MECardNet: A novel multi-scale convolutional ensemble model with adaptive deep supervision for precise cardiac MRI segmentation

•A novel model, MECardNet, is introduced for precise and automatic segmentation of CMRI data, which leverages a multi-scale and adaptive mixture ensemble of convolutional encoder-decoder components for better multi-range dependency modeling.•MECardNet’s design, including an EfficientNetV2L backbone, a mixture ensemble with cross-additive attention mechanisms, an integration of mixture-based Adaptive Deep Supervision (ADS), and a specialized loss function, results in promising CMRI segmentation performance and robustness.•MECardNet exhibits robustness across diverse datasets, affirming its independence from vendor biases and imaging protocols. Moreover, its performance surpasses both baseline models and state-of-the-art methods in cardiac MRI image segmentation. showcasing remarkable results and establishing itself as a benchmark for future research in cardiac MRI analysis. Accurate segmentation of the left ventricle, right ventricle, and myocardium is essential for estimating key cardiac parameters in diagnostic procedures. However, automating Cardiovascular Magnetic Resonance Imaging (CMRI) segmentation faces challenges from diverse imaging vendors and protocols. This study introduces MECardNet framework as an innovative multiclass CMRI segmentation model, representing a prominent advancement in the field. MECardNet leverages a Multiscale Convolutional Mixture of Experts (MCME) ensemble technique with Adaptive Deep Supervision, seamlessly integrated into the U-Net architecture. The MCME framework improves representation learning in the U-Net workflow. It does this by adaptively adjusting the contribution of U-Net layers in the ensemble for better data modeling. Additionally, MECardNet incorporates a cross-additive attention mechanism, an EfficientNetV2L backbone, and a specialized compound loss function, leading to enhanced model performance. Through 10-fold Cross-Validation (CV) analysis on the ACDC dataset, MECardNet surpasses baseline models and state-of-the-art methods, showcasing promising performance levels with evaluation metrics such as Dice Similarity Coefficient (DSC) of 96.1 ± 0.4 %, Jaccard coefficient of 92.2 ± 0.4 %, Hausdorff distance of 1.7 ± 0.1 and mean absolute distance of 1.6 ± 0.1. Further validation on the M&Ms-2 dataset and a local dataset confirms promising performance of MECardNet, with DSC of 94.3 ± 0.7 % and 94.5 ± 0.6 %, respectively. The proposed MECardNet framework establishes a new benchmark in CMRI segmentation by outperfor