Impact of preprocessing cardiac magnetic resonance images for enhancing the performance of deep learning to segment myocardium

Deep learning models require large and well-prepared datasets to achieve reliable performance. However, publicly available cardiac magnetic resonance (CMR) datasets often lack the necessary uniformity and quality for direct use in training. This paper proposes a comprehensive image preprocessing methodology aimed at improving the performance of deep learning models, specifically a 2D U-Net, for myocardium segmentation. The proposed preprocessing pipeline focuses on two main objectives: (i) enhancing image quality through contrast and brightness adjustment, gradient equalization, anisotropic diffusion filtering, and CLAHE; and (ii) accurately identifying the region of interest (ROI) containing the myocardium using a Hough Transform–based approach. After ROI detection, images are cropped to reduce dimensionality while preserving relevant anatomical structures. The methodology was evaluated using three public CMR datasets, comparing segmentation performance with and without preprocessing. The U-Net model was trained under consistent conditions, and performance was assessed using DICE and Hausdorff metrics. The preprocessing pipeline produced more uniform, higher-quality images and achieved robust ROI localization, with a 100% success rate across all datasets. Quantitative evaluation showed consistent improvements in segmentation performance, with an average increase of approximately 19% compared to non-preprocessed data. Additionally, reducing image size after ROI extraction significantly decreased training time while maintaining or improving segmentation accuracy. The results demonstrate that effective preprocessing is a critical component in deep learning pipelines for cardiac MRI segmentation. The proposed methodology enhances robustness, improves segmentation accuracy, and reduces computational cost, particularly when dealing with heterogeneous and limited datasets. This approach highlights the importance of integrating preprocessing strategies to optimize deep learning performance in medical image analysis.