Medical Image Restoration Model for Low-Dose Quality Standardization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The inconsistency in image quality among different medical devices and varying user perceptions leads to challenges in standardizing image quality evaluation, and existing methods to enhance image quality often increase radiation dose and subject discomfort.
Innovation Solution
A method involving a trained image perception restoration model with an image quality perception sub-model and an image restoration sub-model to evaluate and enhance medical images, ensuring a unified quality standard.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If traditional image quality enhancement methods are used, then image quality is improved, but radiation dose increases and subject discomfort increases
Solution Approach 1:
The patent uses a neural network model to learn the mapping relationship between low-quality images (with lower radiation dose) and high-quality images (with higher radiation dose). The model copies the essential features and structural information from high-quality images to reconstruct improved quality from low-quality inputs, avoiding the need to actually increase radiation dose while achieving enhanced image quality through computational reconstruction
Solution Approach 2:
The patent changes the parameter of radiation dose by using deep learning models to reconstruct images with improved quality from low-dose inputs. The neural network learns to transform image parameters (such as noise reduction, contrast enhancement, and detail preservation) through computational processing, achieving quality improvement without physical changes to the imaging parameters during acquisition
2Adaptability or versatility
If different medical devices are used, then imaging capability is enhanced, but image quality consistency deteriorates
Solution Approach 1:
The patent develops a universal neural network model that can process images from multiple different medical imaging devices (CT, MRI, PET, etc.). The model is trained on diverse image data and learns device-specific characteristics and quality variations, enabling it to standardize image quality across different device types while preserving the imaging capabilities and versatility of each device
Solution Approach 2:
The neural network model acts as an intermediary between images from different medical devices and the final diagnostic output. It mediates the quality inconsistencies by learning the specific characteristics of each device type and transforming their outputs into a unified quality standard, allowing diverse imaging capabilities to coexist while achieving consistent image quality
3Measurement precision
If image quality evaluation is performed manually, then evaluation accuracy is maintained, but evaluation time increases and efficiency decreases
Solution Approach 1:
The patent replaces the manual mechanical evaluation process with an automated neural network-based assessment system. The model automatically analyzes image quality parameters such as noise level, contrast, resolution, and diagnostic utility, substituting human expert judgment with computational analysis that maintains high accuracy while dramatically increasing evaluation efficiency and throughput
Data Source
AI summary
A system and a method for medical image processing are provided. The method includes: obtaining a first medical image; obtaining a trained image perception restoration model; the trained image perception restoration model includes an image quality perception sub-model and an image restoration sub-model; and inputting the first medical image into the trained image perception restoration model to obtain a second medical image. The image quality perception sub-model is configured to determine either or both of a first quality evaluation value of the first medical image and a second quality evaluation value of the second medical image, the image restoration sub-model is configured to determine the second medical image, and the quality of the second medical image is higher than that of the first medical image.