ScholarDeck

AI / informaticsEuropean spine journal : official publication of the European Spine Society, the European Spinal Deformity Society, and the European Section of the Cervical Spine Research Society · 2026

Intelligent recognition and segmentation of anatomical structures in spinal endoscopy: a deep learning approach with 1000 annotated images.

Jingtian Yuan, Junwei Zhang, Tairui Zhang … Maji Sun

Read paper

GastroenterologyAI / informatics

Deep learning model segmented the ligamentum flavum with high accuracy in spinal endoscopy

Intelligent recognition and segmentation of anatomical structures in spinal endoscopy: a deep learning approach with 1000 annotated images.

Jingtian Yuan et al. · European spine journal : official publication of the European Spine Society, the European Spinal Deformity Society, and the European Section of the Cervical Spine Research Society · 2026

Background

Accurate intraoperative identification of anatomical structures is critical for ensuring the safety and efficacy of spinal endoscopic surgery.

Purpose

To develop and validate a deep learning-based system for the automated, simultaneous segmentation of multiple key anatomical structures in spinal endoscopic images, aiming to provide a reliable foundation for computer-aided surgical navigation.

Methods

We constructed a large-scale, expert-annotated dataset of 1000 spinal endoscopic images.

n = 100 images

0.882

Results

how well the model outlined the ligamentum flavum (a spinal ligament); higher means better

n = 100 images

More results

Ablation studies confirmed the critical contributions of the CBAM and ASPP modules.

Our model significantly outperformed baseline and state‑of‑the‑art architectures across major structures (P < 0.01, Bonferroni‑corrected), achieving a 17.0% relative improvement in mIoU for the ligamentum flavum compared to DeepLabV3+.

More results

Sensitivity analyses confirmed model robustness, and subgroup analyses revealed consistent performance across major spinal regions.

“

Conclusion · 1 of 3

This study presents a promising segmentation system for spinal endoscopic anatomy that achieves high accuracy for critical soft tissues such as the ligamentum flavum and nerve roots.

Conclusion · 2 of 3

The integration of attention mechanisms and multi-scale feature extraction proves to be an effective strategy.

Conclusion · 3 of 3

However, the current accuracy for posterior longitudinal ligament and bone remains insufficient for clinical use, and further refinement is required before real-time navigation can be considered.

Post

Intelligent recognition and segmentation of anatomical structures in spinal endoscopy: a deep learning approach with 1000 annotated images.

Deep learning model segmented the ligamentum flavum with high accuracy in spinal endoscopy

Related papers