Tumor Extraction Accuracy via Organ Context Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing medical image processing technologies are insufficient in extracting tumor regions with high accuracy, as they rely solely on machine learning determiners without incorporating the context of organ regions.
Innovation Solution
A medical image processing apparatus and method that includes an organ extraction unit and a tumor extraction unit, where the tumor extraction unit is generated using machine learning with known tumor regions as teacher data and organ regions as input data, enabling the extraction of tumor regions from diagnosis target images with improved accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If only a determiner that individually executes machine learning on the type of a tissue or a lesion is used, then the device complexity is reduced, but the measurement precision of tumor extraction is insufficient
Solution Approach 1:
The system is divided into multiple specialized components: an organ extraction unit that extracts organ regions from medical images, and a tumor extraction unit that extracts tumor regions. Each unit performs a specific function with high precision, rather than using a single general-purpose determiner, thereby resolving the contradiction between measurement precision and device complexity.
Solution Approach 2:
The organ extraction unit performs preliminary extraction of organ regions before the tumor extraction unit processes the images. This preliminary action provides contextual information about organ boundaries and structures, which improves the accuracy of subsequent tumor extraction while maintaining a modular system architecture.
2Measurement precision
If machine learning is executed using only tumor region data without organ region context, then the processing speed is maintained, but the extraction accuracy of tumor regions is insufficient
Solution Approach 1:
The organ extraction unit performs preliminary extraction of organ regions from medical images before the tumor extraction process. This preliminary action provides contextual information about organ boundaries and structures, which improves the accuracy of subsequent tumor extraction without requiring complete reprocessing of the entire image dataset.
Solution Approach 2:
The processing is segmented into distinct stages: organ region extraction followed by tumor region extraction. This segmentation allows each unit to focus on specific features, improving overall accuracy while maintaining efficient processing through specialized rather than generalized computation.
Data Source
AI summary
A medical image processing apparatus and a medical image processing method that can improve extraction accuracy of a tumor region included in a diagnosis target image are provided. The medical image processing apparatus configured to extract a predetermined region from a diagnosis target image includes: an organ extraction unit configured to extract an organ region from the diagnosis target image; and a tumor extraction unit generated by executing machine learning using a known tumor region included in each medical image group as teacher data and using an organ region extracted from the medical image group and the medical image group as input data. The tumor extraction unit is configured to extract a tumor region from the diagnosis target image using the organ region extracted from the diagnosis target image by the organ extraction unit.