DTI Brain Connectivity Assessment for Multi-Module ASD Severity
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current ASD assessment tools lack the ability to provide nuanced severity grading across multiple behavioral modules, are subjective, and are often used late, limiting intervention effectiveness, while existing DTI-based methods only offer binary diagnoses.
Innovation Solution
A computer-aided system that utilizes DTI imaging to parcellate the brain, identify connectivity markers, and apply machine learning techniques to determine ASD severity in multiple assessment modules, including a two-phase approach for improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If current ASD assessment tools (e.g., ADOS) are used, then diagnosis can be obtained, but the tools lack objectivity and cannot provide nuanced severity grading across multiple behavioral modules
Solution Approach 1:
The patent replaces the manual, subjective clinical assessment process with an automated computer-aided system that uses machine learning algorithms to analyze neuroimaging data. This substitution eliminates human subjectivity in severity grading while providing precise, quantifiable measurements across multiple ASD behavioral modules through objective computational analysis of brain connectivity patterns
Solution Approach 2:
The system transforms the assessment from qualitative behavioral observations to quantitative neuroimaging parameters. By measuring objective biomarkers such as fractional anisotropy, mean diffusivity, and radial diffusivity from DTI data, the system provides precise severity grading based on quantifiable brain connectivity metrics rather than subjective clinical judgment
2Adaptability or versatility
If existing DTI-based methods are used, then binary diagnosis (ASD vs. typically developing) can be obtained, but nuanced severity grading across multiple modules is not provided
Solution Approach 1:
The patent segments the ASD assessment into five distinct behavioral modules (social awareness, social cognition, social communication, social motivation, and autistic mannerisms). Each module is evaluated separately using specific neuroimaging features and machine learning models, allowing comprehensive assessment that captures nuanced severity variations across different aspects of ASD rather than providing a single binary classification
Solution Approach 2:
The system adds a new dimension to DTI-based ASD assessment by transitioning from one-dimensional binary classification to multi-dimensional severity grading. By incorporating multiple behavioral modules with distinct severity levels and using diverse neuroimaging parameters (FA, MD, RD), the system preserves rich detail information that would be lost in simple binary diagnosis
3Loss of time
If assessment tools are used late in development, then diagnosis is obtained, but intervention effectiveness is limited
Solution Approach 1:
The patent enables preliminary detection of ASD by analyzing neuroimaging data that reflects underlying brain connectivity abnormalities present from early development. The machine learning system can identify patterns indicative of ASD severity before behavioral symptoms fully manifest, allowing for earlier intervention planning and potentially improving treatment outcomes by addressing issues at an earlier stage
Data Source
AI summary
A non-invasive computer-aided system and method for assessing the severity of autism spectrum disorders across multiple assessment modules use as input neuroimaging data of a subject brain, parcellates the subject brain into a plurality of brain regions, identifies neuroimaging markers denoting connectivity between regions, determines connectivity between regions, identifies regions associated with autism spectrum disorder, and uses machine learning techniques to determine the severity of autism spectrum disorder with respect to each module based on the determined connectivity.