Ultrasound Frequency Conversion Model for Lumen Organ Imaging
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing ultrasound diagnostic systems can predict optimal parameters but fail to convert acquired ultrasound images into desired frequencies, limiting diagnostic flexibility.
Innovation Solution
A computer-readable medium and information processing device that utilize machine learning models, such as generative adversarial networks (GANs) and StarGAN, to convert ultrasound images from one frequency to another, enhancing diagnostic capabilities by generating images of desired frequencies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If machine learning models are used to convert ultrasound images between frequencies, then diagnostic flexibility and image resolution are improved, but device complexity and computational requirements increase
Solution Approach 1:
A machine learning model acts as an intermediary between the acquired ultrasound image and the desired frequency conversion. The model receives the input image and generates the converted frequency image, enabling flexible diagnostic analysis without requiring physical re-imaging at different frequencies.
Solution Approach 2:
The patent replaces the mechanical approach of physical re-imaging at different frequencies with a computational machine learning system. This substitution eliminates the need for multiple physical imaging setups while achieving the same diagnostic goal through image processing.
2Measurement precision
If machine learning models convert ultrasound images to desired frequencies, then image resolution and diagnostic clarity are improved, but processing time and computational resources increase
Solution Approach 1:
The machine learning model is trained in advance on large datasets of ultrasound images at different frequencies. This preliminary training phase enables the model to perform rapid frequency conversion during actual diagnostic use, as the complex computational work has already been completed during the training stage.
Solution Approach 2:
The patent changes the frequency parameter of the ultrasound image through machine learning conversion. By transforming the image data in the frequency domain rather than performing complex spatial transformations, the system achieves high resolution conversion with reduced processing time.
Data Source
AI summary
A non-transitory computer-readable medium (CRM) storing computer program code executed by a computer processor that executes a process, an information processing apparatus, and model generation method that generates an image of a lumen organ. The process includes acquiring a first image obtained by imaging a lumen organ of a patient based on an ultrasound signal of a first frequency; and generating a second image by inputting the acquired first image into a model, the model being learned to generate, when the first image is input, the second image in which the lumen organ is imaged based on an ultrasound signal of a second frequency. Preferably, the second image, in which a part of an image region of the first image is converted into the second frequency, is generated using the model, and a synthesis image is generated in which the second image is superimposed to the first image.