Related Experiment Video
Updated: Aug 6, 2026
Murine Model for Non-invasive Imaging to Detect and Monitor Ovarian Cancer Recurrence
Published on: November 2, 2014
Artificial intelligence for the assessment of peritoneal carcinomatosis during diagnostic laparoscopy for advanced
Riccardo Oliva1, Farahdiba Zarin2, Alice Zampolini Faustini3
1Fondazione Policlinico Universitario A. Gemelli IRCCS, Gynecologic Oncology Unit, Rome, Italy; Università Cattolica del Sacro Cuore, Rome, Italy; IRCAD, Research Institute against Digestive Cancer, Strasbourg, France.
Objective:
To develop an artificial intelligence system to support intra-operative decision-making during diagnostic laparoscopy in patients with advanced ovarian cancer. Fagotti score assessment during diagnostic laparoscopy guides treatment planning by estimating surgical resectability, but its subjective, operator-dependent nature limits reproducibility and widespread use.
Methods:
Videos from patients undergoing diagnostic laparoscopy with concomitant Fagotti score assessments at a referral center were retrospectively collected and divided into a development dataset for artificial intelligence training and evaluation and an independent test dataset for validation. Frames extracted from regions of interest in diagnostic laparoscopy videos were manually segmented with anatomical structure and peritoneal carcinomatosis masks by experienced gynecologists. Deep learning models were trained to automatically identify Fagotti score-relevant frames, segment anatomical structures and peritoneal carcinomatosis, and predict video-level Fagotti score and indication to surgery. Performance was evaluated using Dice score for segmentation, F1-score for anatomical stations and indication to surgery prediction, and root mean square error for final Fagotti score assessment.
Results:
In the development dataset, the segmentation model trained on 7311 frames achieved Dice scores of 70 ± 3% for anatomical structures and 56 ± 3% for peritoneal carcinomatosis. Video-level anatomical station classification achieved F1-scores of 74 ± 3% and 73 ± 4%, Fagotti score prediction showed normalized root mean square error values of 1.39 ± 0.18 and 1.15 ± 0.08, and indication to surgery reached F1-scores of 80 ± 8% and 80 ± 2% in the development (n = 101) and independent test datasets (n = 50), respectively.
Conclusions:
This is the first artificial intelligence system to predict the feasibility of cytoreductive surgery by providing automated Fagotti score assessments from diagnostic laparoscopy videos. Its reproducible performance across datasets suggests that artificial intelligence can support surgeons through standardized intra-operative tumor burden assessment and clinical decision-making in advanced ovarian cancer.
