Ločevanje skupin posnetkov elektrohisterografskih signalov s prezgodnjim in terminskim porodom na osnovi ocenjevanja sprememb razširjanja električnih potencialov

Vouk, Paula (author), Jager, Franc (mentor)

S preučevanjem elektrohisterografskih (EHG) signalov, ki prikazujejo spremembe električnih potencialov maternice, se lahko neinvazivno spopadamo s problemom napovedovanja prezgodnjega poroda. V tem magistrskem delu želimo ločevati skupini materničnih EHG posnetkov s prezgodnjim in terminskim porodom na osnovi ocenjevanja hitrosti in smeri razširjanja električnih potencialov. Smeri in hitrosti izračunamo z uporabo kratkočasovne križne korelacije. To je postopek s katerim primerjamo vrednosti parov vzporednih signalov, nad in pod popkom ter levo in desno od popka ter določimo časovne zamike parov signalov. Iz časovnih zamikov nato izračunamo zaporedja hitrosti ter smeri potovanja valov razširjanja. Tekom študije smo definirali značilke, ki opisujejo pojavitev smeri in hitrosti razširjanja ter njuno regularnost. Dodali smo še nekaj značilk, ki opisujejo osnovne signale. Skupni spekter izbranih značilk omogoča boljše razumevanje električne aktivnosti v maternici. Celotno analizo ter ločevanje skupin posnetkov izvajamo na signalih znotraj različnih frekvenčnih območij in s tem preučujemo vplive različnih fizioloških mehanizmov. Na frekvenčnem pasu pod 1,0 Hz na električno aktivnost v maternici najbolj vplivajo maternični popadki, nad 1,0 Hz pa izključno bitje materinega srca. Posnetke analiziramo v celoti ali pa karakteriziramo posamične intervale posnetkov, intervale s popadki ter prazne intervale. Poleg tipa intervalov in frekvenčnega področja signalov pa ocenimo klasifikacijsko točnost definiranih značilk tudi glede na čas snemanja posnetkov. Ugotavljamo, da je preučevanje vplivov materinega srca ključno pri ločevanju skupin posnetkov, saj so najvišje klasifikacijske točnosti dosežene na frekvenčnem področju nad 1,0 Hz. Vplivi materinega srca največ doprinesejo pri klasifikaciji na praznih intervalih. Najvišje rezultate klasifikacije dosegajo značilke, ki opisujejo regularnost osnovnih signalov in značilka pogostost razširjanja električnih potencialov v horizontalni smeri. Zadnja značilka se je izkazala kot najbolj pomembna značilka pri ločevanju posnetkov posnetih zgodaj v nosečnosti in tako omogoča zgodnje napovedovanje prezgodnjega poroda v klinični praksi.

• Language: Slovenian
• Keywords: Elektrohisterografski signali, razširjanje električnih potencialov, prezgodnji porod.
• Work type: Master's thesis/paper
• Typology: 2.09 - Master's Thesis
• Organization: FMF - Faculty of Mathematics and Physics; FRI - Faculty of Computer and Information Science
• Year: 2020
• PID: 20.500.12556/RUL-117182
• COBISS.SI-ID: 21019651
• Publication date in RUL: 01.07.2020

Secondary language

• Language: English
• Title: Separating preterm and term delivery groups of electrohysterography signal records based on the estimation of the electric potential propagation changes

Abstract

By studying the electrohysterogram (EHG) signals, which reveal the changes of the electric potentials of the uterus, we can tackle the problem of preterm birth prediction non-invasively. The aim is to separate the sets of preterm and term delivery EHG records based on the estimation of the velocity and direction of the electric potential propagation. We calculate the directions and velocities using the short-time cross-correlation procedure. We compare the values of pairs of parallel signals above and below, and left and right from the navel, and determine the time delays of the pairs of signals. Sequences of velocities and directions of travel of the propagation waves are calculated next. We defined features that describe the direction and velocity of propagation, and their regularity, and added some features that describe original signals. The features allow us to better understand the electrical activities of the uterus. We perform separation of the groups of records inside the selected frequency bands, and study the impact of different physiological mechanisms. In the frequency band below 1.0 Hz, the most influent on the electrical activity are the uterine contractions, while above 1.0 Hz, exclusively mother's heart beating. We analyse the records as whole, and characterize the selected individual intervals of records, i.e., intervals containing contractions, or non-contraction intervals. Besides the type of the intervals and the selected frequency band, we estimate also the classification accuracy of the defined features with regard to the time of recording. We conclude that studying the influence of the maternal heart is of key importance during separating the groups of records since the highest classification accuracies were obtained above 1.0 Hz. The maternal heart influences are the most contributive when classifying non-contractions intervals. The highest classification results were obtained using those features that describe regularity of the original signals, and frequency of propagation of the electric potentials in horizontal direction. The last feature appeared to be the most important feature when separating records recorded early during pregnancy, thus allowing early prediction of preterm birth in clinical practice.

• Keywords: Electrohysterogram signals, propagation of electric potential, preterm birth.