We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
OC05.01: *Prospective validation of an end‐to‐end machine learning‐based model for the classification of adnexal masses using ultrasonography.
- Authors
Barcroft, J.; Linton‐Reid, K.; Munaretto, M.; Fantauzzi, M.; Kim, J.; Murugesu, S.; Parker, N.; Kyriacou, C.; Novak, A.M.; Pikovsky, M.; Cooper, N.; Lee, S.; Savelli, L.; Thomson, A.R.; Yazbek, J.; Stalder, C.; Bharwani, N.; Posma, J.; Timmerman, D.; Al‐Memar, M.
- Abstract
This article discusses the validation of a machine learning model for classifying adnexal masses using ultrasonography. The model was tested on two cohorts of women with adnexal masses, one in London and one in Seoul. The model's performance was compared to the Assessment of Different NEoplasia's in the adneXa (ADNEX) model. The results showed that the machine learning model had comparable performance to the ADNEX model in both cohorts. However, further validation is needed before the model can be integrated into clinical practice.
- Subjects
TRANSVAGINAL ultrasonography; PEARSON correlation (Statistics); SENSITIVITY &; specificity (Statistics); DEEP learning; RECEIVER operating characteristic curves
- Publication
Ultrasound in Obstetrics & Gynecology, 2024, Vol 64, p12
- ISSN
0960-7692
- Publication type
Article
- DOI
10.1002/uog.27748