Medical image processing apparatus and medical image processing method
By introducing a reference point detection and structure scoring mechanism into a medical image processing device, and combining the probability distribution of position and structural features, the problem of low accuracy and detection rate of feature point detection in medical images is solved, and more efficient feature point localization is achieved.
JP2026086572APending Publication Date: 2026-05-26CANON MEDICAL SYST CORP
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Applications
- Current Assignee / Owner
- CANON MEDICAL SYST CORP
- Filing Date
- 2026-02-05
- Publication Date
- 2026-05-26
AI Technical Summary
Technical Problem
Existing technologies have low accuracy and detection rate in feature point detection in medical images, especially in the presence of interfering tissues, making it difficult to accurately locate feature points.
Method used
By introducing a reference point detection unit, a candidate point generation unit, a position scoring unit, and a structure scoring unit into a medical image processing device, and combining the probability distributions of positional and structural features, candidate points that meet the conditions are scored and selected as feature points.
Benefits of technology
It improves the detection accuracy and rate of multiple feature points in medical images, and can accurately locate feature points even in the presence of interfering tissue.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure 2026086572000001_ABST
Abstract
The present invention provides a medical image processing device that accurately detects multiple feature points in medical images. [Solution] The medical image processing device comprises a reference point detection unit, a candidate point generation unit, a position score unit, a structure score unit, and an output unit. The reference point detection unit detects a reference point in the medical image that has a spatial correlation with the target point for each of the multiple target points corresponding to the multiple feature points. The candidate point generation unit generates multiple candidate points corresponding to each of the multiple target points using a detection model. The position score unit selects a candidate point for each of the multiple target points based on position features that indicate the spatial positional relationship between the target point and the reference point. The structure score unit selects a candidate point combination for each of the multiple candidate point combinations based on structure features that indicate the spatial structural relationship between the multiple target points. The output unit outputs multiple feature points in the medical image based on the selected candidate points and candidate point combinations.
Need to check novelty before this filing date? Find Prior Art