Performance evaluation of Empirical Mode Decomposition and Discrete Wavelet Transform for computerized hypoxia detection and prediction

Cömert, Zafer; Zhang, Yang; Velappan, Subha; Boopathi, A. Manivanna; Kocamaz, Adnan Fatih

doi:10.1109/siu.2018.8404243

Cited by 12 publications

(12 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We employ a multiscale network to classify the fetal state and compare it to other works on the public database. 1) Comparing with ( Cömert et al, 2018a ), ( Cömert et al, 2018b ), the proposed multiscale model is more effective since it did not use complicated features. The proposed multiscale CNN-BiLSTM model has the highest SE and slightly lower SP for the same FHR signal classification criterion.…”

Section: Resultsmentioning

confidence: 99%

“…The experimental results of DFFN and other work on the public database are shown in Table 8 . 1) ( Cömert et al, 2018a ), ( Cömert et al, 2018b ), utilize some time-domain, and nonlinear features. These features perform better for fetal hypoxia identification (i.e.,SE) but are less efficient for normal fetal detection (i.e.,SP).…”

Section: Resultsmentioning

confidence: 99%

“…They demonstrate that ( Cömert et al, 2018a ) uses IBTF features, which can distinguish normal and acidic fetuses more accurately than other machine learning methods (combination of linear and nonlinear features, BFS + DWT). It is temporarily unable to test ( Cömert et al, 2018b ) and ( Cömert et al, 2018a ) on the private database since the essential details of their works are unavailable.…”

Section: Discussionmentioning

confidence: 99%

“…Long-Term Variability (LTV) and Short-Term Variability (STV) have been developed mainly for FHRV analysis ( Malik, 1996 ). On the other hand, transform-based methods such as empirical mode decomposition, discrete wavelet transform, and Fourier transform have been applied to extract implicit CTG features ( Cömert et al, 2018b ). Fetal state assessment also utilizes the features derived from fast Fourier transform and continuous wavelet transform ( Bursa and Lhotská, 2017 ).…”

Section: Introductionmentioning

confidence: 99%

“…(2016b) sought to categorize hypoxic fetuses. Cömert et al (2018b) assessed fetal state through SVM. They proposed an innovative image-based time-frequency feature extraction method (IBTF) ( Cömert et al, 2018a ).…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

A deep feature fusion network for fetal state assessment

Xiao

Liu

et al. 2022

Front. Physiol.

View full text Add to dashboard Cite

CTG (cardiotocography) has consistently been used to diagnose fetal hypoxia. It is susceptible to identifying the average fetal acid-base balance but lacks specificity in recognizing prenatal acidosis and neurological impairment. CTG plays a vital role in intrapartum fetal state assessment, which can prevent severe organ damage if fetal hypoxia is detected earlier. In this paper, we propose a novel deep feature fusion network (DFFN) for fetal state assessment. First, we extract spatial and temporal information from the fetal heart rate (FHR) signal using a multiscale CNN-BiLSTM network, increasing the features’ diversity. Second, the multiscale CNN-BiLSM network and frequently used features are integrated into the deep learning model. The proposed DFFN model combines different features to improve classification accuracy. The multiscale convolutional kernels can identify specific essential information and consider signal’s temporal information. The proposed method achieves 61.97%, 73.82%, and 66.93% of sensitivity, specificity, and quality index, respectively, on the public CTU-UHB database. The proposed method achieves the highest QI on the private database, verifying the proposed method’s effectiveness and generalization. The proposed DFFN combines the advantages of feature engineering and deep learning models and achieves competitive accuracy in fetal state assessment compared with related works.

show abstract