Pelvic Ultrasound Image Evaluation for Objective Function Indices

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing ultrasonic image evaluation methods for pelvic regions rely heavily on subjective interpretation, lacking objective indices for lower urinary tract and pelvic floor functions.

Innovation Solution

An image evaluation method and device that automates the extraction of feature points from ultrasonic images to calculate objective indices such as the angle of the bladder neck, bulbar urethra, and distance between the inferior margin of the pubis and anorectal angle, using algorithms like YOLO and Hough transform, enabling automated calculation of these indices.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual evaluation of ultrasonic images is performed by observers, then flexibility and adaptability are maintained, but objectivity and measurement precision deteriorate due to subjective interpretation

Engineering Contradiction:
Improveevaluation objectivityVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent replaces the manual mechanical evaluation process with an automated image processing system using algorithms (YOLO for detection, Hough transform for line detection) to calculate anatomical indices objectively from ultrasonic images, eliminating observer subjectivity while maintaining evaluation capability

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system performs self-evaluation by automatically processing ultrasonic images to extract feature points and calculate indices without requiring human observers, making the evaluation process independent of human subjectivity while preserving the essential measurement function

Inventive Principle:
Principle #25Self-service

2Measurement precision

If automated image processing is implemented to extract feature points and calculate indices, then measurement precision and objectivity improve, but device complexity and processing time increase

Engineering Contradiction:
Improveindex calculation accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The patent applies preliminary image processing steps (binarization, edge detection) before feature extraction to simplify the image data structure, making subsequent automated feature point detection and index calculation more efficient and accurate

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The evaluation process is segmented into distinct automated stages: image acquisition, preprocessing, feature point extraction using YOLO, line detection using Hough transform, and index calculation, allowing each stage to be optimized independently for efficiency and accuracy

Inventive Principle:
Principle #1Segmentation

3Adaptability or versatility

If multiple feature points are extracted to calculate multiple indices, then evaluation comprehensiveness improves, but device complexity and computational requirements increase

Engineering Contradiction:
Improveevaluation coverageVSAvoidprocessing complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent implements a universal automated evaluation system that can calculate multiple different indices (bladder neck angle, pubis-anorectal distance, etc.) using the same core image processing framework and feature extraction algorithms, enabling comprehensive evaluation without proportionally increasing system complexity

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP4721676A1Image evaluation method, image evaluation device, computer program, and non-transitory computer-readable medium
Publication Date: 2026.04.08 TOKYO DENKI UNIVERSITY
  • EP4721676A1 patent drawingFigure 1~2
  • EP4721676A1 patent drawingFigure 3
  • EP4721676A1 patent drawingFigure 4

AI summary

It is acquired image data corresponding to an ultrasonic image in which a pelvic region of a subject is captured. Image processing is applied with respect to the image data to extract multiple feature points associated with a prescribed portion. It is calculated an index value associated with at least one of a lower urinary tract function and a pelvic floor function of the subject based on the feature points.