EUVIMEDDescubrir EUVIMED
Crossref

Deep‐learning based multibeat echocardiographic cardiac phase detection

Hanlin Cheng, Zhongqing Shi, Zhanru Qi, Xiaoxian Wang, Guanjun Guo, Aijuan Fang, Zhibin Jin, Chunjie Shan, Yue Du, Ruiyang Chen, Sunnan Qian, Shouhua Luo and 1 more

Medical Physics · 2025-06 · 52 (6) · 4278-4298

DOI: 10.1002/mp.17733 ↗

At a glance

Journal article in Medical Physics, published online on 2025-03-19. Written by Hanlin Cheng and 12 co-authors. Institution: School of Biological Sciences and Medical Engineering, Southeast University, Nanjing, China. Major MEDLINE topics: Deep Learning, Echocardiography, Heart, Image Processing, Computer-Assisted. Cited 4 times so far (Crossref); 46 references. Funded by: National Natural Science Foundation of China, Jiangsu Provincial Key Research and Development Program, Special Project of Basic Research on Frontier Leading Technolopy of Jiangsu Province.

ResumenSubjectsDatos bibliográficosCiteRelated studies

Abstract (original language)

Background

End‐to‐end automatic detection of cardiac phase in multibeat echocardiograms is crucial for measuring cardiac parameters in clinical scenarios. However, existing studies face limitations due to the high cost of data annotation and collection, and time‐consuming detection processes.

Purpose

This study introduces a novel multibeat echocardiographic cardiac phase detection network, EchoPhaseNet, to perform fast and accurate cardiac phase detection of variable‐length multibeat echocardiographic sequences, with low annotation costs and limited data. Materials and methods Five echocardiographic datasets were used in this study, including a small‐scale private dataset, Echo‐DT (DrumTower), a medium‐scale publicly available dataset, PhaseDetection, and three additional publicly available datasets: EchoNet‐Dynamic, CAMUS, and EchoNet‐Dynamic‐MultiBeat. EchoPhaseNet and four other deep learning‐based cardiac phase detection methods were trained and internally validated on the Echo‐DT and PhaseDetection datasets (with sample ratios for training, validation, and testing set at 60%:20%:20% and 80%:0%:20%, respectively), and then externally validated on the other three datasets. Model performance was evaluated using GradCAM for qualitative visualization and absolute frame difference (aFD) for quantitative accuracy, with statistical significance assessed using Tukey's test and Benjamini–Hochberg correction, considering corrected p ‐values 0.05 as significant.

Results

The annotation costs and accuracy of end‐diastolic (ED) and end‐systolic (ES) detection using EchoPhaseNet were compared with those of four other comparison methods. EchoPhaseNet achieves effective specific phase detections using only ED/ES labels, reducing annotation costs and making it applicable to a wider range of detection scenarios compared to all the comparison methods. On the Echo‐DT dataset, EchoPhaseNet's mean aFD values for ED and ES detection in the A4C view samples were 1.08 and 1.04, respectively, significantly outperforming three comparison methods in ED detection accuracy ( p ‐values 0.01) and comparable to the remaining one ( p ‐values 0.05). On the PhaseDetection dataset, EchoPhaseNet's mean aFD values for ED and ES detection were 1.67 and 2.19, respectively, comparable to the detection accuracies of all four comparison methods ( p ‐values 0.05). In addition, EchoPhaseNet showed strong generalization ability on multiple external validation datasets. After training on the small‐scale Echo‐DT dataset, EchoPhaseNet significantly outperformed the four comparison methods ( p ‐values 0.01) in ED detection, achieving mean aFD values of 1.67 and 1.11 on the EchoNet‐Dynamic and EchoNet‐Dynamic‐MultiBeat datasets, respectively. After training on the PhaseDetection dataset, EchoPhaseNet significantly outperformed the four compared methods ( p ‐values 0.01) in ES detection on the EchoNet‐Dynamic dataset, achieving mean aFD value of 2.58. EchoPhaseNet's inference time for a single 32‐frame sequence segment is substantially lower than that of the four compared methods, not exceeding 8 ms on an RTX 4080 GPU using the PyTorch deep learning framework.

Conclusions

EchoPhaseNet exhibits clear advantages over existing studies in data annotation and collection costs, as well as detection speed, and is applicable to a wider range of detection scenarios. It demonstrates good practicality and promising prospects for clinical multibeat echocardiographic cardiac phase detection.

Subjects

MeSH terms (MEDLINE)

Deep LearningEchocardiographyHeartImage Processing, Computer-AssistedHumans

Author keywords

deep learningechocardiographyphase detection

Authors and institutions

  • School of Biological Sciences and Medical Engineering, Southeast University, Nanjing, China.
  • Department of Ultrasound Medicine, The Affiliated Hospital of Nanjing University Medical School, Nanjing Drum Tower Hospital, Nanjing, China.
  • Medical Imaging Centre, The Affiliated Hospital of Nanjing University Medical School, Nanjing Drum Tower Hospital, Nanjing, China.
  • Yizheng Hospital of Nanjing Drum Tower Hospital Group, Yangzhou, China.
  • School of Biomedical Engineering and Informatics, Nanjing Medical University, Nanjing, China.
  • Department of Information Office, Jiangsu Province Official Hospital, Nanjing, China.

Funding

  • National Natural Science Foundation of China
  • Jiangsu Provincial Key Research and Development Program
  • Special Project of Basic Research on Frontier Leading Technolopy of Jiangsu Province
  • Medical Research of Jiangsu Provincial Health Comminson in 2022

Cite

APA

Cheng, H., Shi, Z., Qi, Z., Wang, X., Guo, G., Fang, A., Jin, Z., Shan, C., Du, Y., Chen, R., Qian, S., Luo, S., & Yao, J. (2025). Deep‐learning based multibeat echocardiographic cardiac phase detection. Medical Physics, 52(6), 4278-4298. https://doi.org/10.1002/mp.17733

Vancouver

Cheng H, Shi Z, Qi Z, Wang X, Guo G, Fang A, et al. Deep‐learning based multibeat echocardiographic cardiac phase detection. Medical Physics. 2025;52(6):4278-4298. doi:10.1002/mp.17733

BibTeX
@article{Cheng2025,
  author = {Cheng, Hanlin and Shi, Zhongqing and Qi, Zhanru and Wang, Xiaoxian and Guo, Guanjun and Fang, Aijuan and Jin, Zhibin and Shan, Chunjie and Du, Yue and Chen, Ruiyang and Qian, Sunnan and Luo, Shouhua and Yao, Jing},
  title = {Deep‐learning based multibeat echocardiographic cardiac phase detection},
  journal = {Medical Physics},
  year = {2025},
  volume = {52},
  number = {6},
  pages = {4278--4298},
  doi = {10.1002/mp.17733}
}
Start for free →