Artificial Intelligence for the Assessment of Peritoneal Carcinosis during Diagnostic Laparoscopy for Advanced Ovarian Cancer

2025-12-16

AI Summary

The Fagotti Score (FS), widely used for preoperative laparoscopic assessment of advanced ovarian cancer (AOC), suffers from subjectivity and poor inter-observer reproducibility. Method: We developed the first end-to-end AI system for fully automated FS prediction and surgical feasibility assessment directly from diagnostic laparoscopic videos. The system integrates key-frame detection, semantic segmentation of anatomical structures and peritoneal carcinomatosis lesions, multi-site classification, and regression-based FS estimation, jointly optimized using Dice loss, F1-score, and RMSE. Results: On the development (n=101) and independent test sets (n=50), the system achieved F1-scores of 80±8% and 80±2% for surgical indication prediction, normalized RMSE of 1.15±0.08 for FS estimation, and lesion segmentation Dice scores of 56±3%. This work establishes the first standardized, reproducible quantification of peritoneal tumor burden, overcoming operator dependency and enabling objective, data-driven preoperative decision-making.

Technology Category

• Humans and AI: Other Foundations of Human Computation & AI
• Computer Vision: Other Foundations of Computer Vision
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Advanced Ovarian Cancer (AOC) is often diagnosed at an advanced stage with peritoneal carcinosis (PC). Fagotti score (FS) assessment at diagnostic laparoscopy (DL) guides treatment planning by estimating surgical resectability, but its subjective and operator-dependent nature limits reproducibility and widespread use. Videos of patients undergoing DL with concomitant FS assessments at a referral center were retrospectively collected and divided into a development dataset, for data annotation, AI training and evaluation, and an independent test dataset, for internal validation. In the development dataset, FS-relevant frames were manually annotated for anatomical structures and PC. Deep learning models were trained to automatically identify FS-relevant frames, segment structures and PC, and predict video-level FS and indication to surgery (ItS). AI performance was evaluated using Dice score for segmentation, F1-scores for anatomical stations (AS) and ItS prediction, and root mean square error (RMSE) for final FS estimation. In the development dataset, the segmentation model trained on 7,311 frames, achieved Dice scores of 70$pm$3% for anatomical structures and 56$pm$3% for PC. Video-level AS classification achieved F1-scores of 74$pm$3% and 73$pm$4%, FS prediction showed normalized RMSE values of 1.39$pm$0.18 and 1.15$pm$0.08, and ItS reached F1-scores of 80$pm$8% and 80$pm$2% in the development (n=101) and independent test datasets (n=50), respectively. This is the first AI model to predict the feasibility of cytoreductive surgery providing automated FS estimation from DL videos. Its reproducible and reliable performance across datasets suggests that AI can support surgeons through standardized intraoperative tumor burden assessment and clinical decision-making in AOC.

Problem

• AI predicts surgical feasibility from laparoscopy videos
• Automates Fagotti score estimation for ovarian cancer assessment
• Provides standardized tumor burden evaluation to aid decisions

Innovation

• AI automatically identifies key frames and segments anatomical structures.
• Deep learning predicts Fagotti score and surgical indication from videos.
• Model standardizes tumor assessment to support clinical decision-making.