Systems, devices, and methods for improving medical images using machine learning

A combined machine learning model for medical imaging dynamically adjusts image enhancements based on user input and conditions, addressing the inflexibility of conventional models by integrating multiple specialized models for enhanced image quality.

JP2026116844APending Publication Date: 2026-07-13STRYKER CORP
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
JP2025284595
Authority / Receiving Office
JP · JP
Patent Type
Applications
Current Assignee / Owner
Priority Date
2024-12-31
Filing Date
2025-12-26
Publication Date
2026-07-13

AI Technical Summary

Technical Problem

Conventional image improvement techniques, including machine learning models, fail to provide real-time control over image quality adjustments such as smoothness, sharpness, and contrast, making them inflexible for different user preferences and imaging conditions in medical imaging.

Method used

A combined machine learning model is created by integrating multiple specialized models for image enhancement, allowing real-time tuning of image enhancements based on user preferences and imaging conditions, using weighted contributions of individual models.

Benefits of technology

Enables adaptable and high-quality image enhancement in medical imaging, optimizing image quality for various medical procedures and user preferences without retraining, reducing computational overhead.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 2026116844000002
    Figure 2026116844000002
  • Figure 2026116844000003
    Figure 2026116844000003
  • Figure 2026116844000004
    Figure 2026116844000004
Patent Text Reader

Abstract

This invention provides a method and a medical imaging system for creating improved medical images. [Solution] An exemplary method for creating improved medical images is to receive user interaction via a user interface, the interaction including the user's preferences for image improvement; to adjust a combined machine learning model including a combination of multiple expert machine learning models based on the user interaction, the adjustment of the combined machine learning model being to adjust the contribution of at least one of the multiple expert machine learning models to the combined model; and to create one or more improved medical images by inputting medical image data into the combined machine learning model, the combined machine learning model being configured to create one or more improved medical images from medical image data, and to display one or more improved medical images.
Need to check novelty before this filing date? Find Prior Art