Anatomical Structure Segmentation Correction via Deformation Model

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current medical image segmentation tools cannot simultaneously modify multiple anatomical structures while respecting anatomical constraints, requiring separate modifications for each object and lacking consideration for inter-structural relationships.

Innovation Solution

A computer-implemented method that uses an atlas and geometric transformability model to segment medical patient images, allowing simultaneous modification of multiple structures by applying user interactions while adhering to anatomical constraints, such as physical connections and non-penetration boundaries, through a grid-based deformation model.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If current modification tools are used to modify anatomical structures, then one object can be modified at a time, but multiple structures cannot be modified simultaneously while respecting anatomical constraints

Engineering Contradiction:

ImproveAbility to modify multiple structures simultaneouslyVSAvoidAnatomical constraint compliance

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent merges multiple separate modification operations into a single unified operation. When a user modifies one anatomical structure, the system automatically propagates the modification to other related structures through a deformation field that respects anatomical constraints. This allows simultaneous modification of multiple structures (improving versatility) while maintaining anatomical relationships (preserving reliability).

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The system implements feedback by continuously monitoring anatomical constraints during the modification process. When a structure is modified, the system calculates the impact on neighboring structures and adjusts the deformation accordingly to maintain anatomical validity. This feedback mechanism ensures that modifications remain reliable while enabling multi-structure adaptation.

Inventive Principle:

Principle #23Feedback

2Ease of operation

If separate modifications are applied to each object, then anatomical constraints are not considered, but consistent modification across multiple objects cannot be achieved

Engineering Contradiction:

ImproveModification process simplicityVSAvoidAnatomical structural consistency

Core Design Contradiction:

Ease of operationVSStability of the object's composition

Solution Approach 1:

The system performs preliminary action by pre-defining anatomical constraints and relationships between structures before the modification process begins. These constraints are encoded into the deformation model in advance, so when modifications are applied, the system automatically respects the pre-established anatomical rules. This maintains structural consistency without complicating the user operation.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent segments the modification process into independent local deformations that are then integrated globally. Each anatomical structure can be modified independently through simple user interactions, but the segmentation is performed in such a way that the local changes are coordinated through the deformation field to maintain overall anatomical consistency. This achieves both ease of operation and structural stability.

Inventive Principle:

Principle #1Segmentation

3Reliability

If anatomical constraints are enforced during modification, then anatomical integrity is maintained, but the complexity of the modification system increases

Engineering Contradiction:

ImproveAnatomical integrity preservationVSAvoidModification system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system introduces a deformation field as an intermediary between user input and the final modification result. The user provides simple modification commands, and the deformation field acts as a mediator that automatically enforces anatomical constraints while generating the final modified structures. This intermediary approach maintains anatomical integrity without requiring the user to directly manage complex constraint systems.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The modification system performs self-service by automatically calculating and applying constraint-based adjustments without requiring additional user input. When a structure is modified, the system autonomously determines the necessary adjustments to other structures based on pre-defined anatomical relationships. This self-service mechanism maintains anatomical integrity while keeping the user interface simple and the system complexity hidden from the user.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS12190522B2Constrained object correction for a segmented image

Publication Date: 2025.01.07 BRAINLAB AG

AI summary

Disclosed is a computer-implemented method of segmenting a medical patient image using an atlas and relating the segmentation result to a model of possible geometric changes to the segmentation result (e.g. for correcting the position of the segmentation of anatomical structures) which consider for example anatomical limitations. The thus-related segmentation result may be used as a basis for changing and/or correcting the position, shape and/or orientation of at least parts of the segmentation result, e.g. by user interaction. The invention also relates to an atlas data set comprising information such as values of the variables of the model of possible geometric changes in relation to the positions of anatomical structures in the atlas.