Initial Results in the Automatic Visual Recognition of Endometriosis Lesions by Artificial Intelligence During Laparoscopy: A Proof-of-Concept Study

A Netter, Antoine Netter, Saman Noorzadeh, Fanny Duchateau, Henrique Mendonca Abrão, Henrique Abrao, Julie Desternes, J. Desternes, Julien Peyras, Jean‐Luc Pouly, Jean-Luc Pouly, Maurício Simões Abrão, Mauricio S Abrão, Attila Bokor, Ulrik Bak Kirk, Kirk, Ulrik Bak, Aubert Agostini, Blandine Courbière, Blandine Courbiere, Michel Canis, Adrien Bartoli, Nicolas Bourdel, FEMaLe Project Work Group
Journal of minimally invasive gynecology · 2025 · vol. 32(12) , pp. 1118–1125 · doi:10.1016/j.jmig.2025.08.027 · PMID:40912397 · W4413949848
article OA: gold CC0 ⤵ 2 in-corpus citations
🔓 Open OA copy View on OpenAlex View on PubMed View at publisher
⚙ AI-generated summary by claude@2026-06, 2026-06-07 ⓘ

A deep neural network was trained to detect endometriosis lesions during laparoscopy, showing good performance for some lesion types but requiring further development for others.

One-sentence paraphrase of the abstract; not a substitute for reading it. No clinical advice. How this works

⚙ AI-generated deep summary by claude@2026-06, 2026-06-07 ⓘ

This multicenter proof-of-concept study developed and tested a deep neural network (YOLOv5) to automatically detect and classify nine visual classes of endometriosis lesions in laparoscopic surgical videos from 112 patients with suspected endometriosis, using expert-center recordings in France, Hungary, Brazil, and Denmark. The model showed strong performance for “superficial black,” “superficial subtle,” and “ovarian chocolate fluid” (F1 scores 0.94, 0.74, 0.75), moderate/acceptable performance for “dense adhesion,” “ovarian endometrioma,” and “deep endometriosis” (F1 0.70, 0.63, 0.632), and weak performance for “superficial red,” “superficial white,” and “filmy adhesions” (F1 0.25, 0.18, 0.02). The study explicitly limits generalizability by excluding poor-quality sequences and sequences with prior manipulation and by reporting only initial performance, emphasizing the need to refine accuracy/precision and standardize annotation methods. This paper is centrally about endometriosis—developing AI for automatic visual recognition of endometriosis lesions during laparoscopy.

Read from the paper's body, not the abstract. Not a substitute for reading the paper. No clinical advice. How this works

Abstract

OBJECTIVE: To develop a machine learning method for the automatic recognition of endometriosis lesions during laparoscopic surgery and evaluate its feasibility and performance. DESIGN: Collecting and annotating surgical videos and training, validating, and testing a deep neural network. SETTING: Multicenter proof-of-concept study using surgical videos from expert centers in France, Hungary, Brazil, and Denmark. PARTICIPANTS: Surgical video sequences were collected from 112 patients who underwent laparoscopic procedures for suspected endometriosis between January 2020 and August 2023. Sequences with identifiable endometriosis lesions were included, while poor-quality images and sequences with prior surgical manipulation were excluded. INTERVENTIONS: A deep neural network based on YOLOv5 was trained to detect and classify nine visual classes of endometriosis lesions (superficial black, superficial red, superficial white, superficial subtle, filmy adhesions, dense adhesions, deep endometriosis, ovarian endometrioma, and ovarian chocolate fluid). RESULTS: The model performance was good for the "superficial black," "superficial subtle," and "ovarian chocolate fluid" classes (F1 score = 0.94, 0.74, and 0.75, respectively), acceptable for the "dense adhesion," "ovarian endometrioma" and "deep endometriosis" classes (F1 score = 0.70, 0.63 and 0.632, respectively), and weak for the "superficial red," "superficial white," and "filmy adhesions" classes (F1 score = 0.25, 0.18, 0.16 and 0.02, respectively). However, while these results highlight the model's strong potential in identifying most lesions in at least one frame of each sequence, they underscore the need for further refinement to improve accuracy and precision. CONCLUSION: This study demonstrates the feasibility of applying artificial intelligence for visual recognition of endometriosis during laparoscopic surgery. While the initial results are encouraging, further development is needed to enhance the model performance and standardize the annotation methods. The integration of AI in surgical practice holds promise for assisting in endometriosis diagnosis and improving surgical outcomes.

My notes (saved in your browser only)

Condition tags

mesh:D004715endometriosisendometrioma

MeSH descriptors

Artificial Intelligence Artificial Intelligence Artificial Intelligence Artificial Intelligence Artificial Intelligence Artificial Intelligence Artificial Intelligence Artificial Intelligence Artificial Intelligence Artificial Intelligence Artificial Intelligence Artificial Intelligence Endometriosis Endometriosis Endometriosis Endometriosis Endometriosis Endometriosis Endometriosis Endometriosis

Citation neighborhood

Papers in the corpus that this work cites (lower rings, blue) and that cite this one (upper rings, green). Dot size scales with the paper's in-corpus citation count — bigger dot = more influential within the endo/adeno field. Click a dot to open that paper. [ expand to 2 hops ] — adds papers reached through this work's immediate citers/citees. Heavier; up to 60 extra dots.

References (21)

Cited by (2)

Source provenance

europepmc
last seen: 2026-06-04T01:30:01.192114+00:00
openalex
last seen: 2026-06-10T17:14:06.276822+00:00
pubmed
last seen: 2026-05-27T00:31:00.586144+00:00
License: CC0 · commercial use OK