# Improved AI-Assisted Image Recognition of Cervical Spine Vertebrae Enables Motion Pattern Analysis in Dynamic X-Ray Recordings

## TL;DR

This study improves AI models for analyzing cervical spine motion in X-rays, making motion pattern evaluation more accessible and reliable.

## Contribution

The study introduces improved deep-learning models for accurate cervical spine segmentation and motion analysis.

## Key findings

- Models A and B showed high accuracy in analyzing cervical motion patterns.
- High image contrast and sufficient segmental range of motion are crucial for reliable model performance.
- The study advances automated qualitative motion analysis of the cervical spine.

## Abstract

Background: Qualitative motion analysis revealed that the cervical spine moves according to a consistent pattern. Current data analysis methods are limited by the extensive time required to process the retrieved data. A previous study demonstrated the feasibility of using a deep-learning model to automate analysis methods. However, segmentation accuracy needed to be improved. This study aims to improve segmentation model performance to enable reliable motion analysis. Methods: Four nnU-Net configurations were tested: baseline (A), pre-trained (B), with histogram equalization (C), and pre-trained with histogram equalization (D). Segmentation performance was evaluated using Dice Similarity Coefficient (DSC), Intersection over Union (IoU) and 95th percentile Hausdorff Distance (HD95). Vertebral rotation was estimated using mean shapes. Reliability was assessed using the Intraclass Correlation Coefficient (ICC). Sensitivity analyses were conducted. Results: Across all models, mean DSC ranged from 0.67 to 0.92, mean IoU from 0.55 to 0.85, and mean HD95 from 2.35 to 19.67 mm. After sensitivity analysis for low segmental range of motion (sROM) and low-quality recordings, the mean ICC ranged from 0.617 to 0.837 for model A, from 0.609 to 0.780 for model B, from 0.409 to 0.689 for model C, and from 0.480 to 0.835 for model D. Conclusions: This study shows that Models A and B can accurately analyze cervical motion patterns. High image contrast and an adequate sROM are essential for robust model performance. It also marks an important step toward automated qualitative motion analysis, increasing the accessibility of motion pattern evaluation.