The semi-supervised Student model achieved accurate frame-by-frame mitral valve segmentation with a Dice score of 0.82, an average surface distance of 0.37 mm, and a 95% Hausdorff distance of 1.72 mm.
Does a semi-supervised Teacher-Student framework improve automatic 4D mitral valve segmentation accuracy and temporal consistency in TEE images of patients undergoing MV repair?
A semi-supervised deep learning approach using a Teacher-Student framework enables accurate and temporally consistent frame-by-frame 4D mitral valve segmentation from TEE, significantly reducing manual annotation workload.
Performing automatic and standardized 4D TEE segmentation and mitral valve analysis is challenging due to the limitations of echocardiography and the scarcity of manually annotated 4D images. This work proposes a semi-supervised training strategy using pseudo labelling for MV segmentation in 4D TEE; it employs a Teacher-Student framework to ensure reliable pseudo-label generation. 120 4D TEE recordings from 60 candidates for MV repair are used. The Teacher model, an ensemble of three convolutional neural networks, is trained on end-systole and end-diastole frames and is used to generate MV pseudo-segmentations on intermediate frames of the cardiac cycle. The pseudo-annotated frames augment the Student model's training set, improving segmentation accuracy and temporal consistency. The Student outperforms individual Teachers, achieving a Dice score of 0.82, an average surface distance of 0.37 mm, and a 95% Hausdorff distance of 1.72 mm for MV leaflets. The Student model demonstrates reliable frame-by-frame MV segmentation, accurately capturing leaflet morphology and dynamics throughout the cardiac cycle, with a significant reduction in inference time compared to the ensemble. This approach greatly reduces manual annotation workload and ensures reliable, repeatable, and time-efficient MV analysis. Our method holds strong potential to enhance the precision and efficiency of MV diagnostics and treatment planning in clinical settings.
Munafò et al. (Sat,) conducted a other in Mitral regurgitation (n=60). Semi-supervised learning approach (Teacher-Student framework) vs. Individual Teacher models and manual annotations was evaluated on Mitral valve leaflets segmentation accuracy (Dice score). The semi-supervised Student model achieved accurate frame-by-frame mitral valve segmentation with a Dice score of 0.82, an average surface distance of 0.37 mm, and a 95% Hausdorff distance of 1.72 mm.