Lateral-Lateral Skull Radiograph Analysis for Precise Landmark Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for detecting anatomical points of interest in lateral-lateral teleradiographs of the skull are time-consuming, highly dependent on the analyst's experience, and prone to inaccuracies, leading to potential incorrect diagnoses and treatments.

Innovation Solution

A computer-implemented method using a radiographic system with a display unit and processing means that performs learning and inference steps to accurately detect anatomical points through a combination of general and refinement models, including data augmentation and deep learning techniques like SSD and CenterNet, to enhance precision.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual detection of anatomical points by doctors is used, then flexibility and adaptability are maintained, but detection time increases and measurement precision decreases

Engineering Contradiction:

Improvedetection precisionVSAvoiddetection time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical detection process with an automated computer vision system using deep learning models (SSD and CenterNet). The system processes radiographic images through neural networks that automatically identify anatomical points, eliminating the need for manual visual inspection and measurement by doctors.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service detection where the computer vision algorithm autonomously identifies and marks anatomical points without requiring continuous human intervention. The automated pipeline includes image preprocessing, model inference, and result generation, allowing the system to serve itself in completing the detection task.

Inventive Principle:

Principle #25Self-service

2Reliability

If manual detection by doctors is used, then adaptability to different cases is maintained, but reliability and consistency of results deteriorate due to human factors

Engineering Contradiction:

Improvediagnosis reliabilityVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent replaces the human doctor's manual detection process with an automated computer vision system. This substitution eliminates variability introduced by human factors such as fatigue, concentration levels, and experience differences, providing consistent and reliable detection results across all cases.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system uses multiple detection models (SSD and CenterNet) with different parameters and approaches to detect anatomical points. By changing detection parameters and using ensemble methods, the system achieves higher reliability while managing complexity through modular architecture.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If simple display and manual storage systems are used, then ease of operation is maintained, but information completeness and measurement precision are insufficient

Engineering Contradiction:

Improveanatomical point detection precisionVSAvoidsystem operation simplicity

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent replaces simple display and manual storage systems with an automated computer vision pipeline that performs detection, processing, and analysis. The system automatically generates precise anatomical point coordinates and integrates them into the workflow, improving measurement precision while maintaining ease of operation through automated processing.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250217983A1Method for the analysis of radiographic images, and in particular lateral-lateral teleradiographic images of the skull, and relative analysis system

Publication Date: 2025.07.03 CEFLA SOC COOP

AI summary

A computer-implemented method for the geometric analysis of digital radiographic images, in particular lateral-lateral teleradiographs of the skull, uses a radiographic system that includes a display unit and processing system connected to the display unit. The radiographic system is configured for analyzing digital radiographic images.