GLENDA: Gynecologic Laparoscopy Endometriosis Dataset

2025-08-29

AI Summary

Endometriosis (EMS) annotation data is critically scarce in gynecological laparoscopic surgery, severely hindering the development of AI models for automated diagnosis and surgical navigation. Method: We introduce GLENDA—the first publicly available, region-level laparoscopic image dataset specifically designed for EMS. Curated by clinical experts, it comprises multi-center, multi-view laparoscopic images with pixel-level lesion masks and fine-grained anatomical structure annotations. Contribution/Results: Unlike existing coarse-grained or class-level datasets, GLENDA provides the first anatomically grounded, region-level precise annotations for EMS lesions, thereby filling a critical data gap in medical AI for this disease. Organized in standardized formats, it supports segmentation, object detection, and video-based analysis tasks. GLENDA significantly enhances model training reliability and reproducibility, establishing a high-quality benchmark for intelligent EMS diagnosis and intraoperative guidance.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Language Grounding & Multi-modal NLP
• Computer Vision: Multi-modal Vision

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Security and Privacy: Data transparency and provenance
• Responsible Web: Data and user privacy-enhancing technologies for the Web

Abstract

Gynecologic laparoscopy as a type of minimally invasive surgery (MIS) is performed via a live feed of a patient's abdomen surveying the insertion and handling of various instruments for conducting treatment. Adopting this kind of surgical intervention not only facilitates a great variety of treatments, the possibility of recording said video streams is as well essential for numerous post-surgical activities, such as treatment planning, case documentation and education. Nonetheless, the process of manually analyzing surgical recordings, as it is carried out in current practice, usually proves tediously time-consuming. In order to improve upon this situation, more sophisticated computer vision as well as machine learning approaches are actively developed. Since most of such approaches heavily rely on sample data, which especially in the medical field is only sparsely available, with this work we publish the Gynecologic Laparoscopy ENdometriosis DAtaset (GLENDA) - an image dataset containing region-based annotations of a common medical condition named endometriosis, i.e. the dislocation of uterine-like tissue. The dataset is the first of its kind and it has been created in collaboration with leading medical experts in the field.

Problem

• Automating analysis of surgical videos to save time
• Addressing scarcity of annotated medical datasets for endometriosis
• Providing first specialized dataset for gynecologic laparoscopy computer vision

Innovation

• Publishes first endometriosis laparoscopy image dataset
• Includes region-based annotations for medical condition
• Developed with leading medical experts collaboration