CT Image Super-Resolution Reconstruction for Diagnostic Workflow
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current CT imaging technologies face challenges in achieving high-quality images with thin slice thickness, which requires more images and longer reading times, while thick slice images may miss small nodules, necessitating an effective interface to switch between thick and thin slice thicknesses for accurate diagnosis.
Innovation Solution
A computing apparatus and method that allows switching between images of different slice thicknesses by acquiring and processing image groups using a super-resolution scheme, enabling efficient viewing and analysis of both thick and thin slice images, thereby improving diagnostic accuracy and workflow efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If thin slice thickness images are used, then image quality and reading accuracy improve, but the number of images increases and reading time increases
Solution Approach 1:
The system dynamically switches between thick slice and thin slice image groups based on user input, allowing the display to adapt between different image resolutions. This enables the interface to provide high-quality thin slice images when needed while maintaining the ability to quickly navigate through fewer thick slice images, thus balancing reading accuracy with reading time efficiency.
2Measurement precision
If thin slice thickness images are used, then image quality improves, but storage space increases
Solution Approach 1:
The system merges the functionality of storing and displaying both thick slice and thin slice images by generating thin slice images on-demand from thick slice images using super-resolution reconstruction. This combination approach allows the system to maintain storage efficiency with primarily thick slice images while providing thin slice image quality when needed, without requiring separate full-storage of both image types.
Solution Approach 2:
The system creates a reconstructed copy of the thick slice images at thin slice thickness using super-resolution algorithms. This copied image group provides the appearance and diagnostic quality of thin slice images while being generated from the original thick slice data, reducing the need to store separate thin slice acquisitions.
3Productivity
If thick slice thickness images are used, then storage space is saved and reading efficiency improves, but small nodules may be damaged or missed
Solution Approach 1:
The display interface dynamically switches between thick slice and thin slice image groups based on user input, allowing the system to adapt between fast navigation mode (thick slice) and detailed inspection mode (thin slice). This enables readers to efficiently survey the entire volume with thick slice images while being able to switch to thin slice images when detailed examination of small nodules is required.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This solution enhances reading accuracy and speed by allowing medical professionals to quickly switch between thick and thin slice images, reducing reading time and improving image quality without the need for separate image generation and storage.
Implementation Method 1
The first image group may be generated by projecting, onto a plane, at least a portion of the series of images generated for the continuous volumes with the first slice thickness belonging to the subject, and the second image group may be generated from the first image group based on a super-resolution (SR) scheme.
Data Source
AI summary
An image providing method performed by a computing apparatus includes acquiring a first image group including at least a portion of a series of images generated for continuous volumes with a first slice thickness belonging to a subject, providing, as a current viewing image, one image of the first image group or one image of a second image group including images generated for continuous volumes with a second slice thickness belonging to the subject, and in response to a first specific input of an input device, repeatedly updating an image provided as the current viewing image with an individual image provided for a subsequent viewing based on a directivity given for the first specific input and, in response to a second specific input of the input device, switching the current viewing image between an image of the first image group and an image of the second image group.