Detection, segmentation and classification of heart sounds

Slides:



Advertisements
Similar presentations
11/11/02 IDR Workshop Dealing With Location Uncertainty in Images Hasan F. Ates Princeton University 11/11/02.
Advertisements

An Approach to ECG Delineation using Wavelet Analysis and Hidden Markov Models Maarten Vaessen (FdAW/Master Operations Research) Iwan de Jong (IDEE/MI)
Heart Sound Analysis: Theory, Techniques and Applications Guy Amit Advanced Research Seminar May 2004.
An Exploration of Heart Sound Denoising Method Based on Wavelet and Singular Spectrum Analysis Name: ZENG Tao Supervisor: Prof. DONG Mingchui University.
Hidden Markov Models (1)  Brief review of discrete time finite Markov Chain  Hidden Markov Model  Examples of HMM in Bioinformatics  Estimations Basic.
Hidden Markov Models. Room Wandering I’m going to wander around my house and tell you objects I see. Your task is to infer what room I’m in at every point.
Toward Automatic Music Audio Summary Generation from Signal Analysis Seminar „Communications Engineering“ 11. December 2007 Patricia Signé.
Introduction The aim the project is to analyse non real time EEG (Electroencephalogram) signal using different mathematical models in Matlab to predict.
Hidden Markov Models. A Hidden Markov Model consists of 1.A sequence of states {X t |t  T } = {X 1, X 2,..., X T }, and 2.A sequence of observations.
Hidden Markov Models Theory By Johan Walters (SR 2003)
Hidden Markov Models in NLP
Hidden Markov Model based 2D Shape Classification Ninad Thakoor 1 and Jean Gao 2 1 Electrical Engineering, University of Texas at Arlington, TX-76013,
Feature Vector Selection and Use With Hidden Markov Models to Identify Frequency-Modulated Bioacoustic Signals Amidst Noise T. Scott Brandes IEEE Transactions.
HMM-BASED PATTERN DETECTION. Outline  Markov Process  Hidden Markov Models Elements Basic Problems Evaluation Optimization Training Implementation 2-D.
LYU0103 Speech Recognition Techniques for Digital Video Library Supervisor : Prof Michael R. Lyu Students: Gao Zheng Hong Lei Mo.
Multi-resolution Analysis TFDs, Wavelets Etc. PCG applications.
Data Acquisition Carotid pulse (CP), apexcardiogram (ACG), phonocardiogram (PCG), electrocardiogram (EKG) and Doppler-audio signals were digitally acquired.
Lecture 5: Learning models using EM
Hidden Markov Models K 1 … 2. Outline Hidden Markov Models – Formalism The Three Basic Problems of HMMs Solutions Applications of HMMs for Automatic Speech.
Part 6 HMM in Practice CSE717, SPRING 2008 CUBS, Univ at Buffalo.
Efficient Estimation of Emission Probabilities in profile HMM By Virpi Ahola et al Reviewed By Alok Datar.
Modeling of Mel Frequency Features for Non Stationary Noise I.AndrianakisP.R.White Signal Processing and Control Group Institute of Sound and Vibration.
Hidden Markov Models David Meir Blei November 1, 1999.
ECG Signal Delineation And Compression Chapters – th November T Biomedical Signal Processing.
Handwritten Character Recognition using Hidden Markov Models Quantifying the marginal benefit of exploiting correlations between adjacent characters and.
1 QRS Detection Section Linda Henriksson BRU/LTL.
Entropy and some applications in image processing Neucimar J. Leite Institute of Computing
TEMPORAL VIDEO BOUNDARIES -PART ONE- SNUEE KIM KYUNGMIN.
Isolated-Word Speech Recognition Using Hidden Markov Models
The Wavelet Tutorial: Part3 The Discrete Wavelet Transform
Alignment and classification of time series gene expression in clinical studies Tien-ho Lin, Naftali Kaminski and Ziv Bar-Joseph.
EE 6331, Spring, 2009 Advanced Telecommunication Zhu Han Department of Electrical and Computer Engineering Class 11 Feb. 24 th, 2009.
Segmental Hidden Markov Models with Random Effects for Waveform Modeling Author: Seyoung Kim & Padhraic Smyth Presentor: Lu Ren.
BINF6201/8201 Hidden Markov Models for Sequence Analysis
The Wavelet Tutorial Dr. Charturong Tantibundhit.
Fundamentals of Hidden Markov Model Mehmet Yunus Dönmez.
T – Biomedical Signal Processing Chapters
Time Series Data Analysis - I Yaji Sripada. Dept. of Computing Science, University of Aberdeen2 In this lecture you learn What are Time Series? How to.
Automatic Ballistocardiogram (BCG) Beat Detection Using a Template Matching Approach Adviser: Ji-Jer Huang Presenter: Zhe-Lin Cai Date:2014/12/24 30th.
Hidden Markov Models Yves Moreau Katholieke Universiteit Leuven.
Overview: Medical Signal Processing Week 2 Lecture 1.
Authors: Sriram Ganapathy, Samuel Thomas, and Hynek Hermansky Temporal envelope compensation for robust phoneme recognition using modulation spectrum.
Feature Vector Selection and Use With Hidden Markov Models to Identify Frequency-Modulated Bioacoustic Signals Amidst Noise T. Scott Brandes IEEE Transactions.
ECE 8443 – Pattern Recognition ECE 8423 – Adaptive Signal Processing Objectives: ML and Simple Regression Bias of the ML Estimate Variance of the ML Estimate.
Alberto Porta Department of Biomedical Sciences for Health Galeazzi Orthopedic Institute University of Milan Milan, Italy Understanding the effect of nonstationarities.
PGM 2003/04 Tirgul 2 Hidden Markov Models. Introduction Hidden Markov Models (HMM) are one of the most common form of probabilistic graphical models,
Performance Comparison of Speaker and Emotion Recognition
EEL 6586: AUTOMATIC SPEECH PROCESSING Speech Features Lecture Mark D. Skowronski Computational Neuro-Engineering Lab University of Florida February 27,
Presented by: Fang-Hui Chu Discriminative Models for Speech Recognition M.J.F. Gales Cambridge University Engineering Department 2007.
Automatic Speech Recognition A summary of contributions from multiple disciplines Mark D. Skowronski Computational Neuro-Engineering Lab Electrical and.
RCC-Mean Subtraction Robust Feature and Compare Various Feature based Methods for Robust Speech Recognition in presence of Telephone Noise Amin Fazel Sharif.
Bayesian Speech Synthesis Framework Integrating Training and Synthesis Processes Kei Hashimoto, Yoshihiko Nankaku, and Keiichi Tokuda Nagoya Institute.
1 Hidden Markov Models Hsin-min Wang References: 1.L. R. Rabiner and B. H. Juang, (1993) Fundamentals of Speech Recognition, Chapter.
Statistical Models for Automatic Speech Recognition Lukáš Burget.
CPSC 7373: Artificial Intelligence Lecture 12: Hidden Markov Models and Filters Jiang Bian, Fall 2012 University of Arkansas at Little Rock.
EEL 6586: AUTOMATIC SPEECH PROCESSING Speech Features Lecture Mark D. Skowronski Computational Neuro-Engineering Lab University of Florida February 20,
Hidden Markov Model Parameter Estimation BMI/CS 576 Colin Dewey Fall 2015.
Other Models for Time Series. The Hidden Markov Model (HMM)
Visual Recognition Tutorial1 Markov models Hidden Markov models Forward/Backward algorithm Viterbi algorithm Baum-Welch estimation algorithm Hidden.
QRS Detection Linda Henriksson 1.
Supervised Time Series Pattern Discovery through Local Importance
Tremor Detection Using Motion Filtering and SVM Bilge Soran, Jenq-Neng Hwang, Linda Shapiro, ICPR, /16/2018.
8-Speech Recognition Speech Recognition Concepts
An Improved Neural Network Algorithm for Classifying the Transmission Line Faults Slavko Vasilic Dr Mladen Kezunovic Texas A&M University.
Handwritten Characters Recognition Based on an HMM Model
Speech recognition, machine learning
Volume 86, Issue 3, Pages (March 2004)
NON-NEGATIVE COMPONENT PARTS OF SOUND FOR CLASSIFICATION Yong-Choon Cho, Seungjin Choi, Sung-Yang Bang Wen-Yi Chu Department of Computer Science &
Speech recognition, machine learning
Presentation transcript:

Detection, segmentation and classification of heart sounds Daniel Gill Advanced Research Seminar May 2004

Automatic Cardiac Signals Analysis Problems : Pre-processing and noise treatment. Detection\segmentation problem. Classification problem: Feature extraction – waveshape & temporal information. The classifier.

Outline Methods based on waveshape : - Envelogram - Wavelet decomposition and reconstruction - AR modeling - Envelogram estimation using Hilbert transform Suggested method : Homomorphic analysis Suggested temporal modeling : Hidden Markov Models

Heart beat, why do you miss when my baby kisses me ? B. Holly (1957)

PCG Analysis We will concentrate mainly on S1 and S2. We will discuss only methods which do not use external references (ECG, CP or other channels). Most of the methods are non-parametric or semi-parametric (parametric models for the waveshape but non-parametric in the temporal behavior). Suggestion for parametric modeling.

Features of PCG The envelope of PCG signals might convey useful information. In order to detect\segment\classify cardiac events we might need temporal information.

Segmentation Using Envelogram (S. Liang et al. 1997) Use Shannon energy to emphasize the medium intensity signal. Shannon Energy: E=-x2log(x2)

Segmentation Using Envelogram The Shannon energy eliminates the effect of noise. Use threshold to pick up the peaks.

Segmentation Using Envelogram Reject extra peaks and recover weak peaks according to the intervals statistics. Recover lost peaks by lowering the threshold

Segmentation Using Envelogram Identify S1 and S2 according the intervals between adjacent peaks.

Segmentation Using Wavelet Decomposition and Reconstruction (Liang et al. 1997) Use the frequency bands that contain the majority power of S1 and S2. Daubechies filters at frequency bands : a4 : 0-69Hz d4 : 69-138Hz d5 : 34-69Hz

Segmentation Using Wavelet Decomposition and Reconstruction Use Shannon energy to pick up the peaks above certain threshold. Identify S1 and S2 according to set of rules similar to those used in segmentation with envelograms. Compare the segmentation results of d4, d5 and a4. The choosing criterion : more identified S1s and S2s and less discarded peaks.

Segmentation Using Wavelet Decomposition and Reconstruction

AR modeling of PCG (Iwata et al. 1977, 1980) Used narrow sliding windows (25ms) to compute 8th order AR model. Features used : dominant poles (below 80Hz) and bandwidth. Detected S1, S2 and murmurs.

Segmentation and Event Detection - Cons Most of the methods are based on rules of thumb – no physical basis. In most cases there is no parametric model of the waveshape and\or timing mechanism. Not suitable for abnormal\irregular cardiac activity. In case of AR model, there is still question of optimality : window size, order etc. In addition, there is no model for the timing mechanism of the events. Heart sounds are highly non-stationary – AR model is very much inaccurate.

Suggested Methods Waveshape analysis – Homomorphic Filtering. Temporal Model – (Semi) Hidden Markov Models.

Waveshape analysis - Homomorphic filtering Express the PCG signal x(t) by where a(t) is the amplitude modulation (AM) component (envelope) and f(t) is the Frequency modulation (FM) component. Define

… Thus If the FM component is characterized by rapidly variations in time - apply an appropriate linear low-pass filter L. we have L is linear so : By exponentiation :

AM envelopes (a) Normal beat, (b) Atrial septal defect, (c) Mitral stenosis (d) Aortic insufficiency.

Identifying Peaks A simple threshold was used to mark all the peak locations of the AM envelogram. Suppose that two consecutive peaks are found at and . We might have to reject extra peaks or recover lost peaks.

Extra peaks were rejected by the following rules: if (splitted peak) if choose else choose else choose (not splitted)

… When an interval exceeds the high-level limit, it is assumed that a peak has been lost and the threshold is decreased by a certain amount. It is repeated until the lost peaks are found or a certain limit is reached.

Labeling The longest interval between two adjacent peaks is the diastolic period (from the end of S2 to the beginning of S1). The duration of the systolic period (from the end of S1 to the beginning of S2) is relatively constant

Labeling Thus Find the longest time interval. Set S2 as the start point and S1 as the end point. Label the intervals forward and backward.

Normal heart beat with the labels found

Homomorphic Filtering Pros Provides smooth envelope with physical meaning. The envelope resolution (smoothness) can be controlled. Enables parametric modeling of the amplitude modulation for event classification (polynomial fitting ?). Enables parametric modeling of the FM component (pitch estimation, chirp estimation ?)

Temporal Model – (Semi) Hidden Markov Model HMM is a generative model – each waveshape feature is generated by the cardiological state of the heart. HMM models have been already used for ECG signals. The ECG state sequence obeys Markov property – each state is solely dependent on previous state.

HMM Formalism An HMM  can be specified by 3 matrices {P, A, B}: oT o1 ot ot-1 ot+1 x1 xt+1 xT xt xt-1 An HMM  can be specified by 3 matrices {P, A, B}: P = {pi} are the initial state probabilities A = {aij} are the state transition probabilities = Pr(xj|xi) B = {bik} are the observation probabilities = Pr(ok|xi)

Generating a sequence by the model Given a HMM, we can generate a sequence of length n as follows: Start at state xi according to prob i Emit letter o1 according to prob bi(o1) Go to state xj according to prob aij … until emitting oT 1 2 N … 1 1 2 N … 1 2 K … … 1 2 N … 2 2 2 N b2o1 o1 o2 o3 oT

The three main questions on HMMs Evaluation GIVEN a HMM , and a sequence O, FIND Prob[ O |  ] Decoding FIND the sequence X of states that maximizes P[X | O,  ] 3. Learning GIVEN a sequence O, FIND a model  with parameters , A and B that maximize P[ O |  ]

Segmentation of ECG Using a Hidden Markov Model (L. Claveier et al.) Purpose: Segment ECG (12 parts); Detect accurately P-wave, recognize cardiac arrhythmias. Parameters: Amplitude; Slope.

Segmentation of ECG Using a Hidden Markov Model (Con.) Possible state jumps of the HMM Other jumps and states could be added to recognize various shapes of the P and T waves.

Segmentation of ECG Using a Hidden Markov Model (Con.) Automatic segmentation of an ECG beat. Automatic segmentation of a P-Wave

ECG segmentation using HSMM N. Hughes et al. (2003) used HMM in a supervised manner. Training signals were segmented and labeled by group of expert ECG analysts. Used raw data and wavelet encoding.

Segmentation using HSMM - results

Conclusions Homomorphic (or cepstral) analysis may provide parametric modeling of S1 & S2 and reduce significantly the dimension of the problem. Parametric\probabilistic modeling like HMM (or HSMM) may provide robust segmentation of irregular cardiac activity. It can make automatic classification easier.

Thank You !