Automated Measurement of Optic Nerve Sheath Diameter Using Ocular Ultrasound Video

2025-06-03

AI Summary

Ultrasound-based optic nerve sheath diameter (ONSD) measurement suffers from high operator dependency, subjective frame selection, and poor reproducibility. To address these limitations, this study proposes a fully automated dynamic ONSD assessment framework: (1) a novel adaptive optimal-frame selection strategy integrating Kernelized Correlation Filter (KCF) tracking with SLIC superpixel segmentation; and (2) a joint Gaussian Mixture Model–Kullback–Leibler (GMM-KL) divergence model for precise dural sheath boundary delineation and submillimeter ONSD quantification. Evaluated on clinical ultrasound data, the method achieves a mean absolute error of 0.04 mm and a mean squared deviation of 0.054 mm² relative to the average of two expert annotations, with an intraclass correlation coefficient (ICC) of 0.782—meeting clinical accuracy requirements. This work significantly enhances objectivity, efficiency, and reproducibility in ONSD quantification, providing a robust technical foundation for noninvasive, dynamic intracranial pressure monitoring.

Technology Category

• Search and Optimization: Mixed Discrete/Continuous Search
• Computer Vision: Segmentation
• Intelligent Robots: State Estimation

Application Category

• Security and Privacy: Large-scale security measurements
• User Modeling, Personalization and Recommendation: On-Device user modeling, personalization, and recommendation
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs

Abstract

Objective. Elevated intracranial pressure (ICP) is recognized as a biomarker of secondary brain injury, with a significant linear correlation observed between optic nerve sheath diameter (ONSD) and ICP. Frequent monitoring of ONSD could effectively support dynamic evaluation of ICP. However, ONSD measurement is heavily reliant on the operator's experience and skill, particularly in manually selecting the optimal frame from ultrasound sequences and measuring ONSD. Approach. This paper presents a novel method to automatically identify the optimal frame from video sequences for ONSD measurement by employing the Kernel Correlation Filter (KCF) tracking algorithm and Simple Linear Iterative Clustering (SLIC) segmentation algorithm. The optic nerve sheath is mapped and measured using a Gaussian Mixture Model (GMM) combined with a KL-divergence-based method. Results. When compared with the average measurements of two expert clinicians, the proposed method achieved a mean error, mean squared deviation, and intraclass correlation coefficient (ICC) of 0.04, 0.054, and 0.782, respectively. Significance. The findings suggest that this method provides highly accurate automated ONSD measurements, showing potential for clinical application.

Problem

• Automates ONSD measurement to reduce operator dependency
• Uses KCF and SLIC algorithms for optimal frame selection
• Provides accurate ICP monitoring via Gaussian Mixture Model

Innovation

• Uses KCF tracking for optimal frame selection
• Applies SLIC segmentation for precise measurement
• Combines GMM with KL-divergence for sheath mapping