From Motion to Meaning: Biomechanics-Informed Neural Network for Explainable Cardiovascular Disease Identification

2025-07-08

AI Summary

Deep learning models for cardiovascular disease diagnosis often lack physiological interpretability, limiting clinical trust and adoption. Method: This paper proposes a biomechanics-driven explainable AI framework that integrates deep learning-based image registration with physics-informed constraints. Specifically, the deformation field is regularized using a Neo-Hookean hyperelastic constitutive model to ensure physiological plausibility, enabling extraction of motion–mechanics features—such as local myocardial strain—from dynamic cardiac imaging. These features are subsequently refined via feature selection and classified using ensemble classifiers (random forest and SVM). Contribution/Results: Evaluated on the ACDC dataset, the method achieves Dice scores of 0.945 (left ventricle), 0.908 (right ventricle), and 0.905 (myocardium) for cardiac structure segmentation; disease classification accuracy reaches 98% on the training set and 100% on the test set. By embedding biomechanical priors into the learning pipeline, the approach significantly enhances model transparency, physiological interpretability, and clinical credibility.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods, algorithms and applications for the development of semantic models, knowledge graphs and other forms of structured data models with machine-interpretable semantics
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Cardiac diseases are among the leading causes of morbidity and mortality worldwide, which requires accurate and timely diagnostic strategies. In this study, we introduce an innovative approach that combines deep learning image registration with physics-informed regularization to predict the biomechanical properties of moving cardiac tissues and extract features for disease classification. We utilize the energy strain formulation of Neo-Hookean material to model cardiac tissue deformations, optimizing the deformation field while ensuring its physical and biomechanical coherence. This explainable approach not only improves image registration accuracy, but also provides insights into the underlying biomechanical processes of the cardiac tissues. Evaluation on the Automated Cardiac Diagnosis Challenge (ACDC) dataset achieved Dice scores of 0.945 for the left ventricular cavity, 0.908 for the right ventricular cavity, and 0.905 for the myocardium. Subsequently, we estimate the local strains within the moving heart and extract a detailed set of features used for cardiovascular disease classification. We evaluated five classification algorithms, Logistic Regression, Multi-Layer Perceptron, Support Vector Classifier, Random Forest, and Nearest Neighbour, and identified the most relevant features using a feature selection algorithm. The best performing classifier obtained a classification accuracy of 98% in the training set and 100% in the test set of the ACDC dataset. By integrating explainable artificial intelligence, this method empowers clinicians with a transparent understanding of the model's predictions based on cardiac mechanics, while also significantly improving the accuracy and reliability of cardiac disease diagnosis, paving the way for more personalized and effective patient care.

Problem

• Develops biomechanics-informed neural network for cardiac disease identification
• Combines deep learning with physics to model cardiac tissue deformations
• Improves accuracy and explainability of cardiovascular disease diagnosis

Innovation

• Deep learning image registration with physics-informed regularization
• Neo-Hookean material models cardiac tissue deformations
• Explainable AI for transparent cardiovascular disease classification