Detection, segmentation and classification of heart sounds

1
Detection, segmentation and classification of
heart sounds

• Daniel Gill
• Advanced Research Seminar
• May 2004

2
Automatic Cardiac Signals Analysis

• Problems
• Pre-processing and noise treatment.
• Detection\segmentation problem.
• Classification problem
• Feature extraction waveshape temporal
  information.
• The classifier.

3
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

4
Heart beat, why do you miss when my baby kisses
me ?
B. Holly (1957)
5
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.

6
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.

7
Segmentation Using Envelogram (S. Liang et al.
1997)

• Use Shannon energy to emphasize the medium
  intensity signal.
• Shannon Energy E-x2log(x2)

8
Segmentation Using Envelogram

• The Shannon energy eliminates the effect of
  noise.
• Use threshold to pick up the peaks.

9
Segmentation Using Envelogram

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

10
Segmentation Using Envelogram

• Identify S1 and S2 according the intervals
  between adjacent peaks.

11
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

12
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.

13
Segmentation Using Wavelet Decomposition and
Reconstruction
14
AR modeling of PCG (Iwata et al. 1977, 1980)

• AR model
• Used narrow sliding windows (25ms) to compute 8th
  order AR model.
• Features used dominant poles (below 80Hz) and
  bandwidth.
• Detected S1, S2 and murmurs.

15
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.

16
Suggested Methods

• Waveshape analysis Homomorphic Filtering.
• Temporal Model (Semi) Hidden Markov Models.

17
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

18

• 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

19
AM envelopes

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

20
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.

21

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

22

• 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.

23
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

24
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.

25
Normal heart beat with the labels found
26
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 ?)

27
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.

28
HMM Formalism

• 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(xjxi)
• B bik are the observation probabilities
  Pr(okxi)

29
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
2
2
0
N
b2o1
o1
o2
o3
oT
30
The three main questions on HMMs

• Evaluation
• GIVEN a HMM ?, and a sequence O,
• FIND Prob O ?
• Decoding
• GIVEN a HMM ?, and a sequence O,
• FIND the sequence X of states that maximizes
  PX O, ?
• 3. Learning
• GIVEN a sequence O,
• FIND a model ? with parameters ?, A and B
  that
• maximize P O ?

31
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.

32
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.

33
Segmentation of ECG Using a Hidden Markov Model
(Con.)

• Automatic segmentation of an ECG beat.
• Automatic segmentation of a P-Wave

34
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.

35
Segmentation using HSMM - results
36
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.

37

• Thank You !