Real-time instance segmentation of spine endoscopy images using a YOLO-V11 deep convolutional neural network
PLOS One · 18.11.2026 · 21 (11) · e0361612
DOI: 10.1371/journal.pone.0361612 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 18.11.2026. Verfasst von Hyun Ji Jung und 10 weiteren Autor:innen. Die Arbeit nennt 19 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: SPINAI, Samsung Electronics Co..
Abstract (Originalsprache)
Background and Objectives Spine endoscopic surgery requires precise anatomical recognition and real-time bleeding detection to enhance surgical safety and efficiency. However, most existing computer vision studies do not offer real-time multi-class segmentation of the entire scene. This study aims to develop a real-time instance segmentation model based on YOLO-V11, capable of automatically identifying surgical instruments, critical anatomical structures, and bleeding sites in spine endoscopy.
Methods
The model was trained and evaluated using 2,181 annotated frames (training 1,741 / validation 216 / held-out test 224) from spine endoscopy images, covering nine key categories: instruments, bone, ligamentum flavum, dura, soft tissue, vessels, fat, the radiofrequency ablation wand, and bleeding focus. The segmentation model’s performance was evaluated across various YOLO-V11 variants.
Results
Across five random seeds per variant on the same NVIDIA A100 GPU, YOLO-V11 l achieved the highest mask mAP50, defined as mean average precision at an intersection-over-union threshold of 0.50, with a value of 0.7735 ± 0.0030 (mean ± SD, n = 5). It also maintained real-time inference, reaching 270 ± 35 frames per second (FPS) with a per-frame latency of 3.75 ± 0.51 ms. All five variants exceeded 30 FPS, the widely accepted real-time threshold for surgical imaging. The model demonstrated high precision in segmenting vital structures such as the dura and ligamentum flavum and accurately identified bleeding regions.
Conclusion
This research contributes to AI-driven surgical guidance systems, with potential applications in robotic-assisted spine surgery. The developed model enables real-time navigation, improving intraoperative decision-making and enhancing surgical outcomes. In particular, our YOLO-V11-based framework extends prior single-structure or lower-frame-rate multi-element approaches by delivering real-time multi-class instance segmentation of instruments, anatomical structures, and bleeding sites in spine endoscopy, with explicitly quantified inference latency.
Förderung
- SPINAI
- Samsung Electronics Co.
Zitieren
APA
Jung, H. J., Nam, N. E., Lee, C., Lim, Y., Choi, W. C., Lee, J., Kim, G., Kim, H., Lee, S. K., Kang, J., & Kim, T. (2026). Real-time instance segmentation of spine endoscopy images using a YOLO-V11 deep convolutional neural network. PLOS One, 21(11), e0361612. https://doi.org/10.1371/journal.pone.0361612
Vancouver
Jung HJ, Nam NE, Lee C, Lim Y, Choi WC, Lee J, et al. Real-time instance segmentation of spine endoscopy images using a YOLO-V11 deep convolutional neural network. PLOS One. 2026;21(11):e0361612. doi:10.1371/journal.pone.0361612
BibTeX
@article{Jung2026,
author = {Jung, Hyun Ji and Nam, Noah Euyhyun and Lee, Chulmin and Lim, Yeje and Choi, Won Chang and Lee, Junsu and Kim, Gunyul and Kim, Hyunjae and Lee, Sang Kyeong and Kang, Jiho and Kim, Tae-Shin},
title = {Real-time instance segmentation of spine endoscopy images using a YOLO-V11 deep convolutional neural network},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {11},
pages = {e0361612},
doi = {10.1371/journal.pone.0361612}
}
EUVIMED