Wang Yali, Shi Haochun, Qiao Xingye, Cong Fengyu, Zhao Yanbin, Xu Hongming
School of Biomedical Engineering, Faculty of Medicine, Dalian University of Technology, No. 2 Linggong Road, Dalian, 116024, Liaoning Province, China.
State Environmental Protection Key Laboratory of Environmental Health Impact Assessment of Emerging Contaminants, School of Environmental Science and Engineering, Shanghai Jiao Tong University, No. 800 Dongchuan Road, Shanghai, 200240, Shanghai, China.
Med Biol Eng Comput. 2025 Sep 16. doi: 10.1007/s11517-025-03444-5.
Quantifying cardiac functional parameters is crucial for assessing the toxicity of environmental chemicals on the cardiovascular system. Current methodologies for evaluating zebrafish cardiac function largely rely on tedious manual annotations and inaccurate semi-automatic or automatic measurements, hindering accurate and comprehensive functional evaluation. In this paper, we propose a framework for automatically quantifying cardiac functional parameters from zebrafish heartbeat videos by exploring universal segmentation models. We benchmarked 20 state-of-the-art deep segmentation models for automated segmentation of zebrafish ventricles and pericardia. The best-performing model, Mask2Former, was selected to segment ventricles and pericardia from the heartbeat videos. Seven cardiac functional parameters for zebrafish embryos, including heart rate, stroke volume, cardiac output, maximum ventricular area, ejection fraction, diastole to systole ratio, and pericardial arc length, were then computed based on the quantification of ventricular changes and pericardial morphologies. Experiments on 178 zebrafish heartbeat videos reveal that the trained Mask2Former exhibited remarkably superior performance, attaining an IoU of 93.46 and Dice of 96.58 for ventricular segmentation, and an IoU of 83.31 and Dice of 90.89 for pericardial segmentation. Compared to manual measurements, the automatically quantified cardiac functional parameters consistently show high accuracy, with relative errors below 10.0 . Our framework presents a novel, rapid, and reliable tool for evaluating the toxicity of environmental chemicals on the cardiovascular system.
量化心脏功能参数对于评估环境化学物质对心血管系统的毒性至关重要。目前评估斑马鱼心脏功能的方法很大程度上依赖于繁琐的手动注释以及不准确的半自动或自动测量，这阻碍了准确和全面的功能评估。在本文中，我们提出了一个框架，通过探索通用分割模型从斑马鱼心跳视频中自动量化心脏功能参数。我们对20种用于斑马鱼心室和心包自动分割的先进深度分割模型进行了基准测试。选择性能最佳的模型Mask2Former从心跳视频中分割心室和心包。然后根据心室变化和心包形态的量化计算斑马鱼胚胎的七个心脏功能参数，包括心率、每搏输出量、心输出量、最大心室面积、射血分数、舒张期与收缩期比率以及心包弧长。对178个斑马鱼心跳视频的实验表明，训练后的Mask2Former表现出显著优越的性能，心室分割的交并比（IoU）为93.46，骰子系数（Dice）为96.58，心包分割的IoU为83.31，Dice为90.89。与手动测量相比，自动量化的心脏功能参数始终显示出高精度，相对误差低于10.0 。我们的框架为评估环境化学物质对心血管系统的毒性提供了一种新颖、快速且可靠的工具。
