Unified Review and Benchmark of Deep Segmentation Architectures for Cardiac Ultrasound on CAMUS

TL;DR

This paper provides a comprehensive benchmark of deep learning architectures for cardiac ultrasound segmentation, comparing U-Net variants on the CAMUS dataset with various preprocessing and training strategies, highlighting their strengths and limitations.

Contribution

It introduces a standardized, reproducible benchmark for U-Net, Attention U-Net, and TransUNet on CAMUS, along with practical guidance and future outlooks on self-supervision and multimodal annotation pipelines.

Findings

U-Net achieved 94% Dice on native NIfTI data.

Attention U-Net improved boundary accuracy in low-contrast regions.

TransUNet showed superior generalization with SSL initialization.

Abstract

Several review papers summarize cardiac imaging and DL advances, few works connect this overview to a unified and reproducible experimental benchmark. In this study, we combine a focused review of cardiac ultrasound segmentation literature with a controlled comparison of three influential architectures, U-Net, Attention U-Net, and TransUNet, on the Cardiac Acquisitions for Multi-Structure Ultrasound Segmentation (CAMUS) echocardiography dataset. Our benchmark spans multiple preprocessing routes, including native NIfTI volumes, 16-bit PNG exports, GPT-assisted polygon-based pseudo-labels, and self-supervised pretraining (SSL) on thousands of unlabeled cine frames. Using identical training splits, losses, and evaluation criteria, a plain U-Net achieved a 94% mean Dice when trained directly on NIfTI data (preserving native dynamic range), while the PNG-16-bit workflow reached 91% under similar conditions. Attention U-Net provided modest improvements on small or low-contrast regions, reducing boundary leakage, whereas TransUNet demonstrated the strongest generalization on challenging frames due to its ability to model global spatial context, particularly when initialized with SSL. Pseudo-labeling expanded the training set and improved robustness after confidence filtering. Overall, our contributions are threefold: a harmonized, apples-to-apples benchmark of U-Net, Attention U-Net, and TransUNet under standardized CAMUS preprocessing and evaluation; practical guidance on maintaining intensity fidelity, resolution consistency, and alignment when preparing ultrasound data; and an outlook on scalable self-supervision and emerging multimodal GPT-based annotation pipelines for rapid labeling, quality assurance, and targeted dataset curation.