Investigating methods to enhance interpretability and performance in cardiac MRI for myocardial scarring diagnosis using convolutional neural network classification and One Match

TL;DR

This paper introduces One Match, an interpretable algorithm for classifying myocardial scarring in cardiac MRI that improves diagnostic accuracy and trust in AI models.

Contribution

One Match combines template matching with enhancements like autodidactic enhancement and patient-level classifications to boost interpretability and performance in cardiac MRI diagnosis.

Findings

One Match achieved 95.3% accuracy in classifying myocardial scarring when enhanced with autodidactic enhancement and patient-level classifications.

One Match outperformed traditional CNNs in specificity and F1-score when using both enhancements.

Autodidactic enhancement improved One Match accuracy by 4.1% but decreased CNN accuracy.

Abstract

Machine learning (ML) classification of myocardial scarring in cardiac MRI is often hindered by limited explainability, particularly with convolutional neural networks (CNNs). To address this, we developed One Match (OM), an algorithm that builds on template matching to improve on both the explainability and performance of ML myocardial scaring classification. By incorporating OM, we aim to foster trust in AI models for medical diagnostics and demonstrate that improved interpretability does not have to compromise classification accuracy. Using a cardiac MRI dataset from 279 patients, this study evaluates One Match, which classifies myocardial scarring in images by matching each image to a set of labeled template images. It uses the highest correlation score from these matches for classification and is compared to a traditional sequential CNN. Enhancements such as autodidactic enhancement (AE) and patient-level classifications (PLCs) were applied to improve the predictive accuracy of both methods. Results are reported as follows: accuracy, sensitivity, specificity, precision, and F1-score. The highest classification performance was observed with the OM algorithm when enhanced by both AE and PLCs, 95.3% accuracy, 92.3% sensitivity, 96.7% specificity, 92.3% precision, and 92.3% F1-score, marking a significant improvement over the base configurations. AE alone had a positive impact on OM increasing accuracy from 89.0% to 93.2%, but decreased the accuracy of the CNN from 85.3% to 82.9%. In contrast, PLCs improved accuracy for both the CNN and OM, raising the CNN’s accuracy by 4.2% and OM’s by 7.4%. This study demonstrates the effectiveness of OM in classifying myocardial scars, particularly when enhanced with AE and PLCs. The interpretability of OM also enabled the examination of misclassifications, providing insights that could accelerate development and foster greater trust among clinical stakeholders.

Figures