Toward a standardized methodological framework for developing computer vision models in staging laparoscopy
Artificial Intelligence Surgery · 05.06.2026 · 6 (2) · 300-19
DOI: 10.20517/ais.2025.122 ↗Kurz gefasst
Fachartikel in der Zeitschrift Artificial Intelligence Surgery, online erschienen am 05.06.2026. Verfasst von Francesca Tozzi und 11 weiteren Autor:innen. Die Arbeit nennt 41 Literaturangaben.
Abstract (Originalsprache)
Aim
To evaluate deep learning models for anatomical structure and peritoneal metastasis (PM) detection and segmentation during staging laparoscopy (SL) using a phase-independent dataset, and to quantify how annotation strategy and spatial representation relate to predictive performance.
Methods
A checklist covering 25 anatomical structures, one surgical instrument, and PM was defined. Detection models (YOLOv9, Co-DETR) and segmentation models (SegFormer, Mask2Former) were trained under two label configurations. Videos were split at the video level (60/20/20). To quantify annotation distribution and spatial representation, two class-level descriptors were derived from the training set: object count and area fraction (percentage of image area occupied by each class). Class-level associations between these descriptors and test-set performance [F1-score, Intersection over Union (IoU)] were evaluated using Spearman correlation.
Results
Thirty SL videos yielded 2,309 annotated frames (1,304/433/572 for training/validation/testing). YOLOv9 reached mean mAP@50 of 0.52 and 0.61; Mask2Former achieved mean IoU of 0.51 and 0.61 and F1-scores of 0.65 and 0.73 for Sets A and B, respectively. Despite 4,094 annotations, PM remained difficult to segment (IoU 0.29-0.30; F1-score 0.45-0.46), due to low area fraction and high heterogeneity. For IoU, area fraction showed stronger correlations with performance than object count (ρ up to 0.66 vs. 0.48). Similar differences were observed for F1-score.
Conclusions
Anatomical detection and segmentation during SL are feasible but limited by small-target representation and heterogeneous intra-abdominal context. Spatial representation is more closely associated with segmentation performance than annotation frequency, supporting annotation strategies that address sparse pixel coverage in phase-independent intra-abdominal models.
Zitieren
APA
Tozzi, F., Mousavi, S. A., Muynck, R. D., Quintini, D., Molnar, A., Vaerenbergh, F. V., Lille, X. D., Liefferinge, M. V., Ceelen, W., Willaert, W., Neve, W. D., & Rashidian, N. (2026). Toward a standardized methodological framework for developing computer vision models in staging laparoscopy. Artificial Intelligence Surgery, 6(2), 300-19. https://doi.org/10.20517/ais.2025.122
Vancouver
Tozzi F, Mousavi SA, Muynck RD, Quintini D, Molnar A, Vaerenbergh FV, et al. Toward a standardized methodological framework for developing computer vision models in staging laparoscopy. Artificial Intelligence Surgery. 2026;6(2):300-19. doi:10.20517/ais.2025.122
BibTeX
@article{Tozzi2026,
author = {Tozzi, Francesca and Mousavi, Seyed Amir and Muynck, Robbe De and Quintini, Dario and Molnar, Adris and Vaerenbergh, Femke Van and Lille, Xander De and Liefferinge, Matthias Van and Ceelen, Wim and Willaert, Wouter and Neve, Wesley De and Rashidian, Niki},
title = {Toward a standardized methodological framework for developing computer vision models in staging laparoscopy},
journal = {Artificial Intelligence Surgery},
year = {2026},
volume = {6},
number = {2},
pages = {300--19},
doi = {10.20517/ais.2025.122}
}
EUVIMED