Key result
ShapeNet with an improved active shape model achieves an LV segmentation Dice score of 0.87.
Why the study?
Left ventricle segmentation is crucial for cardiac diagnosis but remains challenging in echocardiography.
Does ShapeNet combined with an improved active shape model improve left ventricle segmentation accuracy in echocardiography images?
Does ShapeNet combined with an improved active shape model improve left ventricle segmentation accuracy in echocardiography images?
ShapeNet provides a robust, fully automated method for left ventricle segmentation in echocardiography that generates anatomically plausible contours.
May facilitate automated LV segmentation in echocardiography research; leaves open clinical validation before workflow integration.
Left ventricle (LV) segmentation is crucial for cardiac diagnosis but remains challenging in echocardiography. We present ShapeNet, a fully automatic method combining a convolutional neural network (CNN) ensemble with an improved active shape model (ASM). ShapeNet predicts optimal pose (rotation, translation, and scale) and shape parameters, which are refined using the improved ASM. The ASM optimizes an objective function constructed from gray-level profiles concatenated into a single contour appearance vector. The model was trained on 4800 augmented CAMUS images and tested on both CAMUS and EchoNet databases. It achieved a Dice coefficient of 0.87 and a Hausdorff Distance (HD) of 4.08 pixels on CAMUS, and a Dice coefficient of 0.81 with an HD of 10.21 pixels on EchoNet, demonstrating robust performance across datasets. These results highlight the improved accuracy in HD compared to previous semantic and shape-based segmentation methods by generating statistically valid LV contours from ultrasound images.
No takes yet. Share an insight, caveat, or question.
Galicia et al. (2025) studied Left ventricle segmentation in echocardiography (n=1,217). ShapeNet combined with improved active shape model (ASM) vs. Previous semantic and shape-based segmentation methods (e.g., U-Net, BEASM) was evaluated on Dice coefficient and Hausdorff Distance (HD) for left ventricle segmentation. ShapeNet combined with an improved active shape model achieved a Dice coefficient of 0.87 and a Hausdorff Distance of 4.08 pixels on the CAMUS dataset for left ventricle segmentation.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: