Scalogram-Based Multiclass Fetal State Classification Using Expert-Annotated CTG and SE-ResNet-50
Abstract
Accurate classification of cardiotocographic (CTG) signals plays a critical role in the early detection of fetal health conditions, enabling timely and appropriate medical interventions. A more precise understanding of cardiotocography patterns, particularly in suspicious cases, can help minimize unnecessary interventions and reduce healthcare costs. This study proposes a multiclass classification framework using 552 expert-annotated CTG records containing fetal heart rate (FHR) and uterine contraction (UC) signals. Time-domain augmentation, including cyclic temporal shifting, Gaussian noise, and segmented Gaussian noise, was applied to address class imbalance. The augmented FHR and UC signals were then transformed into scalograms using Continuous Wavelet Transform (CWT), producing dual-channel RGBencoded images. Data were split into 90% for stratified five-fold cross-validation and 10% for independent testing. The proposed ResNet50, enhanced with SE-based channel attention and dropout layers, was compared against several baselines, including CNN, MobileNet, EfficientNet-B0, ResNet18, and ResNet50. It achieved the best performance with an F1-score of 0.7267 and AUC of 0.7489 on the test set, outperforming all baselines. These results highlight its potential for integration into intelligent clinical decision support systems in prenatal care.
Full Text:
PDFReferences
B. Amin, M. Gamal, A. A., I. M. El-Henawy, and K. Mahfouz, “Classifying Cardiotocography Data based on Rough Neural Network,” International Journal of Advanced Computer Science and Applications, vol. 10, no. 8, 2019. https://doi.org/10.14569/ijacsa.2019.0100846
M. T. Alam et al., “Comparative Analysis of Different Efficient Machine Learning Methods for Fetal Health Classification,” Applied Bionics and Biomechanics, vol. 2022, p. 6321884, 2022. https://doi.org/10.1155/2022/6321884
Z. Alfirevic, G. M. Gyte, A. Cuthbert, and D. Devane, “Continuous cardiotocography (CTG) as a form of electronic fetal monitoring (EFM) for fetal assessment during labour,” Cochrane Database of Systematic Reviews, no. 2, 2017. https://doi.org/10.1002/14651858.CD006066.pub3
N. Al Bassam, V. Ramachandran, and S. E. Parameswaran, “Wavelet Theory and Application in Communication and Signal Processing,” in Wavelet Theory, M. Somayeh, Ed. Rijeka: IntechOpen, 2021, ch. 3. https://doi.org/10.5772/intechopen.95047
S. T. Nabipour Hosseini, F. Abbasalizadeh, S. Abbasalizadeh, S. Mousavi, and P. Amiri, “A comparative study of CTG monitoring one hour before labor in infants born with and without asphyxia,” BMC Pregnancy and Childbirth, vol. 23, no. 1, p. 758, 2023. https://doi.org/10.1186/s12884-023-06040-3
H. Allahem and S. Sampalli, “Automated labour detection framework to monitor pregnant women with a high risk of premature labour using machine learning and deep learning,” Informatics in Medicine Unlocked, vol. 28, p. 100771, 2022. https://doi.org/10.1016/j.imu.2021.100771
Z. Anwar et al., “Association of Intrapartum CTG with Fetomaternal Outcome,” Pakistan Journal of Medical & Health Sciences, vol. 16, no. 03, pp. 1045–1045, 2022. https://doi.org/10.53350/pjmhs22164666
D. Campos and J. Bernardes, “Cardiotocography,” UCI Machine Learning Repository, 2010. https://doi.org/10.24432/C51S4N
E. Chandraharan, “Updated NICE Cardiotocograph (CTG) guideline: Is it suspicious or pathological,” Journal of Clinical Medicine and Surgery, vol. 3, no. 2, p. 1129, 2023.
O. Nzelu, E. Chandraharan, and S. Pereira, “Human factors: the dirty dozen in CTG misinterpretation,” Global Journal of Reproductive Medicine, vol. 6, no. 2, p. 555683, 2018. https://doi.org/10.19080/GJORM.2018.06.555683
D. Chinnaiyan and D. S. Alex, “Early Analysis and Prediction of Fetal Abnormalities Using Machine Learning Classifiers,” in 2021 2nd International Conference on Smart Electronics and Communication (ICOSEC), 2021. https://doi.org/10.1109/ICOSEC51865.2021.9591828
V. Chudacek et al., “Open access intrapartum CTG database,” BMC Pregnancy and Childbirth, vol. 14, p. 16, 2014. https://doi.org/10.1186/1471-2393-14-16
S. Das, S. M. Obaidullah, K. C. Santosh, K. Roy, and C. K. Saha, “Cardiotocograph-based labor stage classification from uterine contraction pressure during ante-partum and intra-partum period: a fuzzy theoretic approach,” Health Information Science and Systems, vol. 8, no. 1, p. 16, 2020. https://doi.org/10.1007/s13755-020-00107-7
Y. D. Daydulo, B. L. Thamineni, H. K. Dasari, and G. T. Aboye, “Deep learning based fetal distress detection from time frequency representation of cardiotocogram signal using Morse wavelet: research study,” BMC Medical Informatics and Decision Making, vol. 22, no. 1, p. 329, 2022. https://doi.org/10.1186/s12911-022-02068-1
P. R. D. Intan, M. A. A. Ma’sum, N. Alfiany, W. Jatmiko, A. Kekalih, and A. Bustamam, “Ensemble learning versus deep learning for Hypoxia detection in CTG signal,” in 2019 International Workshop on Big Data and Information Security (IWBIS), 2019. https://doi.org/10.1109/IWBIS.2019.8935796
F. Francis, S. Luz, H. Wu, S. J. Stock, and R. Townsend, “Machine learning on cardiotocography data to classify fetal outcomes: A scoping review,” Computers in Biology and Medicine, vol. 172, p. 108220, Apr. 2024. https://doi.org/10.1016/j.compbiomed.2024.108220
P. Fergus, C. Chalmers, C. C. Montanez, D. Reilly, P. Lisboa, and B. Pineles, “Modelling Segmented Cardiotocography Time-Series Signals Using One-Dimensional Convolutional Neural Networks for the Early Detection of Abnormal Birth Outcomes,” IEEE Transactions on Emerging Topics in Computational Intelligence, 2021. https://doi.org/10.1109/TETCI.2020.3020061
T. E. Geltore and D. L. Anore, “The Impact of Antenatal Care in Maternal and Perinatal Health,” in Empowering Midwives and Obstetric Nurses, IntechOpen, 2021, ch. 8. https://doi.org/10.5772/intechopen.98668
J. Hu, L. Shen, S. Albanie, G. Sun, and E. Wu, “Squeeze-and-Excitation Networks,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 8, pp. 2011–2023, Aug. 2020. https://doi.org/10.1109/TPAMI.2019.2913372
G. Hever, L. Cohen, M. F. O’Connor, I. Matot, B. Lerner, and Y. Bitan, “Machine learning applied to multi-sensor information to reduce false alarm rate in the ICU,” Journal of Clinical Monitoring and Computing, vol. 34, no. 2, pp. 339–352, Apr. 2020. https://doi.org/10.1007/s10877-019-00307-x
T. M. Kadarina, Basari, and D. Gunawan, “ML-Based Interpretation of Cardiotocography Data: Current State and Future Research,” in 2023 International Conference of Computer Science and Information Technology (ICOSNIKOM), Nov. 2023, pp. 1–6. https://doi.org/10.1109/ICoSNIKOM60230.2023.10364517
X. Kang et al., “Prediction of Delivery Mode from Fetal Heart Rate and Electronic Medical Records Using Machine Learning,” in 2022 Computing in Cardiology (CinC), 2022, vol. 498, pp. 1–4. https://doi.org/10.22489/CinC.2022.116
S. Magesh and P. S. Rajakumar, “Ensemble feature extraction-based prediction of fetal arrhythmia using cardiotocographic signals,” Measurement: Sensors, 2023. https://doi.org/10.1016/j.measen.2022.100631
S. Mallat, A Wavelet Tour of Signal Processing. Elsevier, 1999.
M. A. Ma’sum, P. R. D. Intan, W. Jatmiko, A. A. Krisnadhi, N. A. Setiawan, and I. M. A. D. Suarjaya, “Improving Deep Learning Classifier for Fetus Hypoxia Detection in Cardiotocography Signal,” in 2019 International Workshop on Big Data and Information Security (IWBIS), 2019, pp. 51–56. https://doi.org/10.1109/IWBIS.2019.8935835
H. Liang and Y. Lu, “A CNN-RNN unified framework for intrapartum cardiotocograph classification,” Computer Methods and Programs in Biomedicine, vol. 229, p. 107300, Feb. 2023. https://doi.org/10.1016/j.cmpb.2022.107300
J. M. Lilly and S. C. Olhede, “Higher-order properties of analytic wavelets,” IEEE Transactions on Signal Processing, vol. 57, no. 1, pp. 146–160, 2008. https://doi.org/10.1109/TSP.2008.2007607
A. K. Pradhan, J. K. Rout, A. B. Maharana, B. K. Balabantaray, and N. K. Ray, “A Machine Learning Approach for the Prediction of Fetal Health using CTG,” in 2021 19th OITS International Conference on Information Technology (OCIT), 2021. https://doi.org/10.1109/OCIT53463.2021.00056
D. Panda, D. Panda, S. R. Dash, and S. Parida, “Extreme learning machines with feature selection using GA for effective prediction of fetal heart disease: A novel approach,” Informatica (Slovenia), vol. 45, no. 3, 2021. https://doi.org/10.31449/INF.V45I3.3223
R. Chinnaiyan and D. S. Alex, “Early Analysis and Prediction of Fetal Abnormalities Using Machine Learning Classifiers,” in 2021 2nd International Conference on Smart Electronics and Communication (ICOSEC), 2021. https://doi.org/10.1109/ICOSEC51865.2021.9591828
K. Bhogal, “Focus on cardiotocography: Intrapartum monitoring of uterine contractions,” British Journal of Midwifery, vol. 25, no. 8, pp. 491–497, 2017. https://doi.org/10.12968/bjom.2017.25.8.491
R. Zeng, Y. Lu, S. Long, C. Wang, and J. Bai, “Cardiotocography signal abnormality classification using time-frequency features and Ensemble Cost-sensitive SVM classifier,” Computers in Biology and Medicine, vol. 130, p. 104218, Mar. 2021. https://doi.org/10.1016/j.compbiomed.2021.104218
J. O’Heney, S. McAllister, M. Maresh, and M. Blott, “Fetal monitoring in labour: summary and update of NICE guidance,” BMJ, vol. 379, p. o2854, Dec. 2022. https://doi.org/10.1136/bmj.o2854
A. Sharma, Ed., Labour Room Emergencies. Springer, 2020.
H. D. Singh, M. Saini, and J. Kaur, “Fetal distress classification with deep convolutional neural network,” Current Women’s Health Reviews, vol. 17, no. 1, pp. 60–73, 2021.
L. Hruban et al., “Agreement on intrapartum cardiotocogram recordings between expert obstetricians,” Journal of Evaluation in Clinical Practice, vol. 21, no. 4, pp. 694–702, 2015.
A. M. Davani, M. Díaz, and V. Prabhakaran, “Dealing with disagreements: Looking beyond the majority vote in subjective annotations,” Transactions of the Association for Computational Linguistics, vol. 10, pp. 92–110, 2022.
W. H. Organization, Trends in maternal mortality 2000 to 2020: estimates by WHO, UNICEF, UNFPA, World Bank Group and UNDESA/Population Division. Geneva: World Health Organization, 2023.
W. H. Organization, Improving maternal and newborn health and survival and reducing stillbirth: progress report 2023. Geneva: World Health Organization, 2023.
W. H. Organization, WHO Recommendations Non-clinical Interventions to Reduce Unnecessary Caesarean Sections. Geneva: World Health Organization, 2018.
Y. Zhang, Q. Zhou, and X. Li, “The Advent of a New Era of Antenatal Cardiotocography,” Maternal-Fetal Medicine, vol. 4, no. 2, pp. 93–94, 2022. https://doi.org/10.1097/FM9.0000000000000144
P. Garcia-Canadilla, S. Sanchez-Martinez, F. Crispi, and B. Bijnens, “Machine Learning in Fetal Cardiology: What to Expect,” Fetal Diagnosis and Therapy, vol. 47, no. 5, pp. 363–372, 2020. https://doi.org/10.1159/000505021
J. Ogasawara et al., “Deep neural network-based classification of cardiotocograms outperformed conventional algorithms,” Scientific Reports, vol. 11, no. 1, p. 13367, Jun. 2021. https://doi.org/10.1038/s41598-021-92805-9
H. He and E. A. Garcia, “Learning from imbalanced data,” IEEE Transactions on Knowledge and Data Engineering, vol. 21, no. 9, pp. 1263–1284, 2009. https://doi.org/10.1109/TKDE.2008.239
K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770–778. https://doi.org/10.1109/CVPR.2016.90
T.-Y. Ross and G. Dollár, “Focal loss for dense object detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 42, no. 2, pp. 2980–2988, 2018. https://doi.org/10.1109/TPAMI.2018.2858826
X. Li, C. Lv, W. Wang, G. Li, L. Yang, and J. Yang, “Generalized focal loss: Towards efficient representation learning for dense object detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 3, pp. 3139–3153, 2022. https://doi.org/10.1109/TPAMI.2022.3180392
A. Zheng, Evaluating Machine Learning Models: A Beginner’s Guide to Key Concepts and Pitfalls. O’Reilly Media, 2015.
J. O’Heney, S. McAllister, M. Maresh, and M. Blott, “Fetal monitoring in labour: summary and update of NICE guidance,” BMJ, vol. 379, p. o2854, Dec. 2022. https://doi.org/10.1136/bmj.o2854
A. Ilham, I. N. Istiqomah, A. T. A. Nugroho, and S. P. Hadi, “Fetal Health Risk Classification using Important Feature Selection and CART Model on Cardiotocography Data,” Informatica, vol. 49, no. 1, pp. 1–12, 2025. https://doi.org/10.31449/inf.v49i1.5658
DOI: https://doi.org/10.31449/inf.v49i17.8991
This work is licensed under a Creative Commons Attribution 3.0 License.