Medical Imaging Plane Determination from Artifact-Corrected Pre-Scans

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing medical image diagnostic apparatuses struggle to accurately determine standard imaging planes and reference lines when positioning images contain metal artifacts, motion artifacts, or other abnormalities, requiring manual correction that is time-consuming and inefficient.

Innovation Solution

The apparatus employs processing circuitry to generate a normal positioning image from an abnormal one using machine learning models, image databases, and modality conversion techniques to correct abnormalities, allowing automatic determination of imaging planes and reference lines.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automatic determination of imaging planes and reference lines is performed using positioning images, then productivity is improved, but measurement precision deteriorates when artifacts are present

Engineering Contradiction:

Improveautomation of imaging plane determinationVSAvoidaccuracy of anatomical feature point detection

Core Design Contradiction:

ProductivityVSMeasurement precision

Solution Approach 1:

The patent introduces a trained machine learning model as an intermediary between the positioning image and the imaging plane determination. The model processes the positioning image to generate corrected images that eliminate artifacts while preserving anatomical structures, enabling accurate feature point detection even when the original image contains metal artifacts, motion artifacts, or other abnormalities

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent transforms the positioning image through the machine learning model to change its parameters - specifically removing artifacts and correcting abnormalities - while maintaining the underlying anatomical information. This parameter transformation enables subsequent automatic determination to proceed accurately despite the presence of artifacts in the original image

Inventive Principle:

Principle #35Parameter changes

2Measurement precision

If manual correction of positioning images is performed to address artifacts, then measurement precision is improved, but loss of time increases

Engineering Contradiction:

Improveaccuracy of imaging plane determinationVSAvoidtime for manual image correction

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent implements self-service by enabling the system to automatically correct its own positioning images using the trained machine learning model. The apparatus autonomously processes artifacts and abnormalities in the positioning image without requiring operator intervention, thereby maintaining high measurement precision while eliminating the time loss associated with manual correction

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent performs preliminary action by pre-training the machine learning model on a large dataset of images with various artifacts and abnormalities. This preliminary training enables the model to automatically correct positioning images in real-time during actual use, preventing the need for subsequent manual correction and saving time

Inventive Principle:

Principle #10Preliminary action

3Device complexity

If standard imaging planes are determined from positioning images with abnormalities, then device complexity is reduced, but reliability deteriorates

Engineering Contradiction:

Improvesimplicity of imaging workflowVSAvoidaccuracy of diagnostic imaging

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The patent introduces the machine learning model as a reliable intermediary that processes positioning images with abnormalities before they are used for imaging plane determination. This intermediary layer ensures that even when the original positioning image contains metal artifacts, motion artifacts, or other abnormalities, the corrected image provides reliable anatomical information for accurate diagnostic imaging

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent performs preliminary correction of positioning images using the trained machine learning model before the imaging plane determination process. This preliminary action removes artifacts and corrects abnormalities in advance, ensuring that subsequent automatic determination operates on clean, reliable data while maintaining the simplicity of the overall workflow

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS12548156B2Medical image diagnostic apparatus

Publication Date: 2026.02.10 CANON MEDICAL SYST CORP

AI summary

In one embodiment, a medical image diagnostic apparatus includes: a scanner configured to perform a pre-scan of an object and a diagnostic scan of the object after the pre-scan; and processing circuitry. This processing circuitry is configured to: generate a positioning image from data acquired by the pre-scan and a diagnostic image from data acquired by the diagnostic scan; generate a normal positioning image from the generated positioning image when it is an abnormal positioning image having an abnormality, the normal positioning image being an image in which the abnormality is corrected; and determine an imaging plane of the diagnostic scan from the normal positioning image.