Multi-Modality 3D Image Fusion for Medical Region Localization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing target region identification methods based on three-dimensional (3D) images suffer from inaccuracies in medical imaging, particularly in identifying regions of interest such as breast tumors.
Innovation Solution
An image region localization method that acquires and registers multiple 3D images from different modalities, extracts and fuses image features, determines voxel types, selects target voxels, and localizes the target region based on position information, improving accuracy by integrating multiple image perspectives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple 3D images from different modalities are acquired and fused, then the accuracy of target region identification is improved, but the device complexity and processing difficulty increase
Solution Approach 1:
The patent combines multiple 3D images from different imaging modalities (such as CT and MRI) into a unified fused image. This merging process integrates the complementary information from each modality, where CT provides excellent bone and structural detail while MRI offers superior soft tissue contrast. The fusion is achieved through coordinate system alignment and pixel-level integration, resulting in a single comprehensive image that enhances target region identification accuracy while managing system complexity through standardized processing pipelines
2Measurement precision
If multiple 3D images from different modalities are registered and fused, then the localization precision is improved, but the processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary registration and alignment of multiple 3D images before the actual fusion process. This preliminary action involves establishing coordinate systems, applying transformation matrices, and pre-aligning the images to their expected spatial relationships. By completing these preparatory steps beforehand, the subsequent fusion operation can proceed more efficiently, reducing overall processing time while maintaining high localization precision through accurate spatial correspondence
3Reliability
If image features from multiple modalities are fused, then false determinations are reduced, but the difficulty of detecting and measuring increases
Solution Approach 1:
The patent applies local quality enhancement by selectively weighting and emphasizing specific image features from different modalities based on their reliability and diagnostic value in different regions. For example, in bone regions, CT-derived features may be weighted higher, while in soft tissue regions, MRI-derived features receive greater weight. This localized feature fusion approach reduces false determinations by adapting to the specific characteristics of different anatomical regions while managing detection complexity through region-specific processing rules
Data Source
AI summary
Embodiments of this application disclose methods, systems, and devices for image region localization and medical image processing. In one aspect, a method comprises acquiring three-dimensional images of a target body part of a patient. The three-dimensional images comprise a plurality of magnetic resonant imaging (MRI) modalities. The method comprises registering a first image set of a first modality with a second image set of a second modality. After the registering, image features of the three-dimensional images are extracted. The image features are fused to obtain fused features. The method also comprises determining voxel types corresponding to voxels in the three-dimensional images according to the fused features. The method also comprises selecting, from the three-dimensional images, target voxels having a preset voxel type, obtaining position information of the target voxels, and localizing a target region within the target body part based on the position information of the target voxels.