Automated Digitization of the Cardiotocography Signals from Real Scene Image of Binary Clinic Report - 24/05/22

Doi : 10.1016/j.irbm.2022.02.001

Y. Zhang ^a, Y. Si ^a, Z. Liu ^a, Z. Zhao ^a,^{^⁎} , H. Ye ^b,^{^⁎⁎}
^a School of Electronics and Information, Hangzhou Dianzi University, Hangzhou, PR China
^b Department of Obstetrics, Woman's Hospital, School of Medicine, Zhejiang University, Hangzhou, PR China

^⁎Corresponding author at: School of Electronics and Information, Hangzhou Dianzi University, Hangzhou, 310000, PR China.School of Electronics and InformationHangzhou Dianzi UniversityHangzhou310000PR China^⁎⁎Corresponding author at: Department of Obstetrics, Woman's Hospital, School of Medicine, Zhejiang University, Hangzhou, 310000, PR China.Department of ObstetricsWoman's HospitalSchool of MedicineZhejiang UniversityHangzhou310000PR China

Graphical abstract

Le texte complet de cet article est disponible en PDF.

Abstract

Objective

Cardiotocography (CTG) is a popular clinical tool to assess foetal health status. Automatic CTG analysis can remove the judgement differences of inter- and intra- doctors. However, absence of CTG database has hindered the development of automatic CTG analysis based on deep learning. Therefore, digitization of CTG signal from clinic report is an important way to enrich CTG database, and in turn promote the automatic CTG analysis.

Method

The proposed digitization method extracts digital signal from the commonly used binary CTG paper reports. An adaptive region positioning algorithm based on statistical calculation is used to locate signal regions. Then, by deducing the dynamic minimal weight sum in theory, methods based on statistical calculation and on the weight sum are designed to remove grid lines. Next, according to different breakpoint types and signal line trends, different signal reconstruction methods are formulated. This realize extracting the signal line from binary background grid lines. Finally, a calibration method based on segmented sampling is designed to reduce calibration error due to smartphone lens distortion.

Results

The experimental results show that the correlation coefficients of FHR and UC of proposed method both reached 0.98. After three expert gynaecologists's evaluations, there are no clinically relevant differences were identified between the extracted signals and the reference ones.

Le texte complet de cet article est disponible en PDF.

Highlights

•	First time to extract the cardiotocograph signals from the binary clinic paper report.
•	Adaptive region positioning algorithm based on statistical calculation.
•	Statistical calculation and weight sum are designed to remove grid lines.
•	Segmented sampling is designed to reduce calibration error due to smartphone lens distortion.
•	Digitization of CTG signal is important way to promote the automatic CTG analysis.