Automatic Cardiotocography Diagnostic System based on Hilbert Transform and Adaptive Threshold Technique.pdf (708.63 kB)
Download file

Automatic Cardiotocography Diagnostic System Based on Hilbert Transform and Adaptive Threshold Technique

Download (708.63 kB)
journal contribution
posted on 03.04.2020, 15:31 by Joao Alexandre Lobo Marques, Paulo Cesar Cortez, Joao Paulo Do Vale Madeiro, Simon James Fong, Fernando Soares Schlindwein, Vigor Hugo C De Albuquerque
The visual analysis of cardiotocographic examinations is a very subjective process. The accurate detection and segmentation of the fetal heart rate (FHR) features and their correlation with the uterine contractions in time allow a better diagnostic and the possibility of anticipation of many problems related to fetal distress. This paper presents a computerized diagnostic aid system based on digital signal processing techniques to detect and segment changes in the FHR and the uterine tone signals automatically. After a pre-processing phase, the FHR baseline detection is calculated. An auxiliary signal called detection line is proposed to support the detection and segmentation processes. Then, the Hilbert transform is used with an adaptive threshold for identifying fiducial points on the fetal and maternal signals. For an antepartum (before labor) database, the positive predictivity value (PPV) is 96.80% for the FHR decelerations, and 96.18% for the FHR accelerations. For an intrapartum (during labor) database, the PPV found was 91.31% for the uterine contractions, 94.01% for the FHR decelerations, and 100% for the FHR accelerations. For the whole set of exams, PPV and SE were both 100% for the identification of FHR DIP II and prolonged decelerations.

Funding

The first author thanks to Trium Analysis Online GmBH, Maternity Hospital MEAC-UFC, LESC-UFC and Laboratory of Bioengineering at the University of Leicester. The third author thanks to CNPQ via Grant No. 426002/2016-4. The fourth author thanks to UMAC Grant. The sixth author thanks to CNPQ via Grant No. 304315/2017-6.

History

Citation

J. A. Lobo Marques, P. C. Cortez, J. P. D. V. Madeiro, S. J. Fong, F. S. Schlindwein and V. H. C. D. Albuquerque, "Automatic Cardiotocography Diagnostic System Based on Hilbert Transform and Adaptive Threshold Technique," in IEEE Access, vol. 7, pp. 73085-73094, 2019.

Version

AM (Accepted Manuscript)

Published in

IEEE ACCESS

Volume

7

Pagination

73085 - 73094 (10)

Publisher

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC

issn

2169-3536

eissn

2169-3536

Available date

09/04/2019

Publisher version

https://ieeexplore.ieee.org/abstract/document/8682138

Language

English