AI Glottis Image Parameter Calculation via Deep Learning Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The manual calculation of normalized glottal gap area in larynx images is time-consuming and subjective, limiting its clinical application in evaluating vocal fold conditions.
Innovation Solution
An AI-assisted method using deep learning object detection and image recognition to automatically extract and calculate the glottis image and membranous glottal gap area from larynx images, enabling rapid and objective evaluation of vocal fold parameters.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual marking and calculation methods are used, then measurement precision can be maintained, but productivity is significantly reduced due to time-consuming processes
Solution Approach 1:
The patent replaces the manual mechanical process of marking and calculating with an automated image processing system. The system uses coordinate transformation algorithms and computer vision techniques to automatically identify the glottal gap region, calculate its area, and compute the normalized value, eliminating the need for manual marking while maintaining measurement precision through mathematical calculations.
Solution Approach 2:
The patent enables the measurement system to perform self-service by automatically identifying anatomical landmarks, delineating the glottal gap boundary, and calculating the normalized area without requiring manual intervention. The system uses automated feature detection and coordinate transformation to complete the entire measurement process independently, significantly improving productivity while preserving measurement accuracy.
2Measurement precision
If manual marking methods are used, then measurement precision can be maintained, but loss of time increases due to the manual process
Solution Approach 1:
The patent replaces manual marking operations with automated computer vision algorithms that rapidly process laryngeal images. The system automatically detects anatomical features, transforms coordinates to establish reference systems, and calculates the normalized glottal gap area through programmed algorithms, eliminating the time-consuming manual marking process while maintaining measurement precision through mathematical rigor.
Solution Approach 2:
The patent implements preliminary action by pre-establishing coordinate transformation relationships and anatomical reference systems before actual measurement. The system pre-processes images to identify key landmarks and set up the measurement framework in advance, so that when measurement is needed, the system can quickly compute results without time-consuming manual setup, thereby reducing overall measurement time while preserving accuracy.
3Productivity
If automated image processing is implemented, then productivity is improved, but device complexity increases due to AI algorithms
Solution Approach 1:
The patent replaces complex manual operations with automated image processing algorithms that, while computationally intensive, follow well-defined mathematical procedures. The system uses coordinate transformation, region detection, and area calculation algorithms that are implemented through software, converting a manually complex process into an automated computational process that improves productivity despite increased computational requirements.
4Ease of operation
If manual calculation methods are used, then ease of operation can be maintained, but productivity is reduced due to time-consuming calculations
Solution Approach 1:
The patent enables the system to perform self-service by automatically completing the entire measurement workflow from image processing to normalized value calculation. The system independently identifies anatomical landmarks, delineates regions, performs coordinate transformations, and computes results without requiring manual intervention at each step, thereby maintaining ease of operation through automated workflows while dramatically improving productivity.
Data Source
AI summary
A method for calculating parameters in a larynx image with an artificial intelligence assistance includes training a deep learning object detection software and a deep learning image recognition and segmentation software to extract a glottis image from a larynx image and recognize a membranous glottal gap; after receiving a larynx image, a plurality of larynx images captured frame-by-frame, or a larynx video that is captured when vocal folds are in a phonating state, extracting a glottis image by the deep learning object detection software; recognizing a membranous glottal gap in the glottis image and correspondingly outputting a membranous glottal gap filter by the deep learning image recognition and segmentation software; performing image processing of edge detection and image patching on the membranous glottal gap filter to clearly outline the membranous glottal gap and obtaining a medical parameter of several vocal fold anatomies from the clearly outlined membranous glottal gap.