izpis_h1_title_alt

Avtomatsko razlikovanje patoloških in nepatoloških sprememb EKG signala : doktorska disertacija
ID Faganeli Pucer, Jana (Author), ID Kukar, Matjaž (Mentor) More about this mentor... This link opens in a new window

URLURL - Presentation file, Visit http://eprints.fri.uni-lj.si/2328/ This link opens in a new window

Abstract
Snemanje in analiza posnetkov EKG sta pomembna postopka v diagnozi srčnih bolezni. Postopek je še posebej priljubljen, ker ni zahteven za izvedbo, je neinvaziven, poceni in dostopen v primerjavi z drugimi postopki, za diagnozo srčnih bolezni. Poleg kratkih EKG posnetkov v kontroliranem okolju (ambulanti), pa pogosto snemajo tudi dolge (24-urne) EKG posnetke. Taki posnetki so uporabni predvsem za diagnozo različnih aritmij, lahko pa tudi za zgodnje odkrivanje srčne ishemije. Naše delo obravnava razpoznavanje različnih patoloških stanj (anomalij) v dolgih EKG posnetkih. Prva anomalija, ki jo obravnavamo, je srčna ishemija, ki se v EKG posnetkih odraža kot deviacija segmenta ST. V preteklih letih je bilo objavljenih veliko število člankov na temo odkrivanja prehodnih epizod segmenta ST. Težava opisanih pristopov je, da ne znajo razlikovati med ishemičnimi epizodami in nepatološkimi epizodami, ki nastanejo zaradi spremembe srčne frekvence. V našem delu predstavimo dva načina za razlikovanje med tipoma epizod. Prvi način je s pomočjo izbora atributov; atributi, ki opisujejo spremembo srčne frekvence, atributi, ki opisujejo deviacije in spremembe morfologije segmenta ST in spremembo kompleksa QRS. S pomočjo izbranih atributov in različnih klasifikatorjev pokažemo, da je razlikovanje med tipoma epizod mogoče. Po zgledu metod uporabljenih v obremenilnih testih izpeljemo ST(HR) diagram za dolge EKG posnetke in iz njega odčitamo množico atributov, ki nam pomagajo razlikovati med tipoma epizod. Opazujemo diagram v dveh odsekih (podobno kot v obremenilnih testih) od začetka epizode do njenega ekstrema, ter od ekstrema epizode do njenega konca in definiramo maksimalen naklon diagrama, celoten naklon diagrama in kot ob ekstremu diagrama. Nakloni, dva celotna in dva maksimalna, se pokažejo kot relativno dobri atributi (po kriterijih za ocenjevanje kvalitete atributov), medtem ko kot ob ekstremu diagrama ni relevanten atribut. Tem novim atributom dodamo še vrednosti srčne frekvence ob začetku, ekstremu in koncu epizode. S pomočjo teh atributov klasificiramo epizode nekoliko slabše kot z atributi opisanimi v prejšnjem odstavku. Velika prednost te metode je, da je uporablja manj atributov, ki so lažje razumljivi in jih bolj enostavno izračunamo. Druga vrsta anomalij, ki jih obravnavamo, so aritmični utripi. V ta namen razvijemo postopek za detekcijo kompleksov QRS, ki temelji na diskretni Morsejevi teoriji in postopek za detekcijo aritmičnih utripov. Razviti postopek za detekcijo kompleksov QRS temelji na krajšanju parov sosednjih minimumov in maksimumov po postopku krajšanja v diskretni Morsejevi teoriji. Z dodatkom pravil o obliki kompleksa QRS, ki temeljijo na predznanju o EKG posnetkih, razvijemo uspešen in učinkovit postopek (v primerjavi z objavljenimi postopki) za detekcijo kompleksov QRS. Na podoben način razvijemo tudi postopek, ki hkrati poišče komplekse QRS in do 4 valove, značilne za utrip EKG ( P, QRS, T in U) med zaporednima kompleksoma QRS. S pomočjo originalne mere podobnosti med dvema krivuljama ocenjujemo podobnost med sosednjima utripoma. Ker se aritmije pojavljajo kot nenadna spremembe oblike in frekvence srčnega utripa, lahko kot atributa pri klasifikaciji utripov (aritmični ali ne) uporabimo podobnost med dvema zaporednima utripoma in razliko v dolžinah RR intervalov. Rezultati metode za odkrivanje kompleksov QRS so primerljivi z najboljšimi rezultati objavljenimi v literaturi. Zmogljivost postopka za odkrivanje anomalij je tudi visoka, predvsem na posnetkih, ki vsebujejo veliko število patoloških utripov (npr. PVC).

Language:Slovenian
Keywords:elektrokardiogram, ishemija, aritmija, diskretna Morseova teorija, merjenje razdalje med krivuljama, strojno učenje, računalništvo, disertacije
Work type:Dissertation
Typology:2.08 - Doctoral Dissertation
Organization:FRI - Faculty of Computer and Information Science
Place of publishing:Ljubljana
Publisher:[J. Faganeli Pucer]
Year:2013
Number of pages:117 str.
PID:20.500.12556/RUL-68227 This link opens in a new window
UDC:004.85:616.12-073(043.3)
COBISS.SI-ID:10431060 This link opens in a new window
Publication date in RUL:10.07.2015
Views:2193
Downloads:266
Metadata:XML RDF-CHPDL DC-XML DC-RDF
:
Copy citation
Share:Bookmark and Share

Secondary language

Language:English
Title:Automatic razlikovanje of pathologic and non-pathologic changes in ECG signals
Abstract:
Heart disease is the leading cause of death in the developed world. ECG signal recording and analysis is the easiest is the prime diagnostic procedure for early diagnosis of heart conditions. It is non-invasive, inexpensive and accessible when compared to other clinical procedures used in the diagnosis of heart disease. In clinical practice, short ECG recordings are usually used, which are recorded in a controlled environment, but long (24-hour) ECG recording (AECG) are also gaining popularity. AECG recordings are used mostly in the diagnosis of different arrhythmias, sometimes even in the diagnosis oh heart ischemia. Our work deals with the automatic detection of pathologic events in long ECG recordings. The first heart pathology we research is heart ischemia. It manifests as ST segment deviation in ECG signals. In the past years a large number of research papers have been published, dealing with the detection of transient ST segment episodes in AECG. The described ST segment episode detectors fail to differentiate between transient ischemic and transient non-ischemic heart rate related episodes. In our work we describe two methods to differentiate transient ST segment episodes. The first method uses a set of features; features that describe heart rate changes, ST segment deviation and morphology changes and QRS complex morphology changes. Using a set of features and different classifiers we show that automatic classification of the two types of episodes can be successful. Following the example of the methods used in exercise ECG (EECG) we define a ST(HR) diagram for AECG. The diagram is used to calculate a subset of features that help us differentiate between ischemic and heart rate related episodes. Similarly as in EECG we observe the diagram in two parts; from the beginning to the extreme of the episode and from the extreme to the end of the episode. We define two overall slopes, two maximal slope and the angle at the extrema of the episode. The slopes are good features (ranked with feature evaluation techniques) while the angle at the extrema is not a good feature. We also observe the heart rate at the beginning, extrema and end of the episodes. The performance of the classification with this set of features is worse than the classification with the set of features described in the last paragraph. The advantage of the classification with the ST(HR) diagram is that it uses a smaller number of features, the features are more comprehensive and easier to calculate. The second anomaly we study in our work is the detection of arrhythmic beats. Here we first develop a QRS detector based on the discrete Morse theory and then an arrhythmia detector. The QRS detector is based on cancelling neighbouring minima and maxima as in discrete Morse theory. With the addition of knowledge from ECG signal theory the performance of our QRS detector is very similar to the best performances published in the literature. Using a similar method as in QRS detection, we develop a procedure that simultaneously finds QRS complexes and up to four of the most significant waves (typical for ECG signals; P, QRS, T and U) between consecutive R waves. With the help of a newly developed algorithm, that evaluates the similarity between two trajectories, we assessed the similarity between consecutive heart beats. Then we classify pairs of heart beats as normal of arrhythmic with the help of two features; the similarity between the pair of beats and the difference between their RR intervals. The performance of the arrhythmia detector is high, especially on records containing a large number of very pathologic heart beats (e.g. PVC).

Keywords:electrocardiogram, ischemia, arrhythmia, discrete Morse theory, distance between trajectories, machine learning, computer science, doctoral dissertations, theses

Similar documents

Similar works from RUL:
Similar works from other Slovenian collections:

Back