USPTO Patent Grant: Synthetic Electron Density Images from MRI

ChangeBridge: Patent Grants - AI & Computing (G06N)

Published March 24th, 2026

Detected March 24th, 2026

Summary

The USPTO has granted patent US12582373B2 to Spectronic AB for a method of generating synthetic electron density images (sCT) from magnetic resonance (MR) images using a machine-learning model. This technology aims to improve the accuracy and efficiency of medical image processing.

View original document View source feed page

What changed

USPTO Patent Grant US12582373B2, assigned to Spectronic AB, details a novel method for generating synthetic CT (sCT) images from MRI data using a machine-learning model. The patent focuses on a conversion device that processes MR images to predict coefficients for an image transfer function, thereby computing an sCT image. This method is designed to be processing-efficient and robust to misalignment in training data, potentially offering a more accurate and accessible alternative to traditional CT scans for certain diagnostic purposes.

This patent grant does not impose new regulatory obligations on healthcare providers or medical device manufacturers. However, it signifies a technological advancement in medical imaging that may influence future product development and clinical practice. Compliance officers should note this development as it relates to the integration of AI and machine learning in medical devices and diagnostic tools, particularly concerning data processing and image generation standards.

Source document (simplified)

← USPTO Patent Grants

Generating synthetic electron density images from magnetic resonance images

Grant US12582373B2 Kind: B2 Mar 24, 2026

Assignee

SPECTRONIC AB

Inventors

Carl Siversson

Abstract

A conversion device is operable to perform a learning-based method of generating a synthetic electron density image (sCT) of an anatomical portion based on one or more magnetic resonance (MR) images. The method is processing-efficient and capable of producing highly accurate sCT images irrespective of misalignment in the underlying training set. The conversion device receives and installs a machine-learning model trained to predict coefficients of an image transfer function. The conversion device then receives a current set of MR images of the anatomical portion, computes current coefficients of the image transfer function by operating the machine-learning model on the current set of MR images, and computes a current sCT image of the anatomical portion by operating the current coefficients, in accordance with the image transfer function, on the current set of MR images.

CPC Classifications

A61B 6/5235 A61B 5/055 A61B 6/032 A61B 6/5205 A61B 6/5229 A61B 6/5247 A61N 5/1039 G06N 20/00 G06T 2207/10088 G06T 2207/20081 G06T 2207/20084 G06T 2207/30004 G06T 11/001 G01R 33/4812 G01R 33/5608 G16H 50/20 G16H 30/40