ADNEX-AI : automated extraction of ultrasound predictors for interpretable ovarian cancer risk stratification
(2025) In NPJ precision oncology 10(1).- Abstract
Accurate triage of ovarian masses is facilitated in many centers by the guideline-endorsed, extensively validated IOTA-ADNEX risk model, yet the model still relies on manual measurements of key tumor features. We developed ADNEX-AI, a multi-task deep-learning system that automatically segments four ADNEX ultrasound predictors – lesion, locules, solid tissue, papillary projections – and outputs their quantitative values. The network was trained on 816 annotated images from 369 consecutive women recruited at 11 centers (43% malignancies) and prospectively evaluated on a temporally separate cohort of 1088 patients scanned at 10 of those centers (8008 images; 35% malignancies). ADNEX-AI discriminated benign from malignant tumors with an AUC... (More)
Accurate triage of ovarian masses is facilitated in many centers by the guideline-endorsed, extensively validated IOTA-ADNEX risk model, yet the model still relies on manual measurements of key tumor features. We developed ADNEX-AI, a multi-task deep-learning system that automatically segments four ADNEX ultrasound predictors – lesion, locules, solid tissue, papillary projections – and outputs their quantitative values. The network was trained on 816 annotated images from 369 consecutive women recruited at 11 centers (43% malignancies) and prospectively evaluated on a temporally separate cohort of 1088 patients scanned at 10 of those centers (8008 images; 35% malignancies). ADNEX-AI discriminated benign from malignant tumors with an AUC of 0.930 (95% CI 0.913-0.943), less than but close to examiner-derived ADNEX (0.945; 0.930-0.957; P = 0.004) while delivering better calibration and markedly lower inter-center variability. By removing manual caliper work yet preserving full interpretability, ADNEX-AI could extend high-quality ovarian-cancer risk stratification to clinics that lack specialized ultrasound expertise.
(Less)
- author
- organization
- publishing date
- 2025-12-11
- type
- Contribution to journal
- publication status
- published
- subject
- in
- NPJ precision oncology
- volume
- 10
- issue
- 1
- article number
- 18
- publisher
- Springer Nature
- external identifiers
-
- scopus:105027400201
- pmid:41381738
- ISSN
- 2397-768X
- DOI
- 10.1038/s41698-025-01215-x
- language
- English
- LU publication?
- yes
- additional info
- Publisher Copyright: © The Author(s) 2025.
- id
- 90be60d9-2426-43de-83bf-fe5373f52937
- date added to LUP
- 2026-03-09 15:07:29
- date last changed
- 2026-06-16 05:00:49
@article{90be60d9-2426-43de-83bf-fe5373f52937,
abstract = {{<p>Accurate triage of ovarian masses is facilitated in many centers by the guideline-endorsed, extensively validated IOTA-ADNEX risk model, yet the model still relies on manual measurements of key tumor features. We developed ADNEX-AI, a multi-task deep-learning system that automatically segments four ADNEX ultrasound predictors – lesion, locules, solid tissue, papillary projections – and outputs their quantitative values. The network was trained on 816 annotated images from 369 consecutive women recruited at 11 centers (43% malignancies) and prospectively evaluated on a temporally separate cohort of 1088 patients scanned at 10 of those centers (8008 images; 35% malignancies). ADNEX-AI discriminated benign from malignant tumors with an AUC of 0.930 (95% CI 0.913-0.943), less than but close to examiner-derived ADNEX (0.945; 0.930-0.957; P = 0.004) while delivering better calibration and markedly lower inter-center variability. By removing manual caliper work yet preserving full interpretability, ADNEX-AI could extend high-quality ovarian-cancer risk stratification to clinics that lack specialized ultrasound expertise.</p>}},
author = {{Geysels, Axel and Garofalo, Giulia and Timmerman, Stefan and Ceusters, Jolien and Buonomo, Francesca and Fischerová, Daniela and Testa, Antonia Carla and Moro, Francesca and Sladkevicius, Povilas and Jokubkiene, Ligita and Van Holsbeke, Caroline and Kudla, Marek and Czekierdowski, Artur and Epstein, Elisabeth and Groszmann, Yvette and Blaschko, Matthew and Bourne, Tom and De Moor, Bart and Valentin, Lil and Van Calster, Ben and Timmerman, Dirk and Froyman, Wouter}},
issn = {{2397-768X}},
language = {{eng}},
month = {{12}},
number = {{1}},
publisher = {{Springer Nature}},
series = {{NPJ precision oncology}},
title = {{ADNEX-AI : automated extraction of ultrasound predictors for interpretable ovarian cancer risk stratification}},
url = {{http://dx.doi.org/10.1038/s41698-025-01215-x}},
doi = {{10.1038/s41698-025-01215-x}},
volume = {{10}},
year = {{2025}},
}
