Pseudo Radiographic Image Generation Using Neural Networks

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current medical imaging techniques, such as MRI and CT scans, require time-consuming initial survey scans and may expose patients to additional radiation, especially when positioning the subject and adjusting the region of interest, which can be inaccurate.

Innovation Solution

A medical instrument and method utilizing an image transformation neural network to generate a pseudo radiographic image from an optical image, allowing for accurate anatomical landmark identification and positioning without the need for real-time radiographic imaging, thereby accelerating the imaging process and reducing radiation exposure.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If initial survey scans are taken to position the subject and adjust the region of interest, then positioning accuracy is improved, but the process becomes time-consuming and exposes the subject to additional ionizing radiation

Engineering Contradiction:

Improvepositioning accuracyVSAvoidpositioning time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent creates a pseudo radiographic image that copies the essential anatomical information from optical images. This synthetic copy provides sufficient positioning accuracy without requiring actual radiographic survey scans, thereby eliminating the time loss and radiation exposure associated with traditional survey scans while maintaining the ability to accurately identify anatomical landmarks for subject positioning

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent introduces a neural network as an intermediary that transforms optical images into pseudo radiographic images. This intermediary process enables the system to derive positioning information from non-ionizing optical images while producing output that mimics radiographic quality, thus avoiding direct radiation exposure while maintaining positioning accuracy

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If initial survey scans are taken to position the subject and adjust the region of interest, then positioning accuracy is improved, but the process becomes time-consuming

Engineering Contradiction:

Improvepositioning accuracyVSAvoidimaging throughput

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The pseudo radiographic image serves as a sufficient copy for positioning purposes, eliminating the need for time-consuming real radiographic survey scans. The neural network rapidly generates this copy from optical images, maintaining positioning accuracy while significantly reducing the time required for subject positioning and thereby improving overall imaging throughput

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent replaces the mechanical radiographic imaging system with a computational neural network system. Instead of using physical X-ray equipment to generate survey scans, the system uses software-based image transformation to create pseudo radiographic images from optical inputs, eliminating the time delay associated with mechanical radiographic systems while maintaining positioning functionality

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Measurement precision

If real radiographic imaging is used for positioning, then anatomical landmark identification is accurate, but radiation exposure increases

Engineering Contradiction:

Improveanatomical landmark identification accuracyVSAvoidradiation exposure

Core Design Contradiction:

Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent creates a pseudo radiographic copy that contains all necessary anatomical landmark information without using actual radiation. The neural network transforms optical images into synthetic radiographic-like images that preserve anatomical structure details, enabling accurate landmark identification while completely avoiding ionizing radiation exposure to the subject

Inventive Principle:

Principle #26Copying

Solution Approach 2:

The patent converts the potentially harmful radiographic imaging process into a beneficial non-ionizing alternative. By using optical images as input and generating pseudo radiographic images through neural network transformation, the system achieves the same anatomical visualization goals without the harmful radiation component, effectively turning a harmful process into a safe one

Inventive Principle:

Principle #22Blessing in disguise (Convert harm into benefit)

Data Source

PatentUS11983800B2Generation of pseudo radiographic images from optical images

Publication Date: 2024.05.14 KONINKLIJKE PHILIPS NV

AI summary

The invention provides for a medical instrument comprising a memory storing machine executable instructions and an image transformation neural network trained for transforming an optical image of a subject into an output image. The output image comprises a pseudo radiographic image. The pseudo radiographic image is aligned with the optical image. The medical instrument further comprises a processor configured to control the medical imaging system. Execution of the machine executable instructions causes the processor to: receive the optical image of the subject and generate the output image by inputting the optical image into the image transformation neural network.