Radiomics analysis of ultrasound images to discriminate between benign and malignant adnexal masses with solid ultrasound morphology.

OBJECTIVE: Our primary aim was to identify radiomic ultrasound features that can distinguish benign from malignant adnexal masses with solid ultrasound morphology, and primary invasive from metastatic solid ovarian masses, and to develop ultrasound-based machine learning models that include radiomics features to discriminate between benign and malignant solid adnexal masses. Our secondary aim was to compare the diagnostic performance of our radiomics models with that of the ADNEX model and subjective assessment by an experienced ultrasound examiner. METHODS: This is a retrospective observational single center study. Patients with a histological diagnosis of an adnexal tumor with solid morphology at preoperative ultrasound examination performed between 2014 and 2021 were included. The patient cohort was split into training and validation sets with a ratio of 70:30 and with the same proportion of benign and malignant (borderline, primary invasive and metastatic) tumors in the two subsets. The extracted radiomic features belonged to two different families: intensity-based statistical features and textural features. Models to predict malignancy were built based on a random forest classifier, fine-tuned using 5-fold cross-validation over the training set, and tested on the held-out validation set. The variables used in model building were patient's age, and those radiomic features that were statistically significantly different between benign and malignant adnexal masses (Wilcoxon-Mann-Whitney Test with Benjamini-Hochberg correction for multiple comparisons) and assessed as not redundant based on the Pearson correlation coefficient. We describe discriminative ability as area under the receiver operating characteristics curve (AUC) and classification performance as sensitivity and specificity. RESULTS: 326 patients were identified and 775 preoperative ultrasound images were analyzed. 68 radiomic features were extracted, 52 differed statistically significantly between benign and malignant tumors in the training set, and 18 features were selected for inclusion in model building. The same 52 radiomic features differed statistically significantly between benign, primary invasive malignant and metastatic tumors. However, the values of the features manifested overlap between primary malignant and metastatic tumors and did not differ statistically significantly between them. In the validation set, 25/98 tumors (25.5%) were benign, 73/98 (74.5%) were malignant (6 borderline, 57 primary invasive, 10 metastases). In the validation set, a model including only radiomics features had an AUC of 0.80, and 78% sensitivity and 76% specificity at its optimal risk of malignancy cutoff (68% based on Youden's index). The corresponding results for a model including age and radiomics features were 0.79, 86% and 56% (cutoff 60% based on Youden's method), while those of the ADNEX model were 0.88, 99% and 64% (at 20% malignancy cutoff). Subjective assessment had sensitivity 99% and specificity 72%. CONCLUSIONS: Even though our radiomics models had discriminative ability inferior to that of the ADNEX model, our results are promising enough to justify continued development of radiomics analysis of ultrasound images of adnexal masses. This article is protected by copyright. All rights reserved.

Validation of ADNEX and IOTA two-step strategy and estimation of risk of complications during follow-up of adnexal masses in low-risk population.

OBJECTIVES: To evaluate the ability of the Assessment of Different NEoplasias in the adneXa (ADNEX) model and the International Ovarian Tumour Analysis (IOTA) two-step strategy to predict malignancy in adnexal masses detected in an outpatient low-risk setting, and to estimate the risk of complications in masses with benign ultrasound morphology managed using clinical and ultrasound follow-up. METHODS: This single-center study was performed at Hospital Universitari Dexeus, Barcelona, Spain, using interim data from the ongoing prospective observational IOTA Phase-5 (IOTA5) study. The primary aim of the IOTA5 study is to describe the cumulative incidence of complications during follow-up of adnexal masses classified as benign on ultrasound examination. Consecutive patients with an adnexal mass detected between June 2012 and September 2016 in a private center offering screening for gynecological cancer were included and followed up until February 2020. Tumors were classified as benign or malignant based on histology (if patients underwent surgery) or the outcome of clinical and ultrasound follow-up at 12 (range, 10-14) months. Multiple imputation was used when outcomes were uncertain. The ability of the ADNEX model without CA125 and of the IOTA two-step strategy to distinguish benign from malignant masses was evaluated retrospectively using the prospectively collected data. We assessed performance with regard to discrimination (area under the receiver-operating-characteristics curve (AUC)), calibration, classification (sensitivity and specificity) and clinical utility (Net Benefit). In the group of patients with a mass judged to be benign who were selected for conservative management, we evaluated the occurrence of spontaneous resolution or any mass complication during the first 5 years of follow-up by assessing the cumulative incidence of malignancy, torsion, cyst rupture and minor mass complications (inflammation, infection or adhesions) and the time to occurrence of an event. RESULTS: A total of 2654 patients were recruited to the study. After application of exclusion criteria, 2039 patients with a newly detected mass were included for the model validation. Of those, 1684 (83%) masses were benign, 49 (2%) masses were malignant and, for 306 (15%) masses, the outcome was uncertain and therefore imputed. The AUC was 0.95 (95% CI, 0.89-0.98) for ADNEX without CA125 and 0.94 (95% CI, 0.88-0.97) for the two-step strategy. Calibration performance could not be meaningfully interpreted because the small number of malignancies resulted in very wide confidence intervals. The two-step strategy had better clinical utility than did the ADNEX model at malignancy risk thresholds < 3%. There were 1472 (72%) patients whose mass was judged to be benign based on pattern recognition by an experienced ultrasound examiner and were managed with clinical and ultrasound follow-up. In this group, the 5-year cumulative incidence was 66% (95% CI, 63-69%) for spontaneous resolution of the mass, 0% (95% CI, 0-0.2%) for torsion, 0.1% (95% CI, < 0.1-0.4%) for cyst rupture, 0.2% (95% CI, 0.1-0.6%) for a borderline tumor and 0.2% (95% CI, 0.1-0.6%) for invasive malignancy. CONCLUSIONS: The ADNEX model and IOTA two-step strategy performed well to distinguish benign from malignant adnexal masses detected in a low-risk population. Conservative management is safe for masses with a benign ultrasound appearance in this population. © 2024 International Society of Ultrasound in Obstetrics and Gynecology.

A cost-effectiveness analysis of an integrated clinical-radiogenomic screening program for the identification of BRCA 1/2 carriers (e-PROBE study).

Current approach to identify BRCA 1/2 carriers in the general population is ineffective as most of the carriers remain undiagnosed. Radiomics is an emerging tool for large scale quantitative analysis of features from standard diagnostic imaging and has been applied also to identify gene mutational status. The objective of this study was to evaluate the clinical and economic impact of integrating a radiogenomics model with clinical and family history data in identifying BRCA mutation carriers in the general population. This cost-effective analysis compares three different approaches to women selection for BRCA testing: established clinical criteria/family history (model 1); established clinical criteria/family history and the currently available radiogenomic model (49% sensitivity and 87% specificity) based on ultrasound images (model 2); same approach used in model 2 but simulating an improvement of the performances of the radiogenomic model (80% sensitivity and 95% specificity) (model 3). All models were trained with literature data. Direct costs were calculated according to the rates currently used in Italy. The analysis was performed simulating different scenarios on the generation of 18-year-old girls in Italy (274,000 people). The main outcome was to identify the most effective model comparing the number of years of BRCA-cancer healthy life expectancy (HLYs). An incremental cost-effectiveness ratio (ICER) was also derived to determine the cost in order to increase BRCA carriers-healthy life span by 1 year. Compared to model 1, model 2 increases the detection rate of BRCA carriers by 41.8%, reduces the rate of BRCA-related cancers by 23.7%, generating over a 62-year observation period a cost increase by 2.51 €/Year/Person. Moreover, model 3 further increases BRCA carriers detection (+ 68.3%) and decrease in BRCA-related cancers (- 38.4%) is observed compared to model 1. Model 3 increases costs by 0.7 €/Year/Person. After one generation, the estimated ICER in the general population amounts to about 3800€ and 653€ in model 2 and model 3 respectively. Model 2 has a massive effect after only one generation in detecting carriers in the general population with only a small cost increment. The clinical impact is limited mainly due to the current low acceptance rate of risk-reducing surgeries. Further multicentric studies are required before implementing the integrated clinical-radiogenomic model in clinical practice.

Imaging in gynecological disease (27): clinical and ultrasound characteristics of recurrent ovarian stromal cell tumors.

OBJECTIVE: To describe the clinical and ultrasound characteristics of recurrent granulosa cell and Sertoli-Leydig cell tumors. METHODS: This was a retrospective observational study performed at Fondazione Policlinico Universitario A. Gemelli, Istituto di Ricovero e Cura a Carattere Scientifico, IRCCS, Rome (Gemelli center), Italy. Patients with a histological diagnosis of recurrent granulosa cell tumor or Sertoli-Leydig cell tumor were identified from the database of the Department of Gynecological Oncology. Those who had undergone a preoperative ultrasound examination at the Gemelli center between 2012 and 2020 were included, and the data retrieved from the original ultrasound reports. In all of these reports, the recurrent tumors were described using International Ovarian Tumor Analysis (IOTA) terminology. If a patient had more than one episode of relapse, information from all episodes was collected. If there was more than one recurrent tumor at the same ultrasound examination, all tumors were included. One expert sonographer also reviewed all available ultrasound images to identify typical ultrasound patterns using pattern recognition. RESULTS: We identified 30 patients with a histological diagnosis of recurrent granulosa cell tumor (25 patients, 55 tumors) or Sertoli-Leydig cell tumor (five patients, seven tumors). All 30 had undergone at least one preoperative ultrasound examination at the Gemelli center and were included. These women had a total of 66 episodes of relapse, of which a preoperative ultrasound examination had been performed at the Gemelli center in 34, revealing 62 recurrent lesions: one in 22/34 (64.7%) episodes of relapse, two in 4/34 (11.8%) episodes and three or more in 8/34 (23.5%) episodes. Most recurrent granulosa cell tumors (38/55, 69.1%) and recurrent Sertoli-Leydig tumors (6/7, 85.7%) were classified as solid or multilocular-solid tumors, while 8/55 (14.5%) recurrent granulosa cell tumors and 1/7 (14.3%) recurrent Sertoli-Leydig cell tumors were unilocular cysts and 9/55 (16.4%) recurrent granulosa cell tumors were multilocular cysts. The nine unilocular cysts had contents that were anechoic (n = 2) or had low-level echogenicity (n = 7), had either smooth (n = 4) or irregular (n = 5) internal cyst walls, and ranged in largest diameter from 8 to 38 mm, with three being < 20 mm and five being 20-30 mm. On retrospective review of the images, two typical ultrasound patterns were described: small solid tumor measuring < 2 cm (15/62, 24.2%) and tumor with vascularized echogenic ground-glass-like content (12/62, 19.4%). CONCLUSIONS: Some granulosa cell and Sertoli-Leydig cell recurrences manifest one of two typical ultrasound patterns, while some appear as unilocular cysts. These are usually classified as benign, but in patients being followed up for a granulosa cell tumor or Sertoli-Leydig cell tumor, a unilocular cyst should be considered suspicious of recurrence. © 2023 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

Estimating risk of endometrial malignancy and other intracavitary uterine pathology in women without abnormal uterine bleeding using IETA-1 multinomial regression model: validation study.

OBJECTIVES: To assess the ability of the International Endometrial Tumor Analysis (IETA)-1 polynomial regression model to estimate the risk of endometrial cancer (EC) and other intracavitary uterine pathology in women without abnormal uterine bleeding. METHODS: This was a retrospective study, in which we validated the IETA-1 model on the IETA-3 study cohort (n = 1745). The IETA-3 study is a prospective observational multicenter study. It includes women without vaginal bleeding who underwent a standardized transvaginal ultrasound examination in one of seven ultrasound centers between January 2011 and December 2018. The ultrasonography was performed either as part of a routine gynecological examination, during follow-up of non-endometrial pathology, in the work-up before fertility treatment or before treatment for uterine prolapse or ovarian pathology. Ultrasonographic findings were described using IETA terminology and were compared with histology, or with results of clinical and ultrasound follow-up of at least 1 year if endometrial sampling was not performed. The IETA-1 model, which was created using data from patients with abnormal uterine bleeding, predicts four histological outcomes: (1) EC or endometrial intraepithelial neoplasia (EIN); (2) endometrial polyp or intracavitary myoma; (3) proliferative or secretory endometrium, endometritis, or endometrial hyperplasia without atypia; and (4) endometrial atrophy. The predictors in the model are age, body mass index and seven ultrasound variables (visibility of the endometrium, endometrial thickness, color score, cysts in the endometrium, non-uniform echogenicity of the endometrium, presence of a bright edge, presence of a single dominant vessel). We analyzed the discriminative ability of the model (area under the receiver-operating-characteristics curve (AUC); polytomous discrimination index (PDI)) and evaluated calibration of its risk estimates (observed/expected ratio). RESULTS: The median age of the women in the IETA-3 cohort was 51 (range, 20-85) years and 51% (887/1745) of the women were postmenopausal. Histology showed EC or EIN in 29 (2%) women, endometrial polyps or intracavitary myomas in 1094 (63%), proliferative or secretory endometrium, endometritis, or hyperplasia without atypia in 144 (8%) and endometrial atrophy in 265 (15%) women. The endometrial sample had insufficient material in five (0.3%) cases. In 208 (12%) women who did not undergo endometrial sampling but were followed up for at least 1 year without clinical or ultrasound signs of endometrial malignancy, the outcome was classified as benign. The IETA-1 model had an AUC of 0.81 (95% CI, 0.73-0.89, n = 1745) for discrimination between malignant (EC or EIN) and benign endometrium, and the observed/expected ratio for EC or EIN was 0.51 (95% CI, 0.32-0.82). The model was able to categorize the four histological outcomes with considerable accuracy: the PDI of the model was 0.68 (95% CI, 0.62-0.73) (n = 1532). The IETA-1 model discriminated very well between endometrial atrophy and all other intracavitary uterine conditions, with an AUC of 0.96 (95% CI, 0.95-0.98). Including only patients in whom the endometrium was measurable (n = 1689), the model's AUC was 0.83 (95% CI, 0.75-0.91), compared with 0.62 (95% CI, 0.52-0.73) when using endometrial thickness alone to predict malignancy (difference in AUC, 0.21; 95% CI, 0.08-0.32). In postmenopausal women with measurable endometrial thickness (n = 848), the IETA-1 model gave an AUC of 0.81 (95% CI, 0.71-0.91), while endometrial thickness alone gave an AUC of 0.70 (95% CI, 0.60-0.81) (difference in AUC, 0.11; 95% CI, 0.01-0.20). CONCLUSION: The IETA-1 model discriminates well between benign and malignant conditions in the uterine cavity in patients without abnormal bleeding, but it overestimates the risk of malignancy. It also discriminates well between the four histological outcome categories. © 2023 International Society of Ultrasound in Obstetrics and Gynecology.

Addendum to the consensus opinion from the International Deep Endometriosis Analysis (IDEA) group: sonographic evaluation of the parametrium.

Preoperative sonographic staging in patients with suspected parametrial endometriosis is essential to plan the surgical intervention and to anticipate the need for a multidisciplinary approach, and hence optimize surgical outcome. The results of a recent metanalysis suggest that defining more accurately the ultrasonographic criteria of parametrial involvement in endometriosis is needed. The aim of this addendum to the IDEA-consensus is to highlight the sonographic characteristics of the parametrium and identify ultrasound techniques to diagnose deep endometriosis in this area. This article is protected by copyright. All rights reserved.

Subjective assessment and IOTA ADNEX model in evaluation of adnexal masses in patients with history of breast cancer.

OBJECTIVE: To evaluate the performance of subjective assessment and the Assessment of Different NEoplasias in the adneXa (ADNEX) model in discriminating between benign and malignant adnexal tumors and between metastatic and primary adnexal tumors in patients with a personal history of breast cancer. METHODS: This was a retrospective single-center study including patients with a history of breast cancer who underwent surgery for an adnexal mass between 2013 and 2020. All patients had been examined with transvaginal or transrectal ultrasound using a standardized examination technique and all ultrasound reports had been stored and were retrieved for the purposes of this study. The specific diagnosis suggested by the original ultrasound examiner in the retrieved report was analyzed. For each mass, the ADNEX model risks were calculated prospectively and the highest relative risk was used to categorize each into one of five categories (benign, borderline, primary Stage I, primary Stages II-IV or metastatic ovarian cancer) for analysis of the ADNEX model in predicting the specific tumor type. The performance of subjective assessment and the ADNEX model in discriminating between benign and malignant adnexal tumors and between primary and metastatic adnexal tumors was evaluated, using final histology as the reference standard. RESULTS: Included in the study were 202 women with a history of breast cancer who underwent surgery for an adnexal mass. At histology, 93/202 (46.0%) masses were benign, 76/202 (37.6%) were primary malignancies (four borderline and 72 invasive tumors) and 33/202 (16.3%) were metastases. The original ultrasound examiner classified correctly 79/93 (84.9%) benign adnexal masses, 72/76 (94.7%) primary adnexal malignancies and 30/33 (90.9%) metastatic tumors. Subjective ultrasound evaluation had a sensitivity of 93.6%, specificity of 84.9% and accuracy of 89.6%, while the ADNEX model had higher sensitivity (98.2%) but lower specificity (78.5%), with similar accuracy (89.1%), in discriminating between benign and malignant ovarian masses. Subjective evaluation had a sensitivity of 51.5%, specificity of 88.8% and accuracy of 82.7% in distinguishing metastatic and primary tumors (including benign, borderline and invasive tumors), and the ADNEX model had a sensitivity of 63.6%, specificity of 84.6% and similar accuracy (81.2%). CONCLUSIONS: The performance of subjective assessment and the ADNEX model in discriminating between benign and malignant adnexal masses in this series of patients with history of breast cancer was relatively similar. Both subjective assessment and the ADNEX model demonstrated good accuracy and specificity in discriminating between metastatic and primary tumors, but the sensitivity was low. © 2023 International Society of Ultrasound in Obstetrics and Gynecology.

Using IOTA terminology to evaluate fetal ovarian cysts: analysis of 51 cysts over 10-year period.

OBJECTIVES: To describe ultrasound features of fetal ovarian cysts as reported by the original ultrasound examiner, to apply International Ovarian Tumor Analysis (IOTA) terminology after retrospective analysis of the images and to describe patient management and evolution of fetal cysts during pregnancy and after delivery. METHODS: This retrospective observational study included pregnant women diagnosed on ultrasound examination with a fetal ovarian cyst at the Prenatal Diagnosis Division of the Bambino Gesù Children's Hospital, in Rome, between March 2011 and May 2020. Cysts were classified by the original ultrasound examiner as 'simple' (unilocular anechoic cyst) or 'complex' (cyst with other morphology). In addition, three ultrasound examiners, experienced in gynecologic ultrasound, classified retrospectively the fetal ovarian cysts according to IOTA terminology, by reviewing stored ultrasound images. The evolution of these fetal ovarian cysts during pregnancy and after birth was recorded. RESULTS: Included were 51 ovarian cysts in 48 fetuses. Of the 51 cysts, 29 (56.9%) had been classified by the original ultrasound examiner as 'simple', and 22 (43.1%) as 'complex'. Of the simple cysts, the majority (20/29 (69.0%)) resolved spontaneously after delivery, 2/29 (6.9%) resolved following intrauterine aspiration, 2/29 (6.9%) resolved after postnatal aspiration and 5/29 (17.2%) underwent surgery due to persistence after delivery; in all five, normal ovarian parenchyma without signs of necrosis was observed at histology. Of the complex cysts, 7/22 (31.8%) resolved spontaneously. The other 15/22 (68.2%) were removed surgically and, at histology, necrosis was observed in most (12/15 (80.0%)), while a benign epithelial cyst with normal ovarian parenchyma was observed in 3/15 (20%). After reviewing the ultrasound images and applying IOTA terminology, all 51 (100%) fetal cysts were described as unilocular; 29/51 (56.9%) cysts showed anechoic content (described as simple cysts by the original ultrasound examiner), and 10/51 (19.6%) had low-level, 1/51 (2.0%) had ground-glass, 9/51 (17.6%) had hemorrhagic, 1/51 (2.0%) had mixed and 1/51 (2.0%) had undefined content (all described as complex by the original ultrasound examiner). Among the 29 anechoic ovarian cysts, resolution was observed in most (24/29, 82.8%) cases. Similarly, resolution was observed in 7/10 (70.0%) cysts with low-level content. Resolution was not observed in any of the other 12 cysts and all of these cases underwent surgery, with evidence of necrosis being observed in 11 (91.7%). CONCLUSIONS: Applying IOTA terminology provided a more detailed and accurate description of fetal ovarian cysts compared with the original classification into 'simple' and 'complex' categories. Anechoic cysts (described as simple cysts by the original ultrasound examiner) and cysts with low-level content (described as complex by the original ultrasound examiner) frequently resolved spontaneously. Cysts with ground-glass, hemorrhagic, mixed or undefined content were frequently associated with necrosis at histology following surgery. © 2022 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

Benign descriptors and ADNEX in two-step strategy to estimate risk of malignancy in ovarian tumors: retrospective validation in IOTA5 multicenter cohort.

OBJECTIVE: Previous work has suggested that the ultrasound-based benign simple descriptors (BDs) can reliably exclude malignancy in a large proportion of women presenting with an adnexal mass. This study aimed to validate a modified version of the BDs and to validate a two-step strategy to estimate the risk of malignancy, in which the modified BDs are followed by the Assessment of Different NEoplasias in the adneXa (ADNEX) model if modified BDs do not apply. METHODS: This was a retrospective analysis using data from the 2-year interim analysis of the International Ovarian Tumor Analysis (IOTA) Phase-5 study, in which consecutive patients with at least one adnexal mass were recruited irrespective of subsequent management (conservative or surgery). The main outcome was classification of tumors as benign or malignant, based on histology or on clinical and ultrasound information during 1 year of follow-up. Multiple imputation was used when outcome based on follow-up was uncertain according to predefined criteria. RESULTS: A total of 8519 patients were recruited at 36 centers between 2012 and 2015. We excluded patients who were already in follow-up at recruitment and all patients from 19 centers that did not fulfil our criteria for good-quality surgical and follow-up data, leaving 4905 patients across 17 centers for statistical analysis. Overall, 3441 (70%) tumors were benign, 978 (20%) malignant and 486 (10%) uncertain. The modified BDs were applicable in 1798/4905 (37%) tumors, of which 1786 (99.3%) were benign. The two-step strategy based on ADNEX without CA125 had an area under the receiver-operating-characteristics curve (AUC) of 0.94 (95% CI, 0.92-0.96). The risk of malignancy was slightly underestimated, but calibration varied between centers. A sensitivity analysis in which we expanded the definition of uncertain outcome resulted in 1419 (29%) tumors with uncertain outcome and an AUC of the two-step strategy without CA125 of 0.93 (95% CI, 0.91-0.95). CONCLUSION: A large proportion of adnexal masses can be classified as benign by the modified BDs. For the remaining masses, the ADNEX model can be used to estimate the risk of malignancy. This two-step strategy is convenient for clinical use. © 2022 The Authors. Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

Ultrasound features of endometrial pathology in women without abnormal uterine bleeding: results from the International Endometrial Tumor Analysis study (IETA3).

OBJECTIVES: The primary aim of this study was to describe the ultrasound features of various endometrial and other intracavitary pathologies in women without abnormal uterine bleeding (AUB) using the International Endometrial Tumor Analysis (IETA) terminology. The secondary aim was to compare our findings with published data on women with AUB. METHODS: This was a prospective observational study of women presenting at one of seven centers specialized in gynecological ultrasonography, from 2011 until 2018, for indications unrelated to AUB. All patients underwent transvaginal ultrasound using the IETA examination and measurement techniques. Ultrasonography was performed as part of routine gynecological examination or follow-up of non-endometrial pathology, or as part of the work-up before undergoing treatment for infertility, uterine prolapse or ovarian pathology. Ultrasound findings were described using the IETA terminology. Endometrial sampling was performed after the ultrasound scan. The histological endpoints were endometrial atrophy, proliferative or secretory endometrium, endometrial hyperplasia without atypia, endometrial polyp, intracavitary leiomyoma, endometrial intraepithelial neoplasia (EIN), endometrial cancer (EC) and insufficient tissue. The findings in our cohort of women without AUB were compared with those in a published cohort of women with AUB who were examined with transvaginal ultrasound between 2012 and 2015 using the same IETA examination technique and terminology. RESULTS: In this study (IETA3), we included 1745 women without AUB who underwent a standardized transvaginal ultrasound examination followed by either endometrial sampling with histological diagnosis (n = 1537) or at least 1 year of clinical and ultrasound follow-up (n = 208). Of these, 858 (49.2%) women were premenopausal and 887 (50.8%) were postmenopausal. Histology showed the presence of EC and/or EIN in 29 (1.7%) women, endometrial polyps in 1028 (58.9%), intracavitary myomas in 66 (3.8%), proliferative or secretory changes or hyperplasia without atypia in 144 (8.3%), endometrial atrophy in 265 (15.2%) and insufficient tissue in five (0.3%). Most cases of EC or EIN (25/29 (86.2%)) were diagnosed after menopause. The mean endometrial thickness in women with EC or EIN was 11.2 mm (95% CI, 8.9-13.6 mm), being on average 2.4 mm (95% CI, 0.3-4.6 mm) thicker than their benign counterparts. Women with malignant endometrial pathology manifested more frequently non-uniform echogenicity (22/29 (75.9%)) than did those with benign endometrial pathology (929/1716 (54.1%)) (difference, +21.8% (95% CI, +4.2% to +39.2%)). Moderate to abundant vascularization (color score 3-4) was seen in 31.0% (9/29) of cases with EC or EIN compared with 12.8% (220/1716) of those with a benign outcome (difference, +18.2% (95% CI, -0.5% to +36.9%)). Multiple multifocal vessels were recorded in 24.1% (7/29) women with EC or EIN vs 4.0% (68/1716) of those with a benign outcome (difference, +20.2% (95% CI, +4.6% to +35.7%)). A regular endometrial-myometrial junction was seen less frequently in women with EC or EIN (19/29 (65.5%)) vs those with a benign outcome (1412/1716 (82.3%)) (difference, -16.8% (95% CI, -34.2% to +0.6%)). In women with endometrial polyps without AUB, a single dominant vessel was the most frequent vascular pattern (666/1028 (64.8%)). In women with EC, both in those with and those without AUB, the endometrium usually manifested heterogeneous echogenicity, but the endometrium was on average 8.6 mm (95% CI, 5.2-12.0 mm) thinner and less intensely vascularized (color score 3-4: difference, -26.8% (95% CI, -52.2% to -1.3%)) in women without compared to those with AUB. In both pre- and postmenopausal women, asymptomatic endometrial polyps were associated with a thinner endometrium, and they manifested more frequently a bright edge, a regular endometrial-myometrial junction and a single dominant vessel than did polyps in symptomatic women, and they were less intensely vascularized. CONCLUSIONS: We describe the typical ultrasound features of EC, polyps and other intracavitary histologies using IETA terminology in women without AUB. Our findings suggest that the presence of asymptomatic polyps or endometrial malignancy may be accompanied by thinner and less intensely vascularized endometria than their symptomatic counterparts. © 2022 International Society of Ultrasound in Obstetrics and Gynecology.

Imaging in gynecological disease (24): clinical and ultrasound characteristics of ovarian mature cystic teratomas.

OBJECTIVE: To describe the clinical and ultrasound features of ovarian mature cystic teratomas (MCTs). METHODS: This was a retrospective study. From the International Ovarian Tumor Analysis (IOTA) database, we identified patients with a histologically confirmed diagnosis of MCT who had undergone transvaginal ultrasound examination between 1999 and 2016 (IOTA phases 1, 2, 3 and 5) in one of five centers. Ultrasound was performed by an experienced examiner who used the standardized IOTA examination technique and terminology. In addition to extracting data from the IOTA database, available two-dimensional grayscale and color or power Doppler images were reviewed retrospectively to identify typical ultrasound features of MCT described previously and detect possible new features using pattern recognition. All images were reviewed by two independent examiners and further discussed with two ultrasound experts to reach consensus. RESULTS: Included in the study were 454 patients with histologically confirmed MCT. Median age was 33 (range, 8-90) years and 66 (14.5%) patients were postmenopausal. Most MCTs were described by the original ultrasound examiner as unilocular (262/454 (57.7%)) or multilocular (70/454 (15.4%)) cysts with mixed echogenicity of cystic fluid (368/454 (81.1%)), acoustic shadowing (328/454 (72.2%)) and no or little vascularization on color Doppler (color score 1, 240/454 (52.9%); color score 2, 123/454 (27.1%)). The median largest lesion diameter was 66 (range, 15-310) mm. A correct preoperative diagnosis of MCT was suggested by the original ultrasound examiner in 372/454 (81.9%) cases. On retrospective review of ultrasound images of 334 MCTs that had quality sufficient for assessment, 'dots and/or lines' and/or 'echogenic white ball' (typical features according to the literature) were present in 271/334 (81.1%) masses. We identified four new ultrasound features characteristic of MCT: 'cotton wool tufts', 'mushroom cap sign', 'completely hyperechogenic lesion' and 'starry sky sign'. At least one classical or novel ultrasound feature was present in 315/334 (94.3%) MCTs. Twenty-nine (8.7%) MCTs manifested vascularized solid tissue, of which seven exhibited no typical features. CONCLUSION: We provide a comprehensive overview of conventional and newly described ultrasound features of MCTs. Only a small proportion of MCTs did not manifest any of the typical features. © 2022 International Society of Ultrasound in Obstetrics and Gynecology.

Developing and validating ultrasound-based radiomics models for predicting high-risk endometrial cancer.

OBJECTIVES: The primary aim of this study was to develop and validate radiomics models, applied to ultrasound images, capable of differentiating from other cancers high-risk endometrial cancer, as defined jointly by the European Society for Medical Oncology, European Society of Gynaecological Oncology and European Society for Radiotherapy & Oncology (ESMO-ESGO-ESTRO) in 2016. The secondary aim was to develop and validate radiomics models for differentiating low-risk endometrial cancer from other endometrial cancers. METHODS: This was a multicenter, retrospective, observational study. From two participating centers, we identified consecutive patients with histologically confirmed diagnosis of endometrial cancer who had undergone preoperative ultrasound examination by an experienced examiner between 2016 and 2019. Patients recruited in Center 1 (Rome) were included as the training set and patients enrolled in Center 2 (Milan) formed the external validation set. Radiomics analysis (extraction of a high number of quantitative features from medical images) was applied to the ultrasound images. Clinical (including preoperative biopsy), ultrasound and radiomics features that were statistically significantly different in the high-risk group vs the other groups and in the low-risk group vs the other groups on univariate analysis in the training set were considered for multivariate analysis and for developing ultrasound-based machine-learning risk-prediction models. For discriminating between the high-risk group and the other groups, a random forest model from the radiomics features (radiomics model), a binary logistic regression model from clinical and ultrasound features (clinical-ultrasound model) and another binary logistic regression model from clinical, ultrasound and previously selected radiomics features (mixed model) were created. Similar models were created for discriminating between the low-risk group and the other groups. The models developed in the training set were tested in the validation set. The performance of the models in discriminating between the high-risk group and the other groups, and between the low-risk group and the other risk groups for both validation and training sets was compared. RESULTS: The training set comprised 396 patients and the validation set 102 patients. In the validation set, for predicting high-risk endometrial cancer, the radiomics model had an area under the receiver-operating-characteristics curve (AUC) of 0.80, sensitivity of 58.7% and specificity of 85.7% (using the optimal risk cut-off of 0.41); the clinical-ultrasound model had an AUC of 0.90, sensitivity of 80.4% and specificity of 83.9% (using the optimal cut-off of 0.32); and the mixed model had an AUC of 0.88, sensitivity of 67.3% and specificity of 91.0% (using the optimal cut-off of 0.42). For the prediction of low-risk endometrial cancer, the radiomics model had an AUC of 0.71, sensitivity of 65.0% and specificity of 64.5% (using the optimal cut-off of 0.38); the clinical-ultrasound model had an AUC of 0.85, sensitivity of 70.0% and specificity of 80.6% (using the optimal cut-off of 0.46); and the mixed model had an AUC of 0.85, sensitivity of 87.5% and specificity of 72.5% (using the optimal cut-off of 0.36). CONCLUSIONS: Radiomics seems to have some ability to discriminate between low-risk endometrial cancer and other endometrial cancers and better ability to discriminate between high-risk endometrial cancer and other endometrial cancers. However, the addition of radiomics features to the clinical-ultrasound models did not result in any notable increase in performance. Other efficacy studies and further effectiveness studies are needed to validate the performance of the models. © 2021 International Society of Ultrasound in Obstetrics and Gynecology.