ADNEX-AI: automated extraction of ultrasound predictors for interpretable ovarian cancer risk stratification.
Authors
Affiliations (24)
Affiliations (24)
- STADIUS Center for Dynamical Systems, Signal Processing and Data Analytics, Department of Electrical Engineering (ESAT), KU Leuven, Leuven, Belgium.
- Department of Development and Regeneration, KU Leuven, Leuven, Belgium.
- Department of Obstetrics and Gynaecology, University Hospitals Leuven, Leuven, Belgium.
- Department of Gynaecology and Obstetrics, Hôpital Erasme, Hôpital Universitaire de Bruxelles (H.U.B.), Université Libre de Bruxelles (ULB), Brussels, Belgium.
- Laboratory of Tumour Immunology and Immunotherapy, Department of Oncology, KU Leuven, Leuven, Belgium.
- Institute for Maternal and Child Health, IRCCS "Burlo Garofolo", Trieste, Italy.
- Gynaecological Oncology Centre, Department of Obstetrics and Gynaecology, First Faculty of Medicine, Charles University and General University Hospital, Prague, Czechia.
- Department of Woman, Child and Public Health, Fondazione Policlinico Universitario Agostino Gemelli IRCCS, Rome, Italy.
- Department of Life Science and Public Health, Universita' Cattolica del Sacro Cuore, Rome, Italy.
- Saint Camillus International University of Health and Medical Sciences (UniCamillus), Rome, Italy.
- Department of Obstetrics and Gynaecology, Skåne University Hospital, Malmö, Sweden.
- Department of Clinical Sciences, Malmö, Lund University, Lund, Sweden.
- Department of Obstetrics and Gynaecology, Ziekenhuis Oost-Limburg, Genk, Belgium.
- Department of Perinatology and Oncological Gynaecology, Faculty of Medical Sciences, Medical University of Silesia, Katowice, Poland.
- Department of Gynaecological Oncology and Gynaecology, Medical University of Lublin, Lublin, Poland.
- Department of Clinical Science and Education, Södersjukhuset, Karolinska Institutet, Stockholm, Sweden.
- Department of Obstetrics and Gynaecology, Södersjukhuset, Stockholm, Sweden.
- Department of Obstetrics, Gynecology and Reproductive Biology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA, USA.
- Processing Speech and Images (PSI), Department of Electrical Engineering (ESAT), KU Leuven, Leuven, Belgium.
- Department of Obstetrics and Gynaecology, Imperial College London, London, UK.
- Department of Biomedical Data Sciences, Leiden University Medical Centre, Leiden, The Netherlands.
- Leuven Unit for Health Technology Assessment Research (LUHTAR), KU Leuven, Leuven, Belgium.
- Department of Development and Regeneration, KU Leuven, Leuven, Belgium. [email protected].
- Department of Obstetrics and Gynaecology, University Hospitals Leuven, Leuven, Belgium. [email protected].
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 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.