EDMAE: An Efficient Decoupled Masked Autoencoder for Standard View Identification in Pediatric Echocardiography

Abstract

This paper introduces the Efficient Decoupled Masked Autoencoder (EDMAE), a novel self-supervised method for recognizing standard views in pediatric echocardiography. EDMAE introduces a new proxy task based on the encoder-decoder structure. The EDMAE encoder is composed of a teacher and a student encoder. The teacher encoder extracts the potential representation of the masked image blocks, while the student encoder extracts the potential representation of the visible image blocks. The loss is calculated between the feature maps output by the two encoders to ensure consistency in the latent representations they extract. EDMAE uses pure convolution operations instead of the ViT structure in the MAE encoder. This improves training efficiency and convergence speed. EDMAE is pre-trained on a large-scale private dataset of pediatric echocardiography using self-supervised learning, and then fine-tuned for standard view recognition. The proposed method achieves high classification accuracy in 27 standard views of pediatric echocardiography. To further verify the effectiveness of the proposed method, the authors perform another downstream task of cardiac ultrasound segmentation on the public dataset CAMUS. The experimental results demonstrate that the proposed method outperforms some popular supervised and recent self-supervised methods, and is more competitive on different downstream tasks.

arXiv comment15 pages, 5 figures, 8 tables, Published in Biomedical Signal Processing and Control

References in corpus (7)

• An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
• TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation
• Improved Baselines with Momentum Contrastive Learning
• BEiT: BERT Pre-Training of Image Transformers
• Deep Learning for Segmentation using an Open Large-Scale Dataset in 2D Echocardiography
• ConvMAE: Masked Convolution Meets Masked Autoencoders
• Global Contrast Masked Autoencoders Are Powerful Pathological Representation Learners

Cited by in corpus (2)

• Reconstruction of Cardiac Cine MRI Using Motion-Guided Deformable Alignment and Multi-Resolution Fusion
• MambaEviScrib: Mamba and Evidence-Guided Consistency Enhance CNN Robustness for Scribble-Based Weakly Supervised Ultrasound Image Segmentation