AI Cardiac Landmark Detection for Standardized 3D Preoperative Planning

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current medical imaging software for pre-procedural planning of structural heart interventions, such as TAVR, LAAO, and TMVR, relies on semi-automated workflows, requiring significant manual effort and lacking standardization, which hinders efficiency and learning curve for operators.

Innovation Solution

An automated anatomical analysis platform utilizing artificial intelligence to identify anatomical landmarks, construct 3D models, and derive measurements from multi-slice computed tomography images, incorporating deep learning modules for segmentation, point, curve, and plane detection to enhance automation and precision.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If semi-automated workflows are used for MSCT analysis, then manual control and flexibility are maintained, but time consumption increases and standardization is reduced

Engineering Contradiction:

Improvemanual controlVSAvoidtime consumption

Core Design Contradiction:

Ease of operationVSLoss of time

Solution Approach 1:

The system performs self-service by automatically executing the complete workflow including image acquisition, preprocessing, landmark detection, measurement derivation, and 3D model generation without requiring manual intervention at each step, thereby eliminating time consumption while maintaining operational effectiveness

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical operations with an automated computational system that uses AI algorithms and processing modules to perform anatomical analysis, substituting human manual control with automated digital processing to reduce time consumption

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If semi-automated workflows are used for MSCT analysis, then operator flexibility is maintained, but standardization decreases

Engineering Contradiction:

Improveoperator flexibilityVSAvoidstandardization

Core Design Contradiction:

Ease of operationVSStability of the object's composition

Solution Approach 1:

The system standardizes operations by changing the workflow from manual parameter adjustment to automated parameter derivation based on fixed AI models and algorithms, ensuring consistent standardization while maintaining operational effectiveness through programmable flexibility

Inventive Principle:

Principle #35Parameter changes

3Loss of time

If automated AI analysis is implemented, then time consumption is reduced and standardization is improved, but system complexity increases

Engineering Contradiction:

Improveanalysis timeVSAvoidsystem complexity

Core Design Contradiction:

Loss of timeVSDevice complexity

Solution Approach 1:

The patent segments the complex automated system into distinct functional modules including image acquisition module, preprocessing module, landmark detection module, measurement derivation module, and 3D model generation module, making the complex system manageable and implementable while maintaining automation benefits

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system achieves multi-functionality by implementing a unified automated platform that performs multiple tasks (image processing, landmark detection, measurement derivation, 3D modeling) through integrated AI algorithms, reducing the need for separate specialized tools and managing complexity through consolidation

Inventive Principle:

Principle #6Universality (Multi-functionality)

4Measurement precision

If automated landmark identification is used, then measurement precision is improved, but reliability of automated detection must be established

Engineering Contradiction:

Improvelandmark detection precisionVSAvoiddetection reliability

Core Design Contradiction:

Measurement precisionVSReliability

Solution Approach 1:

The system incorporates feedback mechanisms where detected landmarks and measurements are validated through cross-checking with 3D models and anatomical references, ensuring both precision and reliability of automated detection by continuously verifying output against expected anatomical characteristics

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS12471997B2Systems and methods for automatically detecting anatomical features for preoperative cardiac implant simulations

Publication Date: 2025.11.18 FEOPS NV

AI summary

Systems and methods for fully automated anatomical analysis of an anatomical structure are provided to facilitate pre-operative planning. The computerized method may include obtaining a plurality of images, e.g., MSCT images, of patient-specific cardiovascular anatomy, and analyzing the MSCT images with a trained artificial intelligence module to identify one or more anatomical landmarks and to construct a virtual three-dimensional model of the anatomical structure. For example, the trained artificial intelligence module may execute segmentation, point detection, curve detection, or plane detection deep learning modules, independently or in combination, to identify the anatomical landmarks. The method further may include deriving anatomical measurements of the one or more identified anatomical landmarks, and displaying the virtual three-dimensional model alongside the anatomical measurements of the one or more identified anatomical landmarks.