Extreme Cardiac MRI Analysis under Respiratory Motion: Results of the CMRxMotion Challenge

2025-07-25

AI Summary

Clinical cardiac magnetic resonance (CMR) images are frequently degraded by respiratory motion artifacts, severely compromising the robustness of deep learning models—yet existing studies lack systematic evaluation of this issue. To address this gap, we introduce the first publicly available, expertly annotated CMR dataset featuring 320 cardiac cycles with realistic respiratory artifacts. We systematically quantify, for the first time, the impact of such artifacts on five critical biomarkers: left and right ventricular volumes, ejection fractions, and myocardial mass. We formulate two benchmark tasks: automatic image quality classification and artifact-robust myocardial segmentation. Data were acquired under controlled respiratory protocols, enabling fair algorithm evaluation; 22 methods were submitted, with top-performing approaches significantly outperforming baselines on both tasks. All data, annotations, code, and benchmark results are fully open-sourced, establishing a reproducible foundation for robust CMR analysis.

Technology Category

• Computer Vision: Medical and Biological Imaging
• Machine Learning: Multimodal Learning
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Deep learning models have achieved state-of-the-art performance in automated Cardiac Magnetic Resonance (CMR) analysis. However, the efficacy of these models is highly dependent on the availability of high-quality, artifact-free images. In clinical practice, CMR acquisitions are frequently degraded by respiratory motion, yet the robustness of deep learning models against such artifacts remains an underexplored problem. To promote research in this domain, we organized the MICCAI CMRxMotion challenge. We curated and publicly released a dataset of 320 CMR cine series from 40 healthy volunteers who performed specific breathing protocols to induce a controlled spectrum of motion artifacts. The challenge comprised two tasks: 1) automated image quality assessment to classify images based on motion severity, and 2) robust myocardial segmentation in the presence of motion artifacts. A total of 22 algorithms were submitted and evaluated on the two designated tasks. This paper presents a comprehensive overview of the challenge design and dataset, reports the evaluation results for the top-performing methods, and further investigates the impact of motion artifacts on five clinically relevant biomarkers. All resources and code are publicly available at: https://github.com/CMRxMotion

Problem

• Evaluating deep learning robustness in cardiac MRI with respiratory motion artifacts
• Automated image quality assessment for motion severity classification
• Robust myocardial segmentation despite motion-induced image degradation

Innovation

• Deep learning for motion artifact analysis
• Public dataset with controlled motion artifacts
• Robust myocardial segmentation under motion