Artificial intelligence in imaging in the first trimester of pregnancy: a systematic review

INTRODUCTION

ultrasonography in the first trimester of pregnancy offers an early screening tool to identify high risk pregnancies. Artificial intelligence (AI) algorithms have the potential to improve the accuracy of diagnosis and assist the clinician in early risk stratification.

OBJECTIVE

to conduct a systematic review of the use of AI in ultrasonography in the first trimester of pregnancy.

METHODS

We conducted a systematic literature review by searching in computerised databases Pubmed, Embase and Google Scholar from inception to January 2024. Full text peer reviewed journal publications written in English on the evaluation of AI in first trimester pregnancy imaging were included. Review papers, conference abstracts, posters, animal studies, non-English and non-peer-reviewed articles were excluded. Risk of bias was assessed by using PROBAST.

RESULTS

Of the 1595 non-duplicated records screened, 27 studies were included. Twelve studies focussed on segmentation, eight on plane detection, six on image classification and one on both segmentation and classification. Five studies included fetuses with a gestational age of less than ten weeks. The size of the datasets was relatively small, as sixteen studies included less than 1000 cases. The models were evaluated by different metrics. Duration to run the algorithm was reported in twelve publications and ranged between less than one second and fourteen minutes. Only one study was externally validated.

CONCLUSION

Even though the included algorithms reported a good performance in a research setting on testing datasets, further research and collaboration between AI experts and clinicians is needed before implementation in clinical practice.

Migration of Intra-Uterine Devices

Intrauterine devices (IUDs) are a widely used contraceptive. Possible complications from IUDs include failed insertion, pain, vasovagal reaction, infection, abnormal bleeding, and expulsion. Uterine perforation and migration of the IUD are rare complications occurring in approximately 1-2 per 1000 insertions. We executed a systematic review by reviewing all case reports and case series on IUD migration, published between December 2002 and December 2022. Our review indicates that about half of these patients present with pain and that a third are completely asymptomatic. The most common sites of migration are the intestine, bladder, and omentum. We found that the preferred method for removing the migrated IUD is laparoscopy. Generally, there are no lasting injuries after the removal of the migrated IUD, but occasionally, severe complications have been reported. Healthcare providers should be vigilant about this rare complication, especially in cases of painful insertion or the presence of other risk factors for perforation. When uterine perforation is diagnosed, it is advisable to remove the IUD to prevent severe complications.

Management of Uterine Fibroids and Sarcomas: The Palermo Position Paper

BACKGROUND

Uterine fibroids are benign monoclonal tumors originating from the smooth muscle cells of the myometrium, constituting the most prevalent pathology within the female genital tract. Uterine sarcomas, although rare, still represent a diagnostic challenge and should be managed in centers with adequate expertise in gynecological oncology.

OBJECTIVES

This article is aimed to summarize and discuss cutting-edge elements about the diagnosis and management of uterine fibroids and sarcomas.

METHODS

This paper is a report of the lectures presented in an expert meeting about uterine fibroids and sarcomas held in Palermo in February 2023.

OUTCOME

Overall, the combination of novel molecular pathways may help combine biomarkers and expert ultrasound for the differential diagnosis of uterine fibroids and sarcomas. On the one hand, molecular and cellular maps of uterine fibroids and matched myometrium may enhance our understanding of tumor development compared to histologic analysis and whole tissue transcriptomics, and support the development of minimally invasive treatment strategies; on the other hand, ultrasound imaging allows in most of the cases a proper mapping the fibroids and to differentiate between benign and malignant lesions, which need appropriate management.

CONCLUSIONS AND OUTLOOK

The choice of uterine fibroid management, including pharmacological approaches, surgical treatment, or other strategies, such as high-intensity focused ultrasound (HIFU), should be carefully considered, taking into account the characteristics of the patient and reproductive prognosis.

Risk assessment for endometrial cancer in women with abnormal vaginal bleeding: Results from the prospective IETA-1 cohort study

OBJECTIVE

To investigate the association between personal history, anthropometric features and lifestyle characteristics and endometrial malignancy in women with abnormal vaginal bleeding.

METHODS

Prospective observational cohort assessed by descriptive and multivariable logistic regression analyses. Three features-age, body mass index (BMI; calculated as weight in kilograms divided by the square of height in meters), and nulliparity-were defined a priori for baseline risk assessment of endometrial malignancy. The following variables were tested for added value: intrauterine contraceptive device, bleeding pattern, age at menopause, coexisting diabetes/hypertension, physical exercise, fat distribution, bra size, waist circumference, smoking/drinking habits, family history, use of hormonal/anticoagulant therapy, and sonographic endometrial thickness. We calculated adjusted odds ratio, optimism-corrected area under the receiver operating characteristic curve (AUC), R² , and Akaike's information criterion.

RESULTS

Of 2417 women, 155 (6%) had endometrial malignancy or endometrial intraepithelial neoplasia. In women with endometrial cancer median age was 67 years (interquartile range [IQR] 56-75 years), median parity was 2 (IQR 0-10), and median BMI was 28 (IQR 25-32). Age, BMI, and parity produced an AUC of 0.82. Other variables marginally affected the AUC, adding endometrial thickness substantially increased the AUC in postmenopausal women.

CONCLUSION

Age, parity, and BMI help in the assessment of endometrial cancer risk in women with abnormal uterine bleeding. Other patient information adds little, whereas sonographic endometrial thickness substantially improves assessment.

The Risk of Endometrial Malignancy and Other Endometrial Pathology in Women with Abnormal Uterine Bleeding: An Ultrasound-Based Model Development Study by the IETA Group

OBJECTIVES

The aim of this study was to develop a model that can discriminate between different etiologies of abnormal uterine bleeding.

DESIGN

The International Endometrial Tumor Analysis 1 study is a multicenter observational diagnostic study in 18 bleeding clinics in 9 countries. Consecutive women with abnormal vaginal bleeding presenting for ultrasound examination (n = 2,417) were recruited. The histology was obtained from endometrial sampling, D&C, hysteroscopic resection, hysterectomy, or ultrasound follow-up for >1 year.

METHODS

A model was developed using multinomial regression based on age, body mass index, and ultrasound predictors to distinguish between: (1) endometrial atrophy, (2) endometrial polyp or intracavitary myoma, (3) endometrial malignancy or atypical hyperplasia, (4) proliferative/secretory changes, endometritis, or hyperplasia without atypia and validated using leave-center-out cross-validation and bootstrapping. The main outcomes are the model's ability to discriminate between the four outcomes and the calibration of risk estimates.

RESULTS

The median age in 2,417 women was 50 (interquartile range 43-57). 414 (17%) women had endometrial atrophy; 996 (41%) had a polyp or myoma; 155 (6%) had an endometrial malignancy or atypical hyperplasia; and 852 (35%) had proliferative/secretory changes, endometritis, or hyperplasia without atypia. The model distinguished well between malignant and benign histology (c-statistic 0.88 95% CI: 0.85-0.91) and between all benign histologies. The probabilities for each of the four outcomes were over- or underestimated depending on the centers.

LIMITATIONS

Not all patients had a diagnosis based on histology. The model over- or underestimated the risk for certain outcomes in some centers, indicating local recalibration is advisable.

CONCLUSIONS

The proposed model reliably distinguishes between four histological outcomes. This is the first model to discriminate between several outcomes and is the only model applicable when menopausal status is uncertain. The model could be useful for patient management and counseling, and aid in the interpretation of ultrasound findings. Future research is needed to externally validate and locally recalibrate the model.

Diagnosis of appendicitis by transvaginal ultrasound examination

Background

Appendicitis is a frequent cause of abdominal pain. Symptoms may be atypical, and the appendix may not be visualised through abdominal ultrasonography. This case report illustrates the important role transvaginal ultrasound examination may have in the diagnostic workup of abdominal pain.

Methods

A case report focussing on imaging through transvaginal ultrasonography and comparing the ultrasonographic findings with CT-scan, as well as macroscopic examination and microscopy.

Results

A 33-year-old woman presenting at the emergency department with lower abdominal pain since 1 week. Transvaginal ultrasound shows a typical 'target sign' together with a blind-ending fluid-filled structure posterolateral right of the uterus, suggestive of appendicitis. These findings are confirmed on CT-scan, and a laparoscopic appendectomy is performed. We present the typical ultrasound imaging alongside the correlates on CT-scan as well as on macroscopy and on microscopic examination.

Conclusion

As gynaecologists, we must maintain a high degree of suspicion for non-gynaecological findings. This case report illustrates the value of transvaginal ultrasound in diagnosing appendicitis.

Contrast-Enhanced Ultrasound Imaging of Uterine Disorders: A Systematic Review

Uterine disorders are often presented with overlapping symptoms. The microvasculature holds specific information important for diagnosing uterine disorders. Conventional sonography is an established diagnostic technique in gynecology, but is limited by its inability to image the microvasculature. Contrast-enhanced ultrasound (CEUS), is capable of imaging the microvasculature by means of intravascular contrast agents; that is, gas-filled microbubbles. We provide a literature overview on the use of CEUS in diagnosing myometrial and endometrial disorders, that is, fibroids, adenomyosis, leiomyosarcomas and endometrial carcinomas, as well as for monitoring and enhancing the effectiveness of minimally invasive therapies. A systematic literature search with quality assessment was performed until December 2020. In total 34 studies were included, published between 2007 and 2020.The results entail a description of contrast-enhancement patterns obtained from healthy tissue and from malignant and benign tissue; providing a first base for potential diagnostic differentiation in gynecology. In addition it is also possible to determine the degree of myometrial invasion in case of endometrial carcinoma using CEUS. The effectiveness of minimally invasive therapies for uterine disorders can safely and accurately be assessed with CEUS. In conclusion, the abovementioned applications of CEUS are promising and it is worth further exploring its full potential for gynecology by designing innovative and methodologically high-quality clinical studies.

Terminology for describing normally sited and ectopic pregnancies on ultrasound: ESHRE recommendations for good practice

STUDY QUESTION

What recommendations can be provided to improve terminology for normal and ectopic pregnancy description on ultrasound?

SUMMARY ANSWER

The present ESHRE document provides 17 consensus recommendations on how to describe normally sited and different types of ectopic pregnancies on ultrasound.

WHAT IS KNOWN ALREADY

Current diagnostic criteria stipulate that each type of ectopic pregnancy can be defined by clear anatomical landmarks which facilitates reaching a correct diagnosis. However, a clear definition of normally sited pregnancies and a comprehensive classification of ectopic pregnancies are still lacking.

STUDY DESIGN SIZE DURATION

A working group of members of the ESHRE Special Interest Group in Implantation and Early Pregnancy (SIG-IEP) and selected experts in ultrasound was formed in order to write recommendations on the classification of ectopic pregnancies.

PARTICIPANTS/MATERIALS SETTING METHODS

The working group included nine members of different nationalities with internationally recognised experience in ultrasound and diagnosis of ectopic pregnancies on ultrasound. This document is developed according to the manual for development of ESHRE recommendations for good practice. The recommendations were discussed until consensus by the working group, supported by a survey among the members of the ESHRE SIG-IEP.

MAIN RESULTS AND THE ROLE OF CHANCE

A clear definition of normally sited pregnancy on ultrasound scan is important to avoid misdiagnosis of uterine ectopic pregnancies. A comprehensive classification of ectopic pregnancy must include definitions and descriptions of each type of ectopic pregnancy. Only a classification which provides descriptions and diagnostic criteria for all possible locations of ectopic pregnancy would be fit for use in routine clinical practice. The working group formulated 17 recommendations on the diagnosis of the different types of ectopic pregnancies on ultrasound. In addition, for each of the types of ectopic pregnancy, a schematic representation and examples on 2D and 3D ultrasound are provided.

LIMITATIONS REASONS FOR CAUTION

Owing to the limited evidence available, recommendations are mostly based on clinical and technical expertise.

WIDER IMPLICATIONS OF THE FINDINGS

This document is expected to have a significant impact on clinical practice in ultrasound for early pregnancy. The development of this terminology will help to reduce the risk of misdiagnosis and inappropriate treatment.

STUDY FUNDING/COMPETING INTERESTS

The meetings of the working group were funded by ESHRE. T.T. declares speakers' fees from GE Healthcare. The other authors declare that they have no conflict of interest.

TRIAL REGISTRATION NUMBER

N/A.

DISCLAIMER

This Good Practice Recommendations (GPR) document represents the views of ESHRE, which are the result of consensus between the relevant ESHRE stakeholders and where relevant based on the scientific evidence available at the time of preparation. ESHRE's GPRs should be used for informational and educational purposes. They should not be interpreted as setting a standard of care or be deemed inclusive of all proper methods of care nor exclusive of other methods of care reasonably directed to obtaining the same results. They do not replace the need for application of clinical judgement to each individual presentation, nor variations based on locality and facility type. Furthermore, ESHRE's GPRs do not constitute or imply the endorsement, recommendation or favouring of any of the included technologies by ESHRE.

Diagnosing adenomyosis: an integrated clinical and imaging approach

BACKGROUND

Adenomyosis is a benign uterine disorder where endometrial glands and stroma are pathologically demonstrated within the uterine myometrium. The pathogenesis involves sex steroid hormone abnormalities, inflammation, fibrosis and neuroangiogenesis, even though the proposed mechanisms are not fully understood. For many years, adenomyosis has been considered a histopathological diagnosis made after hysterectomy, classically performed in perimenopausal women with abnormal uterine bleeding (AUB) or pelvic pain. Until recently, adenomyosis was a clinically neglected condition. Nowadays, adenomyosis may also be diagnosed by non-invasive techniques, because of imaging advancements. Thus, a new epidemiological scenario has developed with an increasing number of women of reproductive age with ultrasound (US) or magnetic resonance imaging (MRI) diagnosis of adenomyosis. This condition is associated with a wide variety of symptoms (pelvic pain, AUB and/or infertility), but it is also recognised that some women are asymptomatic. Furthermore, adenomyosis often coexists with other gynecological comorbidities, such as endometriosis and uterine fibroids, and the diagnostic criteria are still not universally agreed. Therefore, the diagnostic process for adenomyosis is challenging.

OBJECTIVE AND RATIONALE

We present a comprehensive review on the diagnostic criteria of adenomyosis, including clinical signs and symptoms, ultrasound and MRI features and histopathological aspects of adenomyotic lesions. We also briefly summarise the relevant theories on adenomyosis pathogenesis, in order to provide the pathophysiological background to understand the different phenotypes and clinical presentation. The review highlights the controversies of multiple existing criteria, summarising all of the available evidences on adenomyosis diagnosis. The review aims also to underline the future perspective for diagnosis, stressing the importance of an integrated clinical and imaging approach, in order to identify this gynecological disease, so often underdiagnosed.

SEARCH METHODS

PubMed and Google Scholar were searched for all original and review articles related to diagnosis of adenomyosis published in English until October 2018.

OUTCOMES

The challenge in diagnosing adenomyosis starts with the controversies in the available pathogenic theories. The difficulties in understanding the way the disease arises and progresses have an impact also on the specific diagnostic criteria to use for a correct identification. Currently, the diagnosis of adenomyosis may be performed by non-invasive methods and the clinical signs and symptoms, despite their heterogeneity and poor specificity, may guide the clinician for a suspicion of the disease. Imaging techniques, including 2D and 3D US as well as MRI, allow the proper identification of the different phenotypes of adenomyosis (diffuse and/or focal). From a histological point of view, if the diagnosis of diffuse adenomyosis is straightforward, in more limited disease, the diagnosis has poor inter-observer reproducibility, leading to extreme variations in the prevalence of disease. Therefore, an integrated non-invasive diagnostic approach, considering risk factors profile, clinical symptoms, clinical examination and imaging, is proposed to adequately identify and characterise adenomyosis.

WIDER IMPLICATIONS

The development of the diagnostic tools allows the physicians to make an accurate diagnosis of adenomyosis by means of non-invasive techniques, representing a major breakthrough, in the light of the clinical consequences of this disease. Furthermore, this technological improvement will open a new epidemiological scenario, identifying different groups of women, with a dissimilar clinical and/or imaging phenotypes of adenomyosis, and this should be object of future research.

Signs and symptoms associated with uterine cancer in pre- and postmenopausal women

Uterine cancer is the most and second most common gynecological malignancy in developed and developing countries, respectively. The majority of endometrial cancers are diagnosed early due to the presence of abnormal uterine bleeding. The existing literature however contains only little data regarding the prevalence of such symptoms compared to patients with no or benign pathology. Therefore, a systematic review was conducted in order to determine the significance of various clinical signs and symptoms predicting uterine cancer. Embase, Web of Science and Medline databases were searched from inception until 18 June 2019. Studies eligible for selection inclusion assessed the diagnostic accuracy of clinical signs and symptoms in pre- and postmenopausal women aged 18-99 years old with uterine malignancy. Case reports, case series and studies of which full text was not available, were excluded. The risk of bias was assessed using the QUADAS-2 tool by two independent reviewers. Results were visualized by forest plots using RevMan(5.3). Forty-one studies were eventually included in this systematic review. Abnormal uterine bleeding occurring in pre-, post- and perimenopausal women was proven to be the most widely investigated symptom in relation to cancer of the uterus. Thirty-two articles examined patients with postmenopausal bleeding of which sensitivity and specificity varied between 0.28 to 0.86 and 0.63 to 0.84, respectively. Abnormal bleeding in pre- and perimenopausal women on the other hand showed a sensitivity ranging from 0.63 to 0.81. Its specificity could not be calculated due to missing data. Other symptoms appeared not sufficiently examined to assess their diagnostic accuracy range. This review highlights the current lack of knowledge regarding the diagnostic accuracy of several signs and symptoms for uterine cancer. After a thorough in-depth review of the literature, meta-analysis could not be performed due to the absence of control populations in the majority of articles. Further research is needed to establish the rule-in or rule-out value of specific clinical signs to identify patients at risk for uterine malignancy prompting further clinical assessment.

Intrauterine Fluid Instillation and Transtubal Flow: A Randomized Controlled In vitro Trial Comparing Gel and Water

Background:

Possible transtubal spillage of malignant cells is a major concern in fluid instillation sonography, as it is in hysteroscopy. This study aims to compare the transtubal flow of gel and saline and validate the clinical hypothesis that application of fluids with higher viscosity causes less spillage.

Methods:

Randomized controlled in vitro trial comparing gel and saline infusion on 15 tissue specimens after hysterectomy with bilateral salpingectomy. Instillations are performed with saline and gel dyed with a 1% ink solution. Qualitative assessment of tubal spill is investigated as primary outcome. Secondary outcomes are instillation-volume and -pressure, assessed by measuring endometrial cavity dilation at in vitro ultrasound examination and subjective numeric 10-point scoring of the instillation pressure by a dedicated examiner.

Results:

Tubal flow was more often observed during saline instillation (odds ratio 4.88, P = 0.008). Median subjectively assessed instillation pressures were nine arbitrary units for gel and three for saline (P < 0.001). Tubal flow occurred from 2 cc onward in the saline group versus five cc in the gel instillation group. Cavitary dilation did not differ between both groups.

Conclusion:

Gel instillation sonography is in vitro associated with less tubal flow and therefore could be a safer diagnostic test compared to saline infusion sonography or hysteroscopy. In vivo studies are necessary to confirm these results.

Circulating Transcripts and Biomarkers in Uterine Tumors: Is There a Predictive Role?

PURPOSE OF REVIEW

Uterine cancer comprises endometrial carcinoma and the uterine sarcoma. Endometrial carcinomas are the most frequent variant and have early symptoms and a solid diagnostic work up, resulting in a rather fair prognosis. However, in case of advanced stage disease and relapse, treatment options are limited and prognosis is impaired. Uterine sarcomas are rare, often lacking symptoms and no diagnostic tool for correct pre-operative diagnosis are available. Prognosis is poor.

RECENT FINDINGS

Circulating biomarkers as a liquid biopsy could be beneficial as a diagnostic tool in uterine sarcomas. For both carcinomas and sarcomas, circulating biomarkers could be of use in predicting early disease recurrence. This review in endometrial carcinoma and uterine sarcoma focus on circulating biomarkers; such as proteins; circulating tumor cells; circulating tumor DNA; microRNA; and immune cells.

Juvenile cystic adenomyosis: A case report and review of the literature

This report describes a case of a uterine cystic myometrial lesion in a 16-year-old adolescent girl presenting with pelvic pain and severe progressively worsening dysmenorrhoea. Patient's symptoms, ultrasound and MRI were suggestive of juvenile cystic adenomyosis (JCA). Medical treatment and alcohol sclerotherapy had a moderate and transient effect. The symptoms rapidly recurred, and the lesion was successfully excised via laparoscopic surgery. The treatment of JCA depends on patient's age, the symptoms' severity and the cyst location. Although rare, juvenile cystic adenomyosis should be considered in young women with severe dysmenorrhoea.

Intra- and Inter-Rater Agreement Describing Myometrial Lesions Using Morphologic Uterus Sonographic Assessment: A Pilot Study

OBJECTIVES

To evaluate the intra- and inter-rater agreement for myometrial lesions using Morphologic Uterus Sonographic Assessment terminology.

METHODS

Thirteen raters with high (n = 6) or medium experience (n = 7) assessed 30 3-dimensional ultrasound clips with (n = 20) and without (n = 10) benign myometrial lesions. Myometrial lesions were reported as poorly or well defined and then systematically evaluated for the presence of individual features. The clips were blindly assessed twice (at a 2-month interval). Intra- and inter-rater agreements were calculated with κ statistics.

RESULTS

The reporting of poorly defined lesions reached moderate intra-rater agreement (κ = 0.49 [high experience] and 0.47 [medium experience]) and poor inter-rater agreement (κ = 0.39 [high experience] and 0.25 [medium experience]). The reporting of well-defined lesions reached good to very good intra-rater agreement (κ = 0.73 [high experience] and 0.82 [medium experience]) and good inter-rater agreement (κ = 0.75 [high experience] and 0.63 [medium experience]). Most individual features associated with ill-defined lesions reached moderate intra- and inter-rater agreement among highly experienced raters (κ = 0.41-0.60). The least reproducible features were myometrial cysts, hyperechoic islands, subendometrial lines and buds, and translesional flow (κ = 0.11-0.34). Most individual features associated with well-defined lesions reached moderate to good intra- and inter-rater agreement among all observers (κ = 0.41-0.80). The least reproducible features were a serosal contour, asymmetry, a hyperechoic rim, and fan-shaped shadows (κ = 0.00-0.35).

CONCLUSIONS

The reporting of well-defined lesions showed excellent agreement, whereas the agreement for poorly defined lesions was low, even among highly experienced raters. The agreement on identifying individual features varied, especially for features associated with ill-defined lesions. Guidelines on minimum requirements for features associated with ill-defined lesions to be interpreted as poorly defined lesions may improve agreement.

Prediction of Tubal Ectopic Pregnancy Using Offline Analysis of 3-Dimensional Transvaginal Ultrasonographic Data Sets: An Interobserver and Diagnostic Accuracy Study

OBJECTIVES

To assess interobserver reproducibility in detecting tubal ectopic pregnancies by reading data sets from 3-dimensional (3D) transvaginal ultrasonography (TVUS) and comparing it with real-time 2-dimensional (2D) TVUS.

METHODS

Images were initially classified as showing pregnancies of unknown location or tubal ectopic pregnancies on real time 2D TVUS by an experienced sonologist, who acquired 5 3D volumes. Data sets were analyzed offline by 5 observers who had to classify each case as ectopic pregnancy or pregnancy of unknown location. The interobserver reproducibility was evaluated by the Fleiss κ statistic. The performance of each observer in predicting ectopic pregnancies was compared to that of the experienced sonologist. Women were followed until they were reclassified as follows: (1) failed pregnancy of unknown location; (2) intrauterine pregnancy; (3) ectopic pregnancy; or (4) persistent pregnancy of unknown location.

RESULTS

Sixty-one women were included. The agreement between reading offline 3D data sets and the first real-time 2D TVUS was very good (80%-82%; κ = 0.89). The overall interobserver agreement among observers reading offline 3D data sets was moderate (κ = 0.52). The diagnostic performance of experienced observers reading offline 3D data sets had accuracy of 78.3% to 85.0%, sensitivity of 66.7% to 81.3%, specificity of 79.5% to 88.4%, positive predictive value of 57.1% to 72.2%, and negative predictive value of 87.5% to 91.3%, compared to the experienced sonologist's real-time 2D TVUS: accuracy of 94.5%, sensitivity of 94.4%, specificity of 94.5%, positive predictive value of 85.0%, and negative predictive value of 98.1%.

CONCLUSIONS

The diagnostic accuracy of 3D TVUS by reading offline data sets for predicting ectopic pregnancies is dependent on experience. Reading only static 3D data sets without clinical information does not match the diagnostic performance of real time 2D TVUS combined with clinical information obtained during the scan.

Ultrasound diagnosis of endometriosis and adenomyosis: State of the art

Transvaginal ultrasonography has become the primary test in the diagnosis of pelvic endometriosis and adenomyosis. A review of the literature on the diagnostic accuracy of ultrasonography in pelvic endometriosis and adenomyosis, as well as a comparison with magnetic resonance imaging, will be presented. Criteria for diagnosis of an endometrioma according to robust prospective data together with guidelines as to adequate reporting of the location of deep infiltrating endometriosis will be given. The sonographic features of adenomyosis including the differential diagnosis between focal adenomyosis and a uterine fibroid are reviewed. The available data in the literature on ultrasound diagnosis of pelvic endometriosis and adenomyosis, their clinical relevance, and their limitations are discussed.

Guiding histological assessment of uterine lesions using 3D in vitro ultrasonography and stereotaxis

OBJECTIVE

To compare ultrasonographic features of uterine lesions with the findings at macroscopy and microscopy.

METHODS

Case series of ten consecutive women undergoing a hysterectomy for uterine pathology. A preoperative transvaginal ultrasound examination was performed. After hysterectomy, the uterus was re-evaluated by 3D in vitro ultrasonography and in vitro gel instillation sonography (iGIS). The lesion of interest was pinpointed by inserting an intramuscular injection needle using a free-hand 2D-ultrasound guided technique to focus the macroscopic and the microscopic examination by the pathologist.

RESULTS

Adenomyosis, benign fibroids and infiltrating endometrial cancer were diagnosed in six, five and one patient, respectively. We found that iGIS improved image quality of in vitro ultrasound. There was a good correlation between the reported ultrasound features and the final histological diagnosis. Some lesions had been misinterpreted during preoperative ultrasonography or at macroscopical examination: e.g. dense myometrial vessels reported as small myometrial cysts at grey scale ultrasound examination; absence of macroscopical lesions in a case of diffuse adenomyosis.

CONCLUSIONS

In vitro 3D ultrasonography and iGIS allow for accurate mapping of uterine lesions so that ultrasound features can be matched with final histology. Our series demonstrates some pitfalls in the interpretation of sonographic and macroscopic features of uterine lesions. Stereotaxis of focal uterine lesions could focus histological assessment and reduces examination time for the pathologist.

Optimizing the Histological Diagnosis of Adenomyosis Using in vitro Three-Dimensional Ultrasonography

The use of in vitro three-dimensional ultrasound examination with needle stereotaxis after hysterectomy is illustrated in a case of extensive adenomyosis. The quality of the images at in vitro ultrasonography was compared with the quality of the images obtained at the preoperative ultrasound examination. The ultrasound findings were compared with the macroscopical and the microscopical examination. This new approach helps in indicating the precise location of the preoperatively identified adenomyosis lesions to the pathologist. This may optimize the diagnostic accuracy of the histological examination in women with adenomyosis.

Ultrasound in the diagnosis of endometrial and intracavitary pathology: an update

Over the last two decades, ultrasound evaluation of the endometrium and uterine cavity evolved from 2D grayscale evaluation of the endometrial thickness to a much more comprehensive examination including colour imaging, fluid instillation and 3D ultrasound. The International Endometrial Tumor Analysis (IETA) group recently published a consensus opinion paper on terms, definitions and measurements to describe the sonographic features on the endometrium and intrauterine lesions.

Maximum Peak Systolic Velocity and Management of Highly Vascularized Retained Products of Conception

OBJECTIVES

The purpose of this study was to evaluate blood loss and procedure-related complications during and after surgical removal of retained products of conception with high-velocity enhanced myometrial vascularity.

METHODS

We conducted a prospective study of 18 consecutive women with a diagnosis of retained products of conception and enhanced myometrial vascularity, with a peak systolic velocity (PSV) higher than 60 cm/s. All underwent ultrasound-guided surgical removal of the retained products under general anesthesia. Blood loss during the procedure was collected and recorded. The removed tissue was sent for histologic examination. An ultrasound examination was repeated within 24 hours.

RESULTS

Five patients had retained products of conception after a term delivery, 1 after a second-trimester termination of pregnancy, 7 after a spontaneous first-trimester miscarriage, and 5 after a first-trimester termination elsewhere. The PSV in the area of enhanced myometrial vascularity at diagnosis ranged from 61.0 to 152.6 cm/s (mean, 104.9 cm/s). The estimated blood loss at surgery ranged from 20 to 1000 mL (mean, 200 mL). After surgery, the PSV in the myometrium dropped dramatically (≤30 cm/s in all but 1 case). In all cases, trophoblastic tissue was confirmed at histologic examination.

CONCLUSIONS

Although surgical removal of retained products of conception was uneventful in most cases, heavy bleeding has to be anticipated in cases of high-velocity flow in the myometrium underlying residual trophoblastic tissue. Accordingly, in cases of high-velocity enhanced myometrial vascularity, we advocate surgical removal of the residual tissue under ultrasound guidance by an experienced surgeon and in the presence of a fully informed anesthetist.

Clinical data miner: an electronic case report form system with integrated data preprocessing and machine-learning libraries supporting clinical diagnostic model research

BACKGROUND

Using machine-learning techniques, clinical diagnostic model research extracts diagnostic models from patient data. Traditionally, patient data are often collected using electronic Case Report Form (eCRF) systems, while mathematical software is used for analyzing these data using machine-learning techniques. Due to the lack of integration between eCRF systems and mathematical software, extracting diagnostic models is a complex, error-prone process. Moreover, due to the complexity of this process, it is usually only performed once, after a predetermined number of data points have been collected, without insight into the predictive performance of the resulting models.

OBJECTIVE

The objective of the study of Clinical Data Miner (CDM) software framework is to offer an eCRF system with integrated data preprocessing and machine-learning libraries, improving efficiency of the clinical diagnostic model research workflow, and to enable optimization of patient inclusion numbers through study performance monitoring.

METHODS

The CDM software framework was developed using a test-driven development (TDD) approach, to ensure high software quality. Architecturally, CDM's design is split over a number of modules, to ensure future extendability.

RESULTS

The TDD approach has enabled us to deliver high software quality. CDM's eCRF Web interface is in active use by the studies of the International Endometrial Tumor Analysis consortium, with over 4000 enrolled patients, and more studies planned. Additionally, a derived user interface has been used in six separate interrater agreement studies. CDM's integrated data preprocessing and machine-learning libraries simplify some otherwise manual and error-prone steps in the clinical diagnostic model research workflow. Furthermore, CDM's libraries provide study coordinators with a method to monitor a study's predictive performance as patient inclusions increase.

CONCLUSIONS

To our knowledge, CDM is the only eCRF system integrating data preprocessing and machine-learning libraries. This integration improves the efficiency of the clinical diagnostic model research workflow. Moreover, by simplifying the generation of learning curves, CDM enables study coordinators to assess more accurately when data collection can be terminated, resulting in better models or lower patient recruitment costs.

The use of a new gel foam for the evaluation of tubal patency

AIMS

To evaluate the feasibility and the reliability of hysterosalpingo-foam sonography (HyFoSy) using gel foam in the assessment of tubal patency.

METHODS

Nonrandomized, observational, academic and single-center study of 20 women being investigated because of subfertility and scheduled for a laparoscopy with chromopertubation. A detailed description of HyFoSy with a newly developed gel foam is given in the way it proved to be most efficient in our hands. The results of HyFoSy are compared to the data regarding tubal patency testing during laparoscopy by chromopertubation.

RESULTS

All 20 HyFoSy were technically successful. Four of the 40 tubes, 1 right tube and 3 left tubes, were not patent at HyFoSy (3 tubes with proximal block and 1 tube with distal block). There was a 100% agreement between tubal patency data according to HyFoSy testing and laparoscopic chromopertubation testing.

CONCLUSION

HyFoSy is both feasible and accurate in the diagnosis of tubal patency.

Screening for uterine tumours

The most prevalent uterine tumours are leiomyomas, which are benign and have a prevalence of about 50% at menopause. The incidence of endometrial cancer and uterine sarcomas is about 25 per 100,000 and 0.7 per 100,000, respectively. Reported risk factors for endometrial cancer are advanced age, unopposed oestrogen stimulation, late menopause, obesity, diabetes mellitus, nulliparity, feminising ovarian tumours, polycystic ovarian syndrome, tamoxifen and belonging to a hereditary non-polyposis colorectal cancer family. Unopposed oestrogen stimulation and tamoxifen have also been confirmed to induce uterine sarcomas. Cervical cytology, endometrial sampling and ultrasound have been proposed in the early diagnosis of endometrial cancer. No pathognomonic ultrasound, magnetic resonance imaging or computed tomography features are able to differentiate between a leiomyoma and a uterine sarcoma, and reliable serum markers for sarcomas are lacking. To date, mass screening for uterine malignancies is not feasible or effective.

Association between abnormal vaginal flora and cervical length as risk factors for preterm birth

AIM.: To study the relationship between abnormal vaginal flora (AVF) in the first trimester as a risk factor for shortening cervix length (CL) at second and third trimester, and to assess the combination of these factors in predicting preterm delivery. METHODS.: 1026 unselected low risk women seen before 16 weeks of pregnancy underwent sampling of vaginal fluid for wet mount microscopy at a central laboratory blinded to clinical data. Disappearance of lactobacilli and bacterial vaginosis (BV) were scored according to standardized definitions. Specific cultures were performed for M hominis, U urealyticum, aerobic vaginitis (AV) and vaginal colonization with Candida. CL was measured by transvaginal ultrasound at 10-14, 20-24 and at 30-34 weeks, and gestational age at delivery was recorded. RESULTS.: Short cervix (CL below the lower quartile) at 10-14 weeks is related to a lower CL at 20-24 and 30-34 weeks of gestation (p=0.01, p=0.005 respectively). Short cervix at 20-24 weeks, but not at 10-14 weeks, was predictive for preterm birth. In patients with M. hominis and/or with severe AV at 10-14 weeks, the cervix appeared shorter at 20-24 and at 30-34 weeks than in other women. Increased risk for preterm birth in women with a shorter cervix at 10-14 weeks and AVF could not be proved by this study. DISCUSSION.: Presence of AV or M. hominis is associated with a shorter cervix at 20-24 and 30-34 weeks. Although a short cervix at 10-14 weeks increases the likelihood of having a short cervix later in pregnancy, it was not a prerequisite for AVF to be associated with preterm delivery. Therefore, in the pathogenesis of preterm birth, certain types of AVF may be involved directly in the process of cervical shortening, rather than being exposed to the intrauterine cavity more readily by a short cervix in the early stages of pregnancy. Copyright (c) 2010 ISUOG. Published by John Wiley & Sons, Ltd.

Ultrasound assessment of endometrial thickness and endometrial polyps in women on hormonal replacement therapy

OBJECTIVE

This study was performed to evaluate the thickness and the sonographic features of the endometrium in postmenopausal women on hormone replacement therapy (HRT).

STUDY DESIGN

This prospective study was based on 483 vaginal ultrasound examinations performed in 238 consecutive postmenopausal women on HRT.

RESULTS

Endometrial polyps were diagnosed by ultrasound in 16.3% of the patients; 43.6% were asymptomatic. In the nonpolyp group, a significant difference in endometrial thickness between sequential and continuous schemes was found. In sequential HRT, a three-layer ultrasound pattern of the endometrium was seen in 47% of the women in the estrogen-alone phase of cycle versus 11% in the estrogen-progestogen phase.

CONCLUSION

Patients on HRT need other reference values for endometrial thickness compared with postmenopausal women without HRT. In women on sequential HRT, a transvaginal sonographic evaluation performed in the estrogen-alone phase of cycle may optimize the accuracy for focal lesion detection. The significance of the incidental finding of polyps in an important number of asymptomatic women on HRT remains unsettled.