Medical Image Model Allocation for Faster Scan Throughput
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing demand for assisted diagnosis in medical imaging is leading to higher computing requirements and longer processing times, reducing the usage rate of imaging devices and the number of patients scanned per day.
Innovation Solution
A method and apparatus that utilize a learning network model allocation system, selecting an appropriate model based on medical image information to perform image processing independently of medical imaging systems, allowing for efficient image processing and reducing the load on these systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If image processing is performed directly in the medical imaging device, then image processing capability is provided, but the usage rate of the imaging device is reduced and the number of patients scanned per day decreases
Solution Approach 1:
The patent extracts the image processing function from the medical imaging device and places it in a separate image processing device. This allows the imaging device to focus solely on acquiring images while the processing is handled independently, thereby increasing the imaging device's usage rate and patient throughput while maintaining comprehensive image processing capabilities.
2Adaptability or versatility
If image processing is performed directly in the medical imaging device, then image processing is integrated, but the computing time required increases and scanning efficiency decreases
Solution Approach 1:
By extracting the computationally intensive image processing tasks from the imaging device and performing them in a separate dedicated processing device, the system reduces the computing time that would otherwise block the imaging workflow. This separation allows parallel operation where image acquisition can proceed without waiting for processing completion.
3Measurement precision
If multiple learning network models are maintained for different medical image types, then processing accuracy is improved, but device complexity increases
Solution Approach 1:
The patent implements a universal image processing device that can handle multiple types of medical images (CT, MRI, X-ray, ultrasound) and perform various processing tasks (segmentation, rendering, editing) using a single integrated system. This multi-functional approach maintains high processing accuracy across different image types while avoiding the complexity of duplicating multiple specialized systems.
Data Source
AI summary
The present application provides a method, a non-transitory computer-readable storage medium, and apparatus for allocating image processing. The method for allocating image processing can include, on the basis of relevant information of a medical image, selecting, according to an allocation list, a learning network model corresponding to the information from a plurality of learning network models. The method can also include performing image processing on the medical image on the basis of the selected learning network model, the allocation list including a list of correspondences between relevant information of medical images and the plurality of learning network models.