Key result
Green Learning framework outperforms 3D deep learning, achieving ~94% accuracy for LVEF classification.
Why the study?
Conventional deep learning models for automated echocardiographic LV segmentation and LVEF classification carry a high parameter burden, energy demand, and opacity. Whether a unified feed-forward Green Learning framework can deliver clinically relevant accuracy, computational efficiency, and interpretable feature representations was uncertain.
Does a backpropagation-free multi-task Green Learning (MTGL) framework improve LV segmentation and three-class LVEF classification accuracy and computational efficiency compared to conventional 3D deep learning baselines in the EchoNet-Dynamic dataset?
Does a backpropagation-free multi-task Green Learning (MTGL) framework improve LV segmentation and three-class LVEF classification accuracy and computational efficiency compared to conventional 3D deep learning baselines in the EchoNet-Dynamic dataset?
A compact, interpretable, backpropagation-free Green Learning framework can jointly perform echocardiographic LV segmentation and LVEF classification with higher accuracy and lower parameter count and environmental training cost than conventional 3D deep learning models.
May support efficient LV analysis; leaves open prospective validation before clinical use.
Purpose This study develops an interpretable, backpropagation-free multi-task Green Learning (MTGL) framework for automated echocardiographic analysis. It addresses the need for reliable left ventricular (LV) segmentation and left ventricular ejection fraction (LVEF) classification while reducing the parameter burden, energy demand and opacity associated with conventional deep learning (DL) models. The objective is to determine whether a unified feed-forward framework can deliver clinically relevant accuracy, computational efficiency and interpretable feature representations. Design/methodology/approach The framework uses a four-hop, PCA/Saab-based unsupervised VoxelHop encoder followed by a coarse-to-fine XGBoost residual-regression decoder for LV segmentation and a pooled multi-scale XGBoost classifier for three-class LVEF classification. Experiments used the predefined EchoNet-Dynamic training, validation and test partitions. MTGL was evaluated against matched 3D V-Net, 3D U-Net, 3D UNETR and 3D nnU-Net baselines using classification accuracy and balanced accuracy, and Dice similarity coefficient (DSC) and intersection over union (IoU). Findings On the EchoNet-Dynamic test set, MTGL achieved 94.3% accuracy for three-class LVEF classification, and 0.912 DSC for LV segmentation, outperforming all compared baselines. It used 1.13 million parameters, versus 10.47–49.08 million for the DL comparators, and showed the lowest measured training energy use and carbon emissions. Hop ablation further showed complementary multi-scale information, with the full feature set yielding the highest classification accuracy. Originality/value Unlike end-to-end backpropagation-based DL methods, MTGL combines an unsupervised linear VoxelHop representation with task-specific XGBoost decoders in a single multi-task echocardiographic pipeline. The PCA/Saab direct current and alternating current feature decomposition enables direct inspection of learned spatial and spatiotemporal signals, linking shallow features to anatomical boundaries and deeper features to global contractile dynamics. The study therefore demonstrates that a compact, interpretable Green Learning system can jointly support LV segmentation and LVEF grouping with strong in-domain performance and lower measured training environmental cost.
No takes yet. Share an insight, caveat, or question.
Kao et al. (2026) studied Echocardiographic left ventricular segmentation and left ventricular ejection fraction classification. Multi-task Green Learning (MTGL) framework vs. 3D V-Net, 3D U-Net, 3D UNETR, and 3D nnU-Net baselines was evaluated on Three-class LVEF classification accuracy and LV segmentation Dice similarity coefficient (DSC). The multi-task Green Learning framework achieved 94.3% accuracy for LVEF classification and 0.912 DSC for LV segmentation using 1.13M parameters, outperforming 3D deep learning baselines.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: