A Shape-Consistent Deep-Learning Segmentation Architecture for Low-Quality and High-Interference Myocardial Contrast Echocardiography

Abstract

Objective: Myocardial contrast echocardiography (MCE) plays a crucial role in diagnosing ischemia, infarction, masses, and other cardiac conditions. In the realm of MCE image analysis, accurate and consistent myocardial segmentation results are essential for enabling automated analysis of various heart diseases. However, current manual diagnostic methods in MCE suffer from poor repeatability and limited clinical applicability. MCE images often exhibit low quality and high noise due to the instability of ultrasound signals, while interference structures can further disrupt segmentation consistency. Methods: To overcome the challenges, we proposed a deep learning network for the segmentation of MCE. This architecture leverages dilated convolutions to capture high-scale information without sacrificing positional accuracy, and modifies Multi-head Self-attention (MHSA) to enhance global context and ensure consistency, effectively overcoming issues related to low image quality and interference. Furthermore, we adapted the cascade application of Transformers with convolutional neural network (CNN) for improved segmentation in MCE. Results:In our experiments, compared to several state-of-the-art segmentation models, our architecture achieved the best Dice score of 84.35% for standard MCE views. For nonstandard views and frames with interfering structures (mass), our models also attained the best Dice scores of 83.33% and 83.97%, respectively. Conclusion:The experiments proved that our architecture was of great shape consistency and robustness to deal with segmentation of various types of MCE. Significance:The relatively precise and consistent myocardial segmentation results provide the fundamental conditions for the automated analysis of various heart diseases, helping to discover the underlying pathological features and reduce healthcare costs.