Machine Learning-Assisted Vocal Cord Ultrasound Examination: Project VIPR

TL;DR

This study develops a machine learning algorithm to automatically identify vocal cords and detect paralysis in ultrasound images, aiming to improve diagnostic accuracy and reduce operator dependency.

Contribution

The paper introduces a novel machine learning-based system, VIPRnet, for automatic vocal cord segmentation and paralysis classification in ultrasound images.

Findings

Vocal cord segmentation accuracy of 96%.

VCP classification accuracy of 99%.

Demonstrates potential for improved diagnostic consistency.

Abstract

Intro: Vocal cord ultrasound (VCUS) has emerged as a less invasive and better tolerated examination technique, but its accuracy is operator dependent. This research aims to apply a machine learning-assisted algorithm to automatically identify the vocal cords and distinguish normal vocal cord images from vocal cord paralysis (VCP). Methods: VCUS videos were acquired from 30 volunteers, which were split into still frames and cropped to a uniform size. Healthy and simulated VCP images were used as training data for vocal cord segmentation and VCP classification models. Results: The vocal cord segmentation model achieved a validation accuracy of 96%, while the best classification model (VIPRnet) achieved a validation accuracy of 99%. Conclusion: Machine learning-assisted analysis of VCUS shows great promise in improving diagnostic accuracy over operator-dependent human interpretation.