AI Landmark Detection for Medical Apparatus Positioning Quality

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing methods for determining the positioning of external apparatuses in patients' bodies are subjective, delayed, and prone to errors, leading to potential life-threatening complications due to incorrect placement.

Innovation Solution

An AI-based method using machine learning to automatically detect and localize anatomical landmarks and external apparatuses in medical images, enabling rapid and objective assessment of positioning quality through anatomical landmarks and measurable dimensions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If medical images are evaluated manually by a radiologist to determine apparatus position, then measurement precision can be achieved, but loss of time occurs due to delayed evaluation

Engineering Contradiction:

Improvepositioning quality determinationVSAvoidevaluation delay

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces the manual mechanical evaluation process with an automated image recognition system using artificial intelligence. The system automatically detects the external apparatus and anatomical landmarks in medical images, calculates positioning quality metrics, and provides immediate feedback without requiring radiologist intervention, thus eliminating evaluation delays while maintaining precision through algorithmic consistency

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables self-service by allowing the imaging equipment to automatically perform positioning quality assessment without external human intervention. The automated detection and evaluation process operates independently, providing immediate results that eliminate the time loss associated with manual radiologist evaluation

Inventive Principle:

Principle #25Self-service

2Reliability

If manual evaluation by radiologists is used, then reliability of positioning assessment can be maintained through expert judgment, but device complexity increases due to subjective interpretation variations

Engineering Contradiction:

Improvepositioning assessment consistencyVSAvoidsubjective interpretation variability

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent transforms the subjective interpretation process into objective parameter-based assessment. The system detects specific anatomical landmarks and apparatus positions, calculates quantitative positioning quality metrics based on measured distances and angles, and provides standardized evaluation results. This parameter-based approach eliminates subjective variability while maintaining reliability through consistent algorithmic application

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent replaces the complex human judgment process with a standardized automated system. The image recognition algorithm consistently applies the same detection and measurement criteria to all cases, eliminating the variability inherent in different radiologists' interpretations while maintaining assessment reliability through proven computational methods

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Loss of time

If automatic image analysis is used to identify external apparatuses, then loss of time is reduced through immediate processing, but measurement precision decreases due to difficulty in correct object classification

Engineering Contradiction:

Improveevaluation speedVSAvoidobject classification accuracy

Core Design Contradiction:

Loss of timeVSMeasurement precision

Solution Approach 1:

The patent segments the image analysis process into distinct functional stages: detection of the external apparatus, detection of anatomical landmarks, measurement of positioning parameters, and calculation of quality metrics. This segmentation allows each stage to be optimized independently, ensuring both rapid processing and accurate classification by breaking down the complex task into manageable, precise steps

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system introduces intermediary computational steps between image input and final classification. The image recognition algorithm uses intermediate features such as detected landmarks, measured distances, and calculated angles as mediators to bridge the gap between raw image data and accurate apparatus classification, thereby maintaining precision while enabling rapid automated processing

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS12611259B2Determining how well an object inserted into a patient's body is positioned

Publication Date: 2026.04.28 SIEMENS HEALTHINEERS AG

AI summary

A method is for determining a positioning quality of an external apparatus inserted into a patient's body. In the method, image data of the patient's body is detected; an at least one first anatomical landmark is detected in or with a first subregion, in which the external apparatus is positioned as expected; at least a first subsection of the external apparatus is sought in or with the at least one first subregion; a second anatomical landmark is detected in or with at least one second subregion; at least one second subsection is then detected based upon the already localized subsection; and a quality of the positioning of the at least one second subsection is determined by measuring a suitable dimension between the localized at least one second subsection and the at least one second landmark. A training method, a positioning quality determination facility and a training facility are also disclosed.