Atlas-Based Parcellation for Automated Tissue Boundary Delineation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional radiological diagnosis is largely qualitative and subjective, with existing automated methods for tissue boundary delineation in imaging systems providing only approximate results, necessitating a need for an automatic means to improve detection and characterization of tissue abnormalities from radiological images.
Innovation Solution
A non-invasive imaging system that includes an imaging scanner, signal processing system, and data storage unit configured to reconstruct images, parcellate anatomical substructures, segment constituent tissue types, and automatically identify specific tissue regions using a parcellation atlas for precise tissue boundary delineation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated programs for tissue boundary delineation are used, then productivity is improved, but manufacturing precision deteriorates
Solution Approach 1:
The patent introduces an atlas-based intermediary framework that maps standardized anatomical structures onto patient-specific images. This mediator enables automated delineation by providing pre-defined tissue boundaries from the atlas, which are then adapted to individual patient anatomy through registration, thus achieving both automation and precision
Solution Approach 2:
The patent performs preliminary parcellation of anatomical structures using a standardized atlas before patient-specific analysis. This preliminary action pre-establishes tissue boundaries and relationships, which are then refined for individual patients, avoiding the need for complete manual delineation while maintaining accuracy
2Ease of operation
If voxel-based analyses are used, then ease of operation is improved, but measurement precision deteriorates
Solution Approach 1:
The patent segments the image space into anatomically-defined regions based on atlas-based parcellation before performing voxel-based analyses. This segmentation ensures that voxels are grouped within meaningful anatomical boundaries, preserving the simplicity of voxel-wise operations while improving measurement precision through anatomical context
Solution Approach 2:
The patent applies different analysis approaches to different anatomical regions. By parcellating the brain into functionally and anatomically distinct regions, the system can apply appropriate analysis methods to each region, improving overall measurement precision while maintaining operational simplicity through automated region-specific processing
3Manufacturing precision
If manual delineation is performed, then manufacturing precision is improved, but productivity deteriorates
Solution Approach 1:
The patent creates a standardized anatomical atlas that serves as a template or copy of typical brain structure. This atlas can be rapidly replicated and adapted to multiple patient images through registration, providing high-quality delineation without repeating the tedious manual process for each patient, thus improving productivity while maintaining precision
Data Source
AI summary
A non-invasive imaging system, including an imaging scanner suitable to generate an imaging signal from a tissue region of a subject under observation, the tissue region having at least one anatomical substructure and more than one constituent tissue type; a signal processing system in communication with the imaging scanner to receive the imaging signal from the imaging scanner; and a data storage unit in communication with the signal processing system, wherein the data storage unit is configured to store a parcellation atlas comprising spatial information of the at least one substructure in the tissue region, wherein the signal processing system is adapted to: reconstruct an image of the tissue region based on the imaging signal; parcellate, based on the parcellation atlas, the at least one anatomical substructure in the image; segment the more than one constituent tissue types in the image; and automatically identify, in the image, a portion of the at least one anatomical substructure that correspond to one of the more than one constituent tissue type.