A. Installe

Systematic approach to sonographic evaluation of the pelvis in women with suspected endometriosis, including terms, definitions and measurements : A consensus opinion from the International Deep Endometriosis Analysis (IDEA) group

The IDEA (International Deep Endometriosis Analysis group) statement is a consensus opinion on terms, definitions and measurements that may be used to describe the sonographic features of the different phenotypes of endometriosis. Currently, it is difficult to compare results between published studies because authors use different terms when describing the same structures and anatomical locations. We hope that the terms and definitions suggested herein will be adopted in centers around the world. This would result in consistent use of nomenclature when describing the ultrasound location and extent of endometriosis. We believe that the standardization of terminology will allow meaningful comparisons between future studies in women with an ultrasound diagnosis of endometriosis and should facilitate multicenter research. Copyright

Terms, definitions and measurements to describe sonographic features of myometrium and uterine masses: a consensus opinion from the Morphological Uterus Sonographic Assessment (MUSA) group

The MUSA (Morphological Uterus Sonographic Assessment) statement is a consensus statement on terms, definitions and measurements that may be used to describe and report the sonographic features of the myometrium using gray‐scale sonography, color/power Doppler and three‐dimensional ultrasound imaging. The terms and definitions described may form the basis for prospective studies to predict the risk of different myometrial pathologies, based on their ultrasound appearance, and thus should be relevant for the clinician in daily practice and for clinical research. The sonographic features and use of terminology for describing the two most common myometrial lesions (fibroids and adenomyosis) and uterine smooth muscle tumors are presented. Copyright

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. CDMs integrated data preprocessing and machine-learning libraries simplify some otherwise manual and error-prone steps in the clinical diagnostic model research workflow. Furthermore, CDMs libraries provide study coordinators with a method to monitor a studys 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.

Ultrasound characteristics of endometrial cancer as defined by International Endometrial Tumor Analysis (IETA) consensus nomenclature: prospective multicenter study

To describe the sonographic features of endometrial cancer in relation to tumor stage, grade and histological type, using the International Endometrial Tumor Analysis (IETA) terminology.

Interobserver agreement in assessment of polycystic ovarian morphology using pattern recognition.

In daily clinical practice, ultrasonographic diagnosis of polycystic ovarian (PCO) morphology is frequently made ‘at first glance’, based on pattern recognition. This is a subjective impression of the examiner1, without precise quantification of total follicle number, follicle size, follicle distribution or ovarian volume. The classification of an ovary as being polycystic may have important clinical and therapeutic consequences. The aim of this study was to evaluate the interobserver agreement for the diagnosis of PCO morphology using only the subjective assessment of an examiner (or ‘pattern recognition’). Offline analysis of ultrasound images was conducted using the web-based electronic data capture software framework Clinical Data Miner (CDM)2. CDM enables ultrasound images to be shown alongside questions and multiple-choice categories. For each patient, a single two-dimensional (2D) ultrasound image of an ovary was evaluated. In total, 40 different images from women of reproductive age (days 3–5 of a spontaneous cycle) were integrated into the CDM. Five gynecologists (N.R.F., D.D.N., T.B., T.V.B. and D.T.) with experience in gynecological ultrasound were asked to evaluate the images online. Images were shown in random order without clinical information and the examiners scored each ovary as ‘typical’ PCO morphology, ‘possible’ PCO morphology or ‘not’ PCO morphology. Subsequently the same 40 images were presented again in random order and the examiners had to specify follicle distribution as peripheral or random, follicle size as uniform or non-uniform and stromal appearance as central echogenic, diffuse echogenic or of normal appearance (Figures 1 and 2). Interobserver agreement was assessed using Fleiss’ kappa coefficient3. Bias-corrected estimates and standard errors for the

OP36.08: Optimization of the image quality of endometrial-myometrial junction (EMJ)

measurements and significantly smaller for the CRL measurement (P = 0.041). Conclusions: Medaphor ScanTrainer distinguishes between gynaecologists of differing ultrasound expertise in terms of completing a comprehensive and systematic transvaginal scan and measurement accuracy. This system has sufficient construct validity to warrant further investigation into its use in gynaecological scan training and further research is ongoing.

OP11.04: Interobserver variability in the ultrasound diagnosis of polycystic ovaries using pattern recognition

and higher serum estradiol (E), progesterone (P) and hCG levels and miscarriage rates would be inversely related to these parameters. Methods: Power calculations suggested a sample size of 100: 128 women were prospectively recruited. Blood was drawn for P, E and hCG levels and TV USS (Voluson E8) scan performed to acquire 3D power Doppler data of the uterus and pulsed wave Doppler studies of uterine arteries. VOCAL used to define endometrium and subendometrium and the values corrected for depth by standardising against iliac vessels (sVI, sFI, sVFI). This was repeated after 7 days (ET+7). Stats analysis using ANOVA, logistic regression and ROC analysis. Results: 106 women included. 60 (56.6%) women conceived; 15 (25%) miscarried in the first trimester. All parameters changed significantly from ET to ET+7. Whilst there was no significant difference in endometrial morphometry or standardised subendometrial vascular indices, mean uterine artery PSV and serum E, P and hCG levels were significantly higher in women who conceived at ET+7. All 3 serum markers were predictive of pregnancy with AUC of 0.84 (95% CI 0.73–0.92), 0.76 (95% CI 0.64–0.85) and 0.96 (95% CI 0.90–0.99) for E, P and hCG. The best threshold was hCG 5IU: sensitivity 71%, specificity 98% for pregnancy. No sig difference in any parameter between women who miscarried and those who had live birth (P > 0.05). Conclusions: Mean uterine artery PSV and serum estradiol, progesterone and hCG a week post ET are significantly higher in women who conceive after IVF. hCG levels were most predictive of conception. No serum or ultrasound marker could predict which of these ended in miscarriage.

OP03.04: The influence of patient characteristics on the image quality of the endometrial‐myometrial junction (EMJ)

a maximal angle of 43 degrees. A counterclockwise rotation (to the right) was identified in 39.2% cases with mean angle of 34.1 ± 13.4 degrees and a maximal angle of 72 degrees. Only 11.8% of patients had exact parallel orientation of the uterine fundus to the long axis of the body. Conclusions: Assessment of rotation angle of the uterus at the fundus is possible using 3-D ultrasound. This is important especially for patients whose pelvic exam is not adequate and may help to improve the results of procedures that involve the uterus.

OP08.04: Showing pictograms in electronic data capture software improves interrater agreement

Objectives: To create a web interface for conducting interrater agreement studies in the context of the studies defined by the International Endometrial Tumor Analysis (IETA) group, that should be easily generalizable to other imaging-based interrater agreement studies or as an assessment tool for imaging specialists. Methods: The web interface makes use of the Clinical Data Miner (CDM) framework, which allowed to substantially reduce development time. Results: The interface shows the images to be evaluated in random order, which minimizes the learning effect when the study has to be completed twice by the same observers. The system verifies if any images were already evaluated by the observer for the study, and only presents the ones that were not. This allows the observer to complete a study over the course of multiple sessions. The interface has been used by five independent clinicians for evaluating 200 images and was judged to be user-friendly. Conclusions: We have created a new user-friendly web interface based on CDM for conducting interrater agreement studies on 2D imaging modalities. It may also be used as an efficient teaching modality to test the performance of different imaging specialists.

International Endometrial Tumor Analysis (IETA) terminology in women with postmenopausal bleeding and sonographic endometrial thickness ≥ 4.5 mm: agreement and reliability study

To estimate intra‐ and interrater agreement and reliability with regard to describing ultrasound images of the endometrium using the International Endometrial Tumor Analysis (IETA) terminology.