|
|
Odhad respirační aktivity z křivky elektrokardiogramu pomocí strojového učení
Ondrejková, Eliška ; Vítek, Martin (oponent) ; Plešinger, Filip (vedoucí práce)
Táto bakalárska práca sa zaoberá metódami odhadu dychovej aktivity z EKG. Pre lepšie pochopenie témy je opísaná anatómia a fyziológia dýchacieho a kardiovaskulárneho systému. Okrem toho sú vysvetlené aj viaceré metódy odhadu. V praktickej časti bol použitý verejný dataset EKG signálov odčítaných z polysomnografie. Algoritmus na odhad bol implementovaný v programovacom jazyku Python pomocou knižnice PyTorch. Na záver sa diskutujú výsledky a porovnávajú sa s inými metódami.
|
|
|
Analysis of ultra-high frequency ECG using deep learning
Koščová, Zuzana ; Antin, Christoph Hoog (oponent) ; Plešinger, Filip (vedoucí práce)
Ultra-high-frequency ECG (UHF-ECG) analysis provides information about electrical ventricular dyssynchrony. Additionally, real-time UHF-ECG analysis enables direct optimization of the pacing electrode during pacemaker implantation. In this master thesis, we describe ventricular conduction abnormalities, the current method for UHF-ECG analysis and most importantly, we have developed several deep learning models to find out which steps of UHF-ECG analysis can be replaced by deep learning. Data used for the development and validation of the models come from 2 private hospitals (FNUSA-ICRC hospital, Brno, Czechia, and FNKV hospital Prague, Czechia) and from 3 publicly available datasets. First, we present two deep learning methods for QRS complex detection and QRS complex duration estimation in one inference step. We received an overall F1-score of 98.84 ± 0.51 \% for the detection task and a Mean Absolute Error (MAE) of 12.25 ± 2.16 ms for the QRS duration estimation task. This method enhances UHF-ECG analysis performance and therefore could significantly reduce measurement time. Furthermore, a regression model for pacing stimuli removal based on a conditional generative adversarial network was developed. The results were evaluated based on the correlation of 15 averaged high-frequency envelopes in the QRS complex region between the model output and the target signal. The results show a higher correlation on spontaneous than on paced data and a drop in correlation with the increasing frequency band. Last, two deep learning models with convolutional neural network (CNN) were created to estimate ventricular electrical dyssynchrony (VED). Specifically, one-dimensional (1D) and 2-dimensional (2D) CNN. The MAE between our solution and annotation is 12.61 ±18.95 ms and 12.27 ±17.73 ms for 1D and 2D CNN, respectively. MAE on spontaneous data is approximately 5 ms lower than on paced data for both models, indicating the need to remove the pacing stimuli. These deep learning models yield a reduction in the pre-processing pipeline while delivering output in a single inference step. For the QRS detection and QRS duration estimation model, the performance improvement over the current solution is evident and these steps of UHF-ECG analysis could be replaced by deep learning. However, for the removal of pacing stimuli and VED parameter estimation, it is required to improve the performance.
|
|
|
Odhad respirační aktivity z křivky elektrokardiogramu pomocí strojového učení
Ondrejková, Eliška ; Vítek, Martin (oponent) ; Plešinger, Filip (vedoucí práce)
Táto bakalárska práca sa zaoberá metódami odhadu dychovej aktivity z EKG. Pre lepšie pochopenie témy je opísaná anatómia a fyziológia dýchacieho a kardiovaskulárneho systému. Okrem toho sú vysvetlené aj viaceré metódy odhadu. V praktickej časti bol použitý verejný dataset EKG signálov odčítaných z polysomnografie. Algoritmus na odhad bol implementovaný v programovacom jazyku Python pomocou knižnice PyTorch. Na záver sa diskutujú výsledky a porovnávajú sa s inými metódami.
|
|
|
SMV-2018-19: Systém pro analýzu EKG
Plešinger, Filip ; Jurák, Pavel ; Halámek, Josef ; Viščor, Ivo
Předmětem smluvního výzkumu je vývoj algoritmů pro automatické zpracování EKG z jednosvodových EKG holterů. Jmenovitě se jedná o:\n- vývoj algoritmu pro detekci QRS komplexů s důrazem na odolnost vůči rušení\n- vývoj algoritmu pro analýzu arytmií na základě RR intervalů a dalších ukazatelů. Algoritmus využívá strojové učení (neuronovou síť). Vstupem jsou informace o QRS komplexech a další deskriptory extrahované z EKG signálu. Výstupem je kategorie hodnoceného EKG bloku (fibrilace síní, AV-blok, nekvalitní signál, supraventrikulární extrasystoly, komorové extrasystoly, sinusový rytmus, supraventrikulární tachykardie a komorová tachykardie)\n- implementaci algoritmů jako software pro .NET platformu v jazyce C#. Cílová aplikace je optimalizována pro použití na vícevláknových počítačích (předpokládán výpočetní server zhotovitele).
|
|
|
Biventricular pacing optimization by means of the dyssynchrony parameter
Jurák, Pavel ; Leinveber, P. ; Halámek, Josef ; Plešinger, Filip ; Postránecká, T. ; Lipoldová, J. ; Novák, M.
To improve Cardiac Resynchronization Therapy (CRT), different interventricular delay (VVD) settings can be used. However, relatively small VVD induced hemodynamic changes cannot be measured by standard echocardiographic methods. The QRS complex duration (QRSd) is mostly the main criterion. Here we introduce a new dyssynchrony parameter (DYS) that is able to more accurately detect improved electrical synchrony. Methods: 12-lead 5 kHz ECG during 3-10 minute rest period was measured in 46 patients with CRT OFF and CRT ON with VVD 0 ms (CRT0) and -20 ms (CRT20). We detected QRSd and the dyssynchrony parameter DYS as the time difference between 500-1000 Hz averaged envelopes positions in the V1 and V6 leads in the QRS complex region. Results: 32 of 46 patients had a positive CRT response manifested by QRSd shortening and a DYS decrease. 28 of 32 patients had a positive LV pre-excitation effect: additional QRSd shortening of 4.7+/-.9 ms and a DYS decrease of 12.6+/-7.5 ms. The correlation coefficient of QRSd and DYS changes (CRT 0 vs CRT 20) was 0.23 and indicates information diversity. The DYS parameter differs from QRSd and provides a significantly higher response to VVdelay changes (p <; 0.001).
|
host ::
RSS.