MRI Diagnostic Scan Parameters from Calibration Images

ChangeBridge: Patent Grants - Diagnosis & Surgery (A61B)

Published March 31st, 2026

Detected March 31st, 2026

Summary

The USPTO granted patent US12588817B2 to GE Precision Healthcare LLC for methods and systems that determine MRI diagnostic scan parameters directly from calibration images, bypassing the need for separate localizer images. The patent covers a trained deep neural network that maps calibration images to landmark maps to generate high-resolution diagnostic images more efficiently.

View original document View source feed page

What changed

USPTO granted patent US12588817B2 to GE Precision Healthcare LLC (inventors: André De Almeida Maximo, Dattesh Dayanand Shanbhag, Chitresh Bhushan, Dawei Gui) covering methods for determining MRI diagnostic scan parameters from MR calibration images using a trained deep neural network. The system maps calibration images to landmark maps and determines diagnostic-scan parameters, enabling high-resolution imaging while bypassing localizer image acquisition. The patent (7 claims) covers CPC classifications G01R 33/58, G01R 33/543, A61B 5/0073, A61B 5/005, and A61B 5/055.

Healthcare facilities and medical device manufacturers using MRI technology should note this patent grants intellectual property rights to GE Precision Healthcare for AI-driven MRI parameter optimization. Organizations developing or licensing MRI systems may need to consider potential licensing requirements or design-around strategies. No immediate compliance deadlines or penalties are associated with this patent grant, which serves as an informational notice of intellectual property rights rather than a regulatory mandate.

Source document (simplified)

← USPTO Patent Grants

Systems and methods for generating diagnostic scan parameters from calibration images

Grant US12588817B2 Kind: B2 Mar 31, 2026

Assignee

GE PRECISION HEALTHCARE LLC

Inventors

André De Almeida Maximo, Dattesh Dayanand Shanbhag, Chitresh Bhushan, Dawei Gui

Abstract

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.