Research on intelligent fetal heart monitoring model based on deep active learning_Journal of Biomedical Engineering

Authors：

QUAN Bin ^1,2 , HUANG Yajing ¹ , LI Yanfang ³ , CHEN Qinqun ^1,4 , ZHANG Honglai ^1,4,5 , LI Li ^6,7 , LIU Guiqing ³ ,  WEI Hang ^1,4

1. School of Medical Information Engineering, Guangzhou University of Chinese Medicine, Guangzhou 510006, P. R. China;
2. National Engineering Laboratory of Big Data System Computing Technology, Shenzhen University, Shenzhen, Guangdong 518060, P. R. China;
3. First Affiliated Hospital of Guangzhou University of Chinese Medicine, Guangzhou 510405, P. R. China;
4. Intelligent Chinese Medicine Research Institute, Guangzhou University of Chinese Medicine, Guangzhou 510006, P. R. China;
5. State Key Laboratory of Traditional Chinese Medicine Syndrome, Guangzhou University of Chinese Medicine, Guangzhou 510006, P. R. China;
6. Guangzhou Sunray Medical Apparatus Co. Ltd, Guangzhou 510620, P. R. China;
7. Tianhe District People's Hospital, First Affiliated Hospital of Jinan University, Guangzhou 510630, P. R. China;

Corresponding author：

WEI Hang, Email: crwei@gzucm.edu.cn

Keywords：

Intelligent fetal heart monitoring; Deep active learning; Three-way decision; Multi-objective optimization; Convolution neural network

DOI：

10.7507/1001-5515.202402012

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

Cardiotocography (CTG) is a non-invasive and important tool for diagnosing fetal distress during pregnancy. To meet the needs of intelligent fetal heart monitoring based on deep learning, this paper proposes a TWD-MOAL deep active learning algorithm based on the three-way decision (TWD) theory and multi-objective optimization Active Learning (MOAL). During the training process of a convolutional neural network (CNN) classification model, the algorithm incorporates the TWD theory to select high-confidence samples as pseudo-labeled samples in a fine-grained batch processing mode, meanwhile low-confidence samples annotated by obstetrics experts were also considered. The TWD-MOAL algorithm proposed in this paper was validated on a dataset of 16 355 prenatal CTG records collected by our group. Experimental results showed that the algorithm proposed in this paper achieved an accuracy of 80.63% using only 40% of the labeled samples, and in terms of various indicators, it performed better than the existing active learning algorithms under other frameworks. The study has shown that the intelligent fetal heart monitoring model based on TWD-MOAL proposed in this paper is reasonable and feasible. The algorithm significantly reduces the time and cost of labeling by obstetric experts and effectively solves the problem of data imbalance in CTG signal data in clinic, which is of great significance for assisting obstetrician in interpretations CTG signals and realizing intelligence fetal monitoring.

Citation： QUAN Bin, HUANG Yajing, LI Yanfang, CHEN Qinqun, ZHANG Honglai, LI Li, LIU Guiqing, WEI Hang. Research on intelligent fetal heart monitoring model based on deep active learning. Journal of Biomedical Engineering, 2025, 42(1): 57-64. doi: 10.7507/1001-5515.202402012 Copy

1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11.	Munjal P, Hayat N, Hayat M, et al. Towards robust and reproducible active learning using neural networks//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans: IEEE, 2022: 223-232.
12.
13.
14.	Xie B, Yuan L, Li S, et al. Active learning for domain adaptation: an energy-based approach//Proceedings of the AAAI Conference on Artificial Intelligence. 2022, 36(8): 8708-8716.
15.
16.	Moses S N, Priyadarsine S, Llitha Ambigai V D, et al. Automated classification of CTG signals using deep learning based scalogram analysis//2022 IEEE Global Conference on Computing, Power and Communication Technologies (GlobConPT). New Delhi: IEEE, 2022: 1-6.
17.	Hemmer P, Kühl N, Schöffer J. Deal: deep evidential active learning for image classification// 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA), Miami: IEEE, 2020: 865-870.
18.
19.	谢幸, 苟文丽. 妇产科学. 第8版. 北京: 人民卫生出版社, 2013: 1-488.
20.
21.
22.
23.	Rizve M N, Duarte K, Rawat Y S, et al. In defense of pseudo-labeling: an uncertainty-aware pseudo-label selection framework for semi-supervised learning. arXiv preprint, 2021, arXiv: 2101.06329.
24.	Kingma D P, Ba J. Adam: a method for stochastic optimization. arXiv preprint, 2014, arXiv: 1412.6980.
25.
26.

1.
2.
3.
4.
5.
6.
7.
8.
9.
10.
11. Munjal P, Hayat N, Hayat M, et al. Towards robust and reproducible active learning using neural networks//2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans: IEEE, 2022: 223-232.
12.
13.
14. Xie B, Yuan L, Li S, et al. Active learning for domain adaptation: an energy-based approach//Proceedings of the AAAI Conference on Artificial Intelligence. 2022, 36(8): 8708-8716.
15.
16. Moses S N, Priyadarsine S, Llitha Ambigai V D, et al. Automated classification of CTG signals using deep learning based scalogram analysis//2022 IEEE Global Conference on Computing, Power and Communication Technologies (GlobConPT). New Delhi: IEEE, 2022: 1-6.
17. Hemmer P, Kühl N, Schöffer J. Deal: deep evidential active learning for image classification// 2020 19th IEEE International Conference on Machine Learning and Applications (ICMLA), Miami: IEEE, 2020: 865-870.
18.
19. 谢幸, 苟文丽. 妇产科学. 第8版. 北京: 人民卫生出版社, 2013: 1-488.
20.
21.
22.
23. Rizve M N, Duarte K, Rawat Y S, et al. In defense of pseudo-labeling: an uncertainty-aware pseudo-label selection framework for semi-supervised learning. arXiv preprint, 2021, arXiv: 2101.06329.
24. Kingma D P, Ba J. Adam: a method for stochastic optimization. arXiv preprint, 2014, arXiv: 1412.6980.
25.
26.

Journal of Biomedical Engineering

Research on intelligent fetal heart monitoring model based on deep active learning

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content