D. Franchi

Ultrasound examiners' ability to describe ovarian cancer spread using preacquired ultrasound videoclips from a selected patient sample with high prevalence of cancer spread

ABSTRACTObjectivesTo assess the ability, as well as factors affecting the ability, of ultrasound examiners with different levels of ultrasound experience to detect correctly infiltration of ovarian cancer in predefined anatomical locations, and to evaluate the inter‐rater agreement regarding the presence or absence of cancer infiltration, using preacquired ultrasound videoclips obtained in a selected patient sample with a high prevalence of cancer spread.MethodsThis study forms part of the Imaging Study in Advanced ovArian Cancer multicenter observational study (NCT03808792). Ultrasound videoclips showing assessment of infiltration of ovarian cancer were obtained by the principal investigator (an ultrasound expert, who did not participate in rating) at 19 predefined anatomical sites in the abdomen and pelvis, including five sites that, if infiltrated, would indicate tumor non‐resectability. For each site, there were 10 videoclips showing cancer infiltration and 10 showing no cancer infiltration. The reference standard was either findings at surgery with histological confirmation or response to chemotherapy. For statistical analysis, the 19 sites were grouped into four anatomical regions: pelvis, middle abdomen, upper abdomen and lymph nodes. The videoclips were assessed by raters comprising both senior gynecologists (mainly self‐trained expert ultrasound examiners who perform preoperative ultrasound assessment of ovarian cancer spread almost daily) and gynecologists who had undergone a minimum of 6 months' supervised training in the preoperative ultrasound assessment of ovarian cancer spread in a gynecological oncology center. The raters were classified as highly experienced or less experienced based on annual individual caseload and the number of years that they had been performing ultrasound evaluation of ovarian cancer spread. Raters were aware that for each site there would be 10 videoclips with and 10 without cancer infiltration. Each rater independently classified every videoclip as showing or not showing cancer infiltration and rated the image quality (on a scale from 0 to 10) and their diagnostic confidence (on a scale from 0 to 10). A generalized linear mixed model with random effects was used to estimate which factors (including level of experience, image quality, diagnostic confidence and anatomical region) affected the likelihood of a correct classification of cancer infiltration. We assessed the observed percentage of videoclips classified correctly, the expected percentage of videoclips classified correctly based on the generalized linear mixed model and inter‐rater agreement (reliability) in classifying anatomical sites as being infiltrated by cancer.ResultsTwenty‐five raters participated in the study, of whom 13 were highly experienced and 12 were less experienced. The observed percentage of correct classification of cancer infiltration ranged from 70% to 100% depending on rater and anatomical site, and the median percentage of correct classification for the 25 raters ranged from 90% to 100%. The probability of correct classification of all 380 videoclips ranged from 0.956 to 0.975 and was not affected by the rater's level of ultrasound experience. The likelihood of correct classification increased with increased image quality and diagnostic confidence and was affected by anatomical region. It was highest for sites in the pelvis, second highest for those in the middle abdomen, third highest for lymph nodes and lowest for sites in the upper abdomen. The inter‐rater agreement of all 25 raters regarding the presence of cancer infiltration ranged from substantial (Fleiss kappa, 0.68 (95% CI, 0.66–0.71)) to very good (Fleiss kappa, 0.99 (95% CI, 0.97–1.00)) depending on the anatomical site. It was lowest for sites in the upper abdomen (Fleiss kappa, 0.68 (95% CI, 0.66–0.71) to 0.97 (95% CI, 0.94–0.99)) and highest for sites in the pelvis (Fleiss kappa, 0.94 (95% CI, 0.92–0.97) to 0.99 (95% CI, 0.97–1.00)).ConclusionsUltrasound examiners with different levels of ultrasound experience can classify correctly predefined anatomical sites as being infiltrated or not infiltrated by ovarian cancer based on video recordings obtained by an experienced ultrasound examiner, and the inter‐rater agreement is substantial. The likelihood of correct classification as well as the inter‐rater agreement is highest for sites in the pelvis and lowest for sites in the upper abdomen. However, owing to the study design, our results regarding diagnostic accuracy and inter‐rater agreement are likely to be overoptimistic. © 2025 The Author(s). Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

Reply to letter to editor on “Expectant management of borderline ovarian tumor during pregnancy”

Comparison of ultrasound with computed tomography and whole‐body diffusion‐weighted MRI in prediction of surgical outcome using ESMO ‐ ESGO criteria in patients with tubo‐ovarian carcinoma: prospective ISAAC study

ABSTRACT Objective To test the non‐inferiority of extended abdominopelvic ultrasound examination compared with contrast‐enhanced computed tomography (CT) and whole‐body diffusion‐weighted magnetic resonance imaging (WB‐DWI/MRI) in discriminating preoperatively between resectable and non‐resectable disease based on the European Society for Medical Oncology (ESMO) and European Society of Gynecological Oncology (ESGO)‐defined criteria in patients with tubo‐ovarian carcinoma. Methods The Imaging Study on Advanced ovArian Cancer was a prospective multicenter observational study conducted in five European gynecological oncology centers. All centers had ESGO accreditation to perform advanced ovarian cancer surgery, and ultrasound examinations were performed by a European Federation of Societies for Ultrasound in Medicine and Biology level‐III examiner in a standardized manner. Included in the analysis were patients enrolled between 2020 and 2022 with suspected or histologically proven primary tubo‐ovarian (including peritoneal) carcinoma who, for the purposes of the study, underwent ultrasound and CT imaging, as well as WB‐DWI/MRI if available, prior to surgery. The index tests, which included the preoperative imaging modalities as well as intraoperative exploration at the start of surgery, supplemented by biopsy or follow‐up imaging for extra‐abdominal locations, evaluated the presence of disease at eight anatomical sites that, if infiltrated, would indicate non‐resectability of the tumor according to the ESMO‐ESGO criteria. Surgical outcome, described by the surgeons at the end of the procedure, was used as the reference standard and non‐resectability was defined as the presence of residual disease > 1 cm or when debulking surgery was not feasible. The area under the receiver‐operating‐characteristics curve (AUC) and F 1  score were used to assess the performance of the preoperative imaging methods and surgical exploration in discriminating between patients with resectable and those with non‐resectable disease, based on the ESMO‐ESGO criteria. We also calculated the percentage agreement between imaging findings and surgical exploration findings at the start of surgery, supplemented when applicable by biopsy or follow‐up imaging for extra‐abdominal locations, regarding the presence of tumor infiltration at each of the eight anatomical sites associated with non‐resectability. Results Of 279 patients enrolled during the study period, 242 were included in the final analysis. In the subgroup of 167 patients who underwent surgery and had been examined by all three imaging methods, the AUC of the three imaging modalities and surgical exploration for discriminating between resectable and non‐resectable disease based on the ESMO‐ESGO criteria was 0.835 (95% CI, 0.756–0.915) for ultrasound, for CT it was 0.754 (95% CI, 0.664–0.843), for WB‐DWI/MRI it was 0.720 (95% CI, 0.626–0.814) and for surgical exploration it was 0.952 (95% CI, 0.915–0.988). Ultrasound was not inferior to CT or WB‐DWI/MRI, based on the AUC and F 1 score, in discriminating between patients with resectable and those with non‐resectable tubo‐ovarian carcinoma. At surgical exploration, at least one non‐resectability criterion was present in 32.2% cases. The criteria observed most frequently at surgical exploration were small‐bowel involvement (23.6% of cases), diffuse deep infiltration of the root of the small‐bowel mesentery (18.2% of cases) and hepatic hilum involvement (5.4% of cases). The percentage agreement between ultrasound and surgical exploration in assessing the presence of disease in at least one of the eight anatomical sites that, if infiltrated, would indicate non‐resectability of tumor, was 83.9%, surpassing the percentage agreement with surgical exploration of both CT (77.7%) and WB‐DWI/MRI (75.8%). Conclusion When performed by an experienced examiner, ultrasound is not inferior to either CT or WB‐DWI/MRI in discriminating between resectable and non‐resectable disease in patients with tubo‐ovarian carcinoma, based on evaluation of the presence of the disease in at least one of eight anatomical sites that, if infiltrated, would indicate non‐resectability of the tumor. © 2025 The Author(s). Ultrasound in Obstetrics & Gynecology published by John Wiley & Sons Ltd on behalf of International Society of Ultrasound in Obstetrics and Gynecology.

International multicenter validation of AI-driven ultrasound detection of ovarian cancer

Abstract Ovarian lesions are common and often incidentally detected. A critical shortage of expert ultrasound examiners has raised concerns of unnecessary interventions and delayed cancer diagnoses. Deep learning has shown promising results in the detection of ovarian cancer in ultrasound images; however, external validation is lacking. In this international multicenter retrospective study, we developed and validated transformer-based neural network models using a comprehensive dataset of 17,119 ultrasound images from 3,652 patients across 20 centers in eight countries. Using a leave-one-center-out cross-validation scheme, for each center in turn, we trained a model using data from the remaining centers. The models demonstrated robust performance across centers, ultrasound systems, histological diagnoses and patient age groups, significantly outperforming both expert and non-expert examiners on all evaluated metrics, namely F1 score, sensitivity, specificity, accuracy, Cohen’s kappa, Matthew’s correlation coefficient, diagnostic odds ratio and Youden’s J statistic. Furthermore, in a retrospective triage simulation, artificial intelligence (AI)-driven diagnostic support reduced referrals to experts by 63% while significantly surpassing the diagnostic performance of the current practice. These results show that transformer-based models exhibit strong generalization and above human expert-level diagnostic accuracy, with the potential to alleviate the shortage of expert ultrasound examiners and improve patient outcomes.

Imaging Study in Advanced Ovarian Cancer

The aim of the study is the assessment of tumour sites critical for the achievement of optimal cytoreduction in patients with advanced ovarian cancer using Ultrasound, CT and WB-DWI/MRI. The study uses an equivalence design with a hypothesis that cases with non-resectable disease identified by Index test (Ultrasound, CT and WB-DWI MRI) are equivalent to a portion of cases identified during surgery.