Method for providing diagnostic auxiliary information and device for executing the same

A neural network-based method for medical image analysis segments and calculates standardized disease indexes, addressing subjective clinical judgments and image variability to enhance diagnostic accuracy.

JP7766365B2Active Publication Date: 2025-11-10NEUROPHET INC
View PDF 8 Cites -1 Cited by

Patent Information

Application Number
JP2024123085
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Filing Date
2024-07-30
Publication Date
2025-11-10
Estimated Expiration
2040-12-30

AI Technical Summary

Technical Problem

Existing medical image analysis methods rely heavily on clinical judgment, leading to subjective disease-related information, and segmentation variability across different image acquisition conditions hinders accurate diagnostic support.

Method used

A method using a highly trained artificial neural network to segment medical images, distinguishing between ventricular and white matter hyperintensity regions, and calculating standardized disease indexes based on reference boundaries, providing objective diagnostic auxiliary information.

Benefits of technology

Provides objective and clear disease information by standardizing the analysis, eliminating the influence of clinical judgment and accounting for image diversity, thus enhancing accuracy.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007766365000003
    Figure 0007766365000003
  • Figure 0007766365000004
    Figure 0007766365000004
  • Figure 0007766365000005
    Figure 0007766365000005
Patent Text Reader

Abstract

To provide a method for providing diagnostic aid information by analyzing a medical image, and a system for executing the same.SOLUTION: A provision method of diagnostic aid information for providing diagnostic aid information by analyzing a medical image, includes: acquiring an image; labeling a feature value reflecting a region of a brain; determining a reference boundary in the brain image; calculating a first disease index and a second disease index; and providing diagnostic aid information based on the first disease index and the second disease index.SELECTED DRAWING: Figure 5
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Cluster-based automatic WMH extraction system

    CN108171697A

  • White matter hyperintensities automatic segmentation system and method based on Unet model

    CN109859215A

  • Method and device for segmenting brain white matter high signal based on deep learning method

    CN110991408A

  • White matter high-signal scoring system and scoring method thereof

    CN111681230A

  • Improved Lesion Detection Methods

    JP2023522366A