Motion-related Artefact Classification Using Patch-based Ensemble and Transfer Learning in Cardiac MRI

TL;DR

This paper presents an automated method for classifying motion artefacts in cardiac MRI using ensemble and transfer learning, achieving top performance on a challenging dataset to facilitate quality assessment.

Contribution

It introduces a novel ensemble transfer learning framework for cardiac MRI quality classification, improving accuracy on imbalanced, multi-class datasets.

Findings

Achieved 78.8% accuracy on training data

Secured 72.5% accuracy on independent test set

Ranked top 1 in the CMRxMotion grand challenge

Abstract

Cardiac Magnetic Resonance Imaging (MRI) plays an important role in the analysis of cardiac function. However, the acquisition is often accompanied by motion artefacts because of the difficulty of breath-hold, especially for acute symptoms patients. Therefore, it is essential to assess the quality of cardiac MRI for further analysis. Time-consuming manual-based classification is not conducive to the construction of an end-to-end computer aided diagnostic system. To overcome this problem, an automatic cardiac MRI quality estimation framework using ensemble and transfer learning is proposed in this work. Multiple pre-trained models were initialised and fine-tuned on 2-dimensional image patches sampled from the training data. In the model inference process, decisions from these models are aggregated to make a final prediction. The framework has been evaluated on CMRxMotion grand challenge (MICCAI 2022) dataset which is small, multi-class, and imbalanced. It achieved a classification accuracy of 78.8% and 70.0% on the training set (5-fold cross-validation) and a validation set, respectively. The final trained model was also evaluated on an independent test set by the CMRxMotion organisers, which achieved the classification accuracy of 72.5% and Cohen's Kappa of 0.6309 (ranked top 1 in this grand challenge). Our code is available on Github: https://github.com/ruizhe-l/CMRxMotion.