Medical Image Target Area Detection With 2.5D Sectional Views

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The processing of 3D medical images for target area determination in CT imaging is computationally intensive and results in significant information loss when using 2D data, posing challenges in disease diagnosis.

Innovation Solution

A method involving pre-processing of original images, acquiring a target point, and generating sectional images using a deep learning model to determine a target area, combining 2.5D image processing to reduce computational load and preserve information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If 3D data processing is used for target area determination, then processing accuracy is improved, but computational load increases significantly

Engineering Contradiction:

Improvetarget area determination accuracyVSAvoidcomputational load

Core Design Contradiction:

Measurement precisionVSPower

Solution Approach 1:

The patent divides the 3D medical image into multiple 2D sectional images (transverse, coronal, sagittal planes) and processes them separately. This segmentation allows the system to maintain spatial information from 3D data while reducing computational complexity by handling 2D slices rather than processing the entire 3D volume at once.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent transforms the problem from 3D data processing to 2D sectional image processing. By acquiring target areas in multiple 2D planes (transverse, coronal, sagittal), the system achieves accurate target area determination while significantly reducing computational load compared to direct 3D processing.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

2Power

If 2D data is used for processing, then computational load is reduced, but information loss occurs

Engineering Contradiction:

Improvecomputational loadVSAvoidspatial information loss

Core Design Contradiction:

PowerVSLoss of information

Solution Approach 1:

The patent merges information from multiple 2D sectional images (transverse, coronal, sagittal planes) to reconstruct the complete target area. By combining the target area boundaries and spatial relationships from these multiple 2D slices, the system achieves accurate 3D target area determination while using computationally lighter 2D processing.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

Instead of losing information by using 2D data, the patent uses multiple 2D sectional images from different spatial dimensions (transverse, coronal, sagittal planes) to comprehensively represent the 3D target area. This multi-dimensional 2D approach preserves complete spatial information while reducing computational complexity.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS12588876B2Target area determination method and medical imaging system

Publication Date: 2026.03.31 GE PRECISION HEALTHCARE LLC

AI summary

Provided in the present application are a target area determination method and a medical imaging system, specifically a target area determination method and device, a medical imaging system, and a non-transitory computer-readable storage medium. The target area determination method includes: pre-processing an original image to acquire a pre-processed medical image, acquiring a target point in the medical image, and acquiring a plurality of sectional images of the medical image according to the target point, and acquiring, on the basis of a first model, a target area corresponding to the target point in the plurality of sectional images.