Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

ADNEX-AI : automated extraction of ultrasound predictors for interpretable ovarian cancer risk stratification

Geysels, Axel ; Garofalo, Giulia LU ; Timmerman, Stefan ; Ceusters, Jolien ; Buonomo, Francesca ; Fischerová, Daniela ; Testa, Antonia Carla ; Moro, Francesca ; Sladkevicius, Povilas LU orcid and Jokubkiene, Ligita LU , et al. (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)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; ; and (Less)
organization
publishing date
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}},
}