Lesion Orientation Assessment in 3D Medical Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current medical imaging technologies, such as MR and CT, struggle to assess the orientation of breast lesions with respect to the skin surface, a crucial parameter in ultrasound imaging, due to variable image acquisition and lack of direct visual accessibility in three-dimensional imaging.
Innovation Solution
A system comprising a surface detector to identify part of the surface, a lesion detector to identify and model-fit the lesion, and a view generator to establish the lesion's orientation relative to the surface, allowing for automatic computation and visualization of lesion orientation in three-dimensional medical images.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If three-dimensional imaging techniques (MR and CT) are used to assess lesion orientation, then the need for multiple imaging modalities is reduced, but the ability to accurately determine lesion orientation with respect to the skin surface deteriorates due to variable image acquisition and lack of direct visual accessibility
Solution Approach 1:
The patent transforms the three-dimensional medical image data into a two-dimensional representation where the skin surface is flattened and displayed as a reference plane. This dimensional transformation allows lesion orientation to be visualized and measured accurately in 2D space while maintaining the spatial relationships from the original 3D data, resolving the contradiction between using 3D imaging and achieving accurate orientation measurement.
Solution Approach 2:
The patent introduces an intermediate computational processing step that identifies the skin surface geometry from the 3D medical image and uses it as a reference frame. This intermediary process creates a virtual ultrasound-like view where the skin surface orientation is explicitly represented, enabling accurate lesion orientation assessment without direct ultrasound acquisition.
2Reliability
If multiple imaging modalities (ultrasound, MR, CT) are used to comprehensively assess lesion characteristics, then diagnostic accuracy is improved, but imaging time and patient exposure to multiple procedures increase
Solution Approach 1:
The patent makes the 3D medical imaging modality (MR or CT) multi-functional by enabling it to provide both the primary diagnostic information and the lesion orientation assessment that previously required separate ultrasound imaging. This universal application of a single imaging modality reduces the need for multiple procedures while maintaining comprehensive diagnostic capability.
Solution Approach 2:
The patent merges the functions of 3D medical imaging and ultrasound-based orientation assessment into a single integrated analysis process. By combining the volumetric data from MR/CT with automated surface detection and orientation calculation, the system consolidates multiple imaging purposes into one procedure, reducing total imaging time and patient burden.
3Productivity
If automated computer-aided detection systems are implemented, then diagnostic efficiency and reproducibility are improved, but the complexity of the analysis system increases
Solution Approach 1:
The patent implements self-service functionality where the system automatically identifies the skin surface, calculates its orientation, and determines lesion orientation relative to this surface without requiring manual intervention. The automated detection and computation processes perform the complex analysis tasks independently, improving diagnostic efficiency while the modular architecture manages system complexity.
Solution Approach 2:
The patent replaces manual visual assessment and manual measurement techniques with automated computational algorithms. The computer-based system performs complex 3D-to-2D transformations, surface detection, and orientation calculations that would be extremely time-consuming and subjective if done manually, thereby improving productivity while the algorithms manage the computational complexity.
Data Source
AI summary
A system for analyzing an at least three-dimensional medical image comprises a lesion detector (51) for identifying a lesion (4) represented by the image. A surface detector (52) identifies at least part of a surface (5) of an object represented by the image. Means (53) are provided for establishing an orientation of the lesion (4) with respect to at least part of the surface (5), based on an output of the lesion detector (51) and an output of the surface detector (52). A model fitter (54) fits a model (6) to the lesion (4). The means (53) for establishing an orientation of the lesion (4) comprises a lesion orientation detector (56) for computing an orientation value (α) indicative of an orientation of the model (6) with respect to at least part of the surface (5).


