was lower than those in the Annual Diploma Course (28.4±1.6 versus 35.2±8.0 years, p<0.001). Residents had higher previous experience in laparoscopic surgery (42% vs 36%, p< 0.001), in animal model surgery and in laparoscopic training box (67% vs 36% and 93% vs 67% respectively, p<0.001). Notable improvement was noted in both groups in the camera navigation exercise; first attempt 105±19 vs 117±9 seconds and final attempt 81±15 and 103±20 seconds respectively (p<0.001).Both groups improved significantly in most of the tests evaluated. French residents had better results in all evaluations, except in one aspect of the suture exercise (maintaining optimal results in performing the knot). After excluding the residents who attended the Annual Diploma Course, all the differences between both groups were statistically more significant.Copyright © 2020 Facts, Views & Vision.
|
| [36] |
Artificial intelligence and augmented reality have been progressively incorporated into our daily life. Technological advancements have resulted in the permeation of similar systems into medical practice.
|
| [37] |
|
| [38] |
|
| [39] |
|
| [40] |
This study aimed to evaluate characteristics of endometrial surveillance in women treated for breast cancer to build a clinical prediction model.A multicentric retrospective cohort study was conducted at two tertiary-care university hospitals from January 2020 to June 2023. Perimenopausal and postmenopausal women treated for breast cancer were categorized into two groups: patients with and without diagnosis of endometrial malignancy (endometrial carcinoma) or premalignancy (atypical endometrial hyperplasia). Characteristics of breast cancer and ultrasonographic and hysteroscopic examinations were compared. A prediction model for endometrial malignancy was built using logistic regression. Predictive accuracy was assessed using the receiver operating characteristic (ROC) curve and goodness of fit using the Hosmer-Lemeshow test.One hundred and thirty-two (28 with premalignancy or malignancy and 104 without malignancy) women were analyzed. A nomogram was produced for prediction model development utilizing the presence and duration in months of abnormal uterine (BL)eeding, ultrasound (US) vascular pattern and echogenicity and (H)ysteroscopic appearance of endometrium (BLUSH) as determined by logistic regression. Sensitivity and specificity were 79.17% and 95.19%, respectively, with an area under ROC curve of 0.965, indicating good accuracy. Good goodness of fit and prediction stability were indicated by the calibration curve and Hosmer-Lemeshow test ( = 26.36; = 0.999).Breast cancer survivors undergoing endometrial surveillance might benefit from a potentially useful prediction model based on hysteroscopic appearance, ultrasonographic uniformity of endometrium, Doppler flow and presence of abnormal uterine bleeding.
|
| [41] |
The primary aim was to analyze the current practices on the use of operative hysteroscopy for preserving fertility in patients diagnosed with endometrial cancer and premalignancies. Our secondary objectives included investigating medical therapy and analyzing reported pregnancy-related outcomes subsequent to fertility preservation procedures.We performed a semi-systematic literature review on PubMed, employing pertinent terms related to hysteroscopy, fertility preservation, and endometrial cancer and premalignancies. Patients undergoing operative hysteroscopy with or without following medical treatment were included. We adhered to the PRISMA 2020 statement and utilized Covidence software to manage our systematic review. We performed a pooled analysis on various outcomes.Our final analysis included 15 studies evaluating 458 patients, where 238 (52.0%) were diagnosed with endometrial cancer, and 220 (48.0%) had endometrial premalignancies. With 146 pregnancies in our study, the overall pregnancy rate was 31.9%. Among these, 97 resulted in live births, accounting for 66.4% of the reported pregnancies. In terms of medical treatment, various forms of progestins were reported. Complications or adverse effects related to operative hysteroscopy were not reported in more than half of the studies. Among those studies that did report them, no complications nor adverse effects were documented. After hysteroscopic resection, complete response to medical treatment has been reported in 65.5% of the overall cases.Our review sheds light on the contemporary landscape of operative hysteroscopy for fertility preservation in endometrial cancer and premalignancies. Future studies should include the integration of molecular classification into fertility-preserving management of endometrial malignancies to offer a more personalized and precise strategy.© 2024. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.
|
| [42] |
|
| [43] |
|
| [44] |
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.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.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.The VGGNet-16 model performs well in classifying endometrial lesions from hysteroscopic images and can provide objective diagnostic evidence for hysteroscopists.
|
| [45] |
|
| [46] |
李冰, 习开超, 高丽丽. 子宫内膜癌及子宫内膜不典型增生患者分子分型特征与宫腔镜治疗疗效和临床病理特征关系研究[J]. 中国实用妇科与产科杂志, 2024, 40(6):661-664.DOI: 10.19538/j.fk2024060118.
|
| [47] |
/
| 〈 |
|
〉 |