Patent Application for Medical Imaging Image Processing

ChangeBridge: Patent Apps - Health Informatics (G16H)

Published September 26th, 2024

Detected March 26th, 2026

Summary

The USPTO has published a new patent application (US20260087616A1) from Canon Medical Systems Corporation for a method of processing image data in medical imaging systems. The application details a technique using neural networks to improve image quality from input data, potentially enhancing diagnostic capabilities.

View original document View source feed page

What changed

This document is a published patent application from the USPTO detailing a method and apparatus for image data processing in medical imaging systems, filed by Canon Medical Systems Corporation. The core innovation involves training a neural network, using a pretrained domain-specific network, to infer output image data from input data, aiming to achieve superior image quality. This technology could lead to improved diagnostic accuracy and efficiency in medical imaging.

While patent applications do not impose direct regulatory obligations on entities, they signal technological advancements and potential future product developments. Companies operating in the medical imaging space, particularly those developing or utilizing AI-driven image enhancement software, should be aware of this patent filing. It may influence future product roadmaps, R&D investments, and competitive landscapes. No immediate compliance actions are required, but monitoring patent filings in this area is advisable for strategic planning.

Source document (simplified)

← USPTO Patent Applications

METHOD AND APPARATUS FOR PROCESSING IMAGE DATA IN A MEDICAL IMAGING SYSTEM

Application US20260087616A1 Kind: A1 Mar 26, 2026

Assignee

CANON MEDICAL SYSTEMS CORPORATION

Inventors

Joseph WHITEHEAD, Joseph MANAK, Yi HU

Abstract

A method for performing image data processing in a medical imaging system is provided. The method includes collecting a first image dataset, using the collected first image dataset, training a first neural network, based on a loss function having a perceptual component; and using the trained first neural network, inferring output image data from input image data obtained by the medical imaging system, such that the inferred output image data has an image quality better than an image quality of the obtained input image data. The training of the first neural network uses a pretrained second neural network. The pretrained second neural network is specific to a particular domain to which the medical imaging system corresponds.