OP03.05: Detection of Vulvar International Tumor Analysis criteria among sonographers in lymph node evaluation: interrater reliability study
Year: 2024
Type: conference-abstract
Abstract: Results: Fifty studies were included; of these 37/50 (74.0%) on ovarian masses or ovarian cancer, 5/50 (10.0%) on endometrial cancer, 5/50 (10.0%) on cervical cancer and 3/50 (6.0%) on other malignancies.Most studies were at high risk of bias for subject selection and index test domains, whereas there was a generally low risk of bias for reference standard and workflow domains.35/50 (70.0%) studies were single-centre studies while 7/50 (14.0%) multicentre.32/50 (64.0%) studies included less than 500 women, while four studies more than 1,000.Most studies presented machine learning models (33/50, 66.0%) for the diagnosis and histopathological correlation of ovarian masses detected on ultrasound, while others focused on automatic segmentation, reproducibility of radiomics features, improvement of image quality, prediction of therapy resistance, progression free survival and genetic mutation.Conclusions: The published literature on AI applied to ultrasound in gynecology oncology focused mostly on histopathological correlation of ovarian masses.The current evidence supports the role of AI as a complementary clinical and research tool in diagnosis, patient stratification and prediction of histopathological correlation in gynecological malignancies.
DOI: 10.1002/uog.27896
Language: English
Topic: AI in cancer detection
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4402359722