CAT Scan Image Registration via Displacement Vector Field

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Computerized axial tomography (CAT) scans often result in staggered images due to misalignment of image sets obtained at different bed positions or time points, making it difficult to accurately diagnose and treat structures like bones and blood vessels.

Innovation Solution

A system and method for image processing that involves obtaining displacement vector fields from corresponding regions in multiple image sets, registering the images, and generating a target image to align and process the images effectively, thereby improving diagnostic accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If multiple image sets are obtained at different bed positions or time points, then more comprehensive image data is acquired, but image misalignment and staggering occur

Engineering Contradiction:
Improveimage dataVSAvoidimage alignment
Core Design Contradiction:
Quantity of substanceVSManufacturing precision

Solution Approach 1:

A displacement vector field is introduced as an intermediary to bridge multiple image sets. The field is determined by registering corresponding regions across image sets and then applied to transform images, serving as a mediator that aligns data from different acquisitions while preserving the comprehensive nature of the multi-image dataset

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces mechanical alignment methods with a computational field-based approach. Instead of physically repositioning or mechanically adjusting images, a displacement vector field computationally transforms image coordinates to achieve alignment, substituting mechanical operations with mathematical transformations

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Manufacturing precision

If image registration is performed to align images, then image alignment improves, but processing complexity increases

Engineering Contradiction:
Improveimage alignmentVSAvoidprocessing complexity
Core Design Contradiction:
Manufacturing precisionVSDevice complexity

Solution Approach 1:

The image registration process is segmented into distinct stages: determining the displacement vector field from representative images, then applying this field to transform individual images. This segmentation allows the complex registration task to be broken into manageable steps, reducing overall processing complexity while maintaining alignment precision

Inventive Principle:
Principle #1Segmentation

3Productivity

If displacement vector field is determined from representative images, then processing efficiency improves, but accuracy may be compromised

Engineering Contradiction:
Improveprocessing efficiencyVSAvoidalignment accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent creates a displacement vector field based on representative images that copy the alignment relationships from those images. This field then serves as a template to transform all other images in the set, achieving efficient batch processing while maintaining accuracy through the consistent application of the copied alignment pattern

Inventive Principle:
Principle #26Copying

Data Source

PatentUS20240037762A1Systems and methods for image processing
Publication Date: 2024.02.01 SHANGHAI UNITED IMAGING HEALTHCARE
  • US20240037762A1 patent drawing
  • US20240037762A1 patent drawing
  • US20240037762A1 patent drawing

AI summary

The present disclosure is related to systems and methods for image processing. The method includes obtaining, from a first image set of a subject acquired at a first time point, a first image; obtaining, from a second image set of the subject acquired at a second time point, a second image, wherein the first image and the second image correspond to a same region of the subject; determining a displacement vector field based on the first image and the second image; and generating a target image based on the displacement vector field, the first image set and the second image set.