Surface Point Filtering for Hair-Obscured Medical Registration

Solution Overview

Problem

Existing surface-based image registration methods in medical navigation systems face challenges with measurement errors due to contact-based methods and the inability of contact-free methods to acquire points on covered regions, such as those obscured by hair.

Innovation Solution

A method for sampling relevant surface points by determining and validating surface points based on tissue type, using a computer-implemented process to identify and discard non-relevant points, thereby improving surface geometry acquisition.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If contact-based methods are used to acquire surface points, then points can be acquired on covered regions, but measurement errors occur since points are acquired above or below the actual surface

Engineering Contradiction:

Improvesurface point accuracyVSAvoidability to acquire points on covered regions

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The system performs preliminary classification of surface points by tissue type before using them for registration. By pre-identifying and filtering out non-relevant points (such as hair or drapes) based on their tissue type characteristics, the system ensures that only relevant anatomical surface points are used for measurement, thereby eliminating measurement errors while maintaining the ability to work on covered regions.

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If contact-free methods are used to acquire surface points, then measurement accuracy is improved, but points cannot be acquired on covered regions such as those obscured by hair

Engineering Contradiction:

Improvesurface point accuracyVSAvoidability to acquire points on covered regions

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The system performs preliminary classification of surface points by tissue type before using them for registration. By pre-identifying and filtering out non-relevant points (such as hair or drapes) based on their tissue type characteristics, the system ensures that only relevant anatomical surface points are used for measurement, thereby eliminating measurement errors while maintaining the ability to work on covered regions.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system changes the parameter used for point validation from simple spatial coordinates to include tissue type classification. By incorporating tissue type as an additional parameter for point validation, the system can distinguish between relevant anatomical surfaces and irrelevant covered regions, enabling accurate acquisition of points on previously inaccessible areas.

Inventive Principle:

Principle #35Parameter changes

3Quantity of substance

If all acquired surface points are used for registration, then data coverage is maximized, but accuracy decreases due to inclusion of non-relevant points

Engineering Contradiction:

Improvenumber of surface pointsVSAvoidregistration accuracy

Core Design Contradiction:

Quantity of substanceVSMeasurement precision

Solution Approach 1:

The system applies different quality criteria to different surface points based on their tissue type classification. Instead of treating all points uniformly, the system identifies and selectively validates points with relevant tissue types (such as skin or mucosa) while discarding points from non-relevant tissue types (such as hair or synthetic drapes). This local quality differentiation ensures high registration accuracy while maintaining sufficient data coverage from relevant anatomical regions.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS12458445B2Method of sampling relevant surface points of a subject

Publication Date: 2025.11.04 BRAINLAB AG

AI summary

A method and a registration device for sampling relevant surface points of a subject for a medical navigation system is presented. From a plurality of surface points of the subject, relevant surface points are accepted and non-relevant surface points are discarded. The method allows the surface geometry acquisition of a subject to be improved. For this purpose, additional information of the surface points is acquired and assigned to the respective surface point for validating each surface point.