Image Reconstruction via ROI Segmentation for Long AFOV Imaging

Solution Overview

Problem

Imaging devices with a long axial field of view (AFOV) generate excessive imaging data, leading to increased radiation dose, storage redundancy, and decreased speed and accuracy of image processing for specific medical regions of interest.

Innovation Solution

A system and method that determine regions of interest (ROIs) within the imaging data, isolate target portions of the data corresponding to these ROIs, and reconstruct images specifically for the ROIs, thereby reducing unnecessary data processing and improving efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If image data from a long AFOV imaging device is processed for a specific ROI, then the scanning range and detection capability are improved, but the radiation dose, storage requirements, and processing time increase due to the large amount of data from other regions

Engineering Contradiction:

Improvescanning rangeVSAvoidprocessing time

Core Design Contradiction:

Adaptability or versatilityVSLoss of time

Solution Approach 1:

The patent segments the full AFOV image data into multiple regions along the axial direction. It identifies and extracts only the subset of data corresponding to the specific ROI, discarding data from other regions. This segmentation approach maintains the advantage of long AFOV scanning while eliminating the time penalty of processing unnecessary data.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent extracts the target portion of image data corresponding to the ROI from the complete AFOV dataset. By taking out only the relevant data portion, the system achieves fast processing for the specific medical region while the imaging device retains its extended scanning capability.

Inventive Principle:

Principle #2Taking out (Extraction)

2Adaptability or versatility

If image data from a long AFOV imaging device is processed for a specific ROI, then the scanning range and detection capability are improved, but the radiation dose, storage requirements, and processing time increase due to the large amount of data from other regions

Engineering Contradiction:

Improvescanning rangeVSAvoidstorage requirements

Core Design Contradiction:

Adaptability or versatilityVSQuantity of substance

Solution Approach 1:

The patent segments the full AFOV image data into multiple regions along the axial direction. It identifies and extracts only the subset of data corresponding to the specific ROI, discarding data from other regions. This segmentation approach maintains the advantage of long AFOV scanning while eliminating the time penalty of processing unnecessary data.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent extracts the target portion of image data corresponding to the ROI from the complete AFOV dataset. By taking out only the relevant data portion, the system achieves fast processing for the specific medical region while the imaging device retains its extended scanning capability.

Inventive Principle:

Principle #2Taking out (Extraction)

3Adaptability or versatility

If image data from a long AFOV imaging device is processed for a specific ROI, then the scanning range and detection capability are improved, but the radiation dose, storage requirements, and processing time increase due to the large amount of data from other regions

Engineering Contradiction:

Improvescanning rangeVSAvoidradiation dose

Core Design Contradiction:

Adaptability or versatilityVSObject-affected harmful factors

Solution Approach 1:

The patent extracts the target portion of image data corresponding to the ROI from the complete AFOV dataset. By taking out only the relevant data portion, the system achieves fast processing for the specific medical region while the imaging device retains its extended scanning capability.

Inventive Principle:

Principle #2Taking out (Extraction)

Data Source

PatentUS20250104247A1Systems and methods for image reconstruction and processing

Publication Date: 2025.03.27 SHANGHAI UNITED IMAGING HEALTHCARE

AI summary

The present disclosure provides a system and method for image reconstruction and processing. The method may include obtaining image data of an object acquired by an imaging device. The method may include determining one or more regions of interest (ROIs) of the object. The method may also include determining, based on each ROI of the one or more ROIs, a target portion of the image data corresponding to the ROI among the image data. The method may further include reconstructing, based on the target portion of the image data, one or more images of the ROI.