A Fully Automatic Framework for Intracranial Pressure Grading: Integrating Keyframe Identification, ONSD Measurement and Clinical Data

2025-09-11

AI Summary

Clinical assessment of intracranial pressure (ICP) via manual optic nerve sheath diameter (ONSD) measurement suffers from high inter-observer variability, poor reproducibility, and inconsistent diagnostic thresholds. To address these limitations, we propose a fully automated, two-stage framework for noninvasive ICP grading. Our method integrates intelligent key-frame selection from ocular ultrasound videos—guided by anatomical segmentation and clinical consensus guidelines—with pixel-level ONSD quantification and multimodal embedding of auxiliary clinical data, followed by machine learning–based ICP classification. To our knowledge, this is the first work to combine interpretable ultrasound analysis with multimodal feature fusion for ICP grading, substantially reducing operator dependency. In cross-validation, the model achieves an accuracy of 0.845 ± 0.071; on an independent test set, it attains 0.786—both significantly outperforming conventional threshold-based approaches (0.637 ± 0.111 and 0.429, respectively). The framework demonstrates strong robustness and promising clinical translatability.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification

Application Category

• Security and Privacy: Large-scale security measurements
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

Intracranial pressure (ICP) elevation poses severe threats to cerebral function, thus necessitating monitoring for timely intervention. While lumbar puncture is the gold standard for ICP measurement, its invasiveness and associated risks drive the need for non-invasive alternatives. Optic nerve sheath diameter (ONSD) has emerged as a promising biomarker, as elevated ICP directly correlates with increased ONSD. However, current clinical practices for ONSD measurement suffer from inconsistency in manual operation, subjectivity in optimal view selection, and variability in thresholding, limiting their reliability. To address these challenges, we introduce a fully automatic two-stage framework for ICP grading, integrating keyframe identification, ONSD measurement and clinical data. Specifically, the fundus ultrasound video processing stage performs frame-level anatomical segmentation, rule-based keyframe identification guided by an international consensus statement, and precise ONSD measurement. The intracranial pressure grading stage then fuses ONSD metrics with clinical features to enable the prediction of ICP grades, thereby demonstrating an innovative blend of interpretable ultrasound analysis and multi-source data integration for objective clinical evaluation. Experimental results demonstrate that our method achieves a validation accuracy of $0.845 pm 0.071$ (with standard deviation from five-fold cross-validation) and an independent test accuracy of 0.786, significantly outperforming conventional threshold-based method ($0.637 pm 0.111$ validation accuracy, $0.429$ test accuracy). Through effectively reducing operator variability and integrating multi-source information, our framework establishes a reliable non-invasive approach for clinical ICP evaluation, holding promise for improving patient management in acute neurological conditions.

Problem

• Automating intracranial pressure grading non-invasively
• Reducing subjectivity in optic nerve sheath measurement
• Integrating ultrasound analysis with clinical data

Innovation

• Fully automatic two-stage ICP grading framework
• Rule-based keyframe identification from ultrasound
• Multi-source data fusion for ICP prediction