MRI Scan Parameter Mapping Without Localizer Images

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional MRI systems require time-consuming localizer images to locate anatomical regions of interest, prolonging scan duration and causing patient discomfort due to repeated adjustments.

Innovation Solution

Utilizing deep neural networks to map MR calibration images to landmark maps, enabling direct determination of diagnostic-scan parameters without localizer images, thereby automating the process and reducing scan time.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If localizer images are acquired to locate anatomical regions of interest, then anatomical location accuracy is improved, but total scan duration is prolonged

Engineering Contradiction:

Improveanatomical location accuracyVSAvoidtotal scan duration

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary action by using calibration images (acquired before diagnostic scanning) to pre-determine diagnostic-scan parameters through deep neural network processing. This eliminates the need for separate localizer image acquisition, as the calibration images are reused for both calibration and anatomical localization purposes, thereby reducing total scan duration while maintaining anatomical location accuracy

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The invention makes calibration images multi-functional by using them for both their original purpose (hardware calibration and intensity normalization) and for determining diagnostic-scan parameters. The deep neural network extracts anatomical information from calibration images, enabling a single image to serve multiple functions and eliminate redundant scanning steps

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Reliability

If localizer scans are repeated due to inadequate anatomical display or imaging artifacts, then anatomical region clarity is improved, but total MRI duration is prolonged

Engineering Contradiction:

Improveanatomical region clarityVSAvoidtotal MRI duration

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system implements feedback by using deep neural networks to automatically analyze calibration images and determine diagnostic-scan parameters with high reliability. The network provides consistent anatomical localization without human intervention, eliminating the need for repeated scans due to operator error or inadequate initial parameter selection, thereby preventing time loss from repeat acquisitions

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system performs self-service by automatically determining diagnostic-scan parameters from calibration images through deep neural network processing without requiring operator interpretation or manual adjustment. This automation ensures consistent anatomical region clarity while eliminating the time-consuming iterative process of manual parameter adjustment and repeat scanning

Inventive Principle:

Principle #25Self-service

3Measurement precision

If calibration images are used for hardware calibration, then hardware setting accuracy is improved, but anatomical location information is insufficient

Engineering Contradiction:

Improvehardware setting accuracyVSAvoidanatomical location information

Core Design Contradiction:

Measurement precisionVSLoss of information

Solution Approach 1:

The invention changes parameters by transforming calibration images from their traditional low-resolution, large-FOV state into rich anatomical information sources through deep neural network processing. The network extracts detailed anatomical features and determines precise diagnostic-scan parameters, converting the calibration image's limited apparent information content into comprehensive anatomical location data without altering the original image acquisition

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS12588817B2Systems and methods for generating diagnostic scan parameters from calibration images

Publication Date: 2026.03.31 GE PRECISION HEALTHCARE LLC

AI summary

Methods and systems are provided for determining diagnostic-scan parameters for a magnetic resonance (MR) diagnostic-scan, from MR calibration images, enabling acquisition of high-resolution diagnostic images of one or more anatomical regions of interest, while bypassing acquisition of localizer images, increasing a speed and efficiency of MR diagnostic-scanning. In one embodiment, a method for a magnetic resonance imaging (MRI) system comprises, acquiring a magnetic resonance (MR) calibration image of an imaging subject, mapping the MR calibration image to a landmark map using a trained deep neural network, determining one or more diagnostic-scan parameters based on the landmark map, acquiring an MR diagnostic image according to the diagnostic-scan parameters, and displaying the MR diagnostic image via a display device.