We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
OC01.04: *AI‐driven ultrasound detection of ovarian cancer that generalises: an international multicentre validation study.
- Authors
Christiansen, F.; Konuk, E.; Ganeshan, A.; Welch, R.; Huix, J. Palés; Czekierdowski, A.; Leone, F.; Haak, L.A.; Fruscio, R.; Gaurilcikas, A.; Franchi, D.; Fischerová, D.; Mor, E.; Savelli, L.; Pascual, M.; Kudla, M.J.; Guerriero, S.; Buonomo, F.; Liuba, K.; Montik, N.
- Abstract
This article discusses the development and validation of an artificial intelligence (AI)-driven deep learning model for the detection of ovarian cancer using ultrasound images. The study collected 17,119 ultrasound images from 3,652 women with ovarian lesions from 20 centers in eight countries. The AI models demonstrated robust performance across different centers, ultrasound systems, and histological diagnoses, outperforming both expert and non-expert examiners. The introduction of AI-driven diagnostic support into clinical workflows has the potential to reduce human resource demands and improve diagnostic performance.
- Subjects
RECEIVER operating characteristic curves; ARTIFICIAL intelligence; EARLY detection of cancer; DELAYED diagnosis; DEEP learning; OVARIAN cancer
- Publication
Ultrasound in Obstetrics & Gynecology, 2024, Vol 64, p2
- ISSN
0960-7692
- Publication type
Article
- DOI
10.1002/uog.27724