Adaptive Sojourn Time HSMM for Heart Sound Segmentation

@article{Oliveira2019AdaptiveST,
  title={Adaptive Sojourn Time HSMM for Heart Sound Segmentation},
  author={Jorge Oliveira and Francesco Renna and Theofrastos Mantadelis and Miguel Tavares Coimbra},
  journal={IEEE Journal of Biomedical and Health Informatics},
  year={2019},
  volume={23},
  pages={642-649}
}
Heart sounds are difficult to interpret due to events with very short temporal onset between them (tens of milliseconds) and dominant frequencies that are out of the human audible spectrum. Computer-assisted decision systems may help but they require robust signal processing algorithms. In this paper, we propose a new algorithm for heart sound segmentation using a hidden semi-Markov model. The proposed algorithm infers more suitable sojourn time parameters than those currently suggested by the… 

Figures and Tables from this paper

Heart Sound Segmentation Using Bidirectional LSTMs With Attention
TLDR
A novel framework for the segmentation of phonocardiogram signals into heart states is proposed, exploiting the temporal evolution of the PCG as well as considering the salient information that it provides for the detection of the heart state.
Automatic Recognition of Fundamental Heart Sound Segments From PCG Corrupted With Lung Sounds and Speech
TLDR
A combination of conventional signal processing technique with deep neural network (DNN) is proposed to enhance the accuracy of automated FHSS recognition compared to long short term memory (LSTM), and gated recurrent unit (GRU).
Temporal Convolutional Network Connected with an Anti-Arrhythmia Hidden Semi-Markov Model for Heart Sound Segmentation
TLDR
This study aimed to develop a real-time algorithm for HSS by combining the temporal convolutional network (TCN) and the hidden semi-Markov model (HSMM), and improve the performance of HSMM for heart sounds with arrhythmias.
Noise Robust Detection of Fundamental Heart Sound using Parametric Mixture Gaussian and Dynamic Programming
TLDR
An unsupervised algorithm to detect the heart sound candidates using the stationary wavelet transforms and group delay and an objective function to select the candidates is proposed.
The CirCor DigiScope Dataset: From Murmur Detection to Murmur Classification
TLDR
The currently largest pediatric heart sound dataset has been prepared, and for the first time, each cardiac murmur has been manually annotated by an expert annotator according to its timing, shape, pitch, grading, and quality.
Deep Convolutional Neural Networks for Heart Sound Segmentation
TLDR
The proposed methods are shown to outperform current state-of-the-art segmentation methods by achieving an average sensitivity of 93.9% and an average positive predictive value of 94% in detecting S1 and S2 sounds.
Automatic Segmentation and Classification of Heart Sounds Using Modified Empirical Wavelet Transform and Power Features
TLDR
The modified empirical wavelet transform (EWT) and the normalized Shannon average energy are used in pre-processing and automatic segmentation to identify the systolic and diastolic intervals in a heart sound recording.
Joint Training of Hidden Markov Model and Neural Network for Heart Sound Segmentation
TLDR
The proposed approach is based on the combination of two families of state-of-the-art solutions for such problem, hidden Markov models and deep neural networks, in a single training framework and it is shown to achieve an average sensitivity and positive predictive value.
A strong anti-noise segmentation algorithm based on variational mode decomposition and multi-wavelet for wearable heart sound acquisition system
TLDR
A segmentation algorithm based on Variational Mode Decomposition (VMD) and multi-wavelet that can achieve high-precision segmentation of the heart sound under a mixed noise condition is proposed.
A Review of Computer-Aided Heart Sound Detection Techniques
TLDR
The latest development of the computer-aided heart sound detection techniques over the last five years has been reviewed, hoping to provide reference to the prediction of cardiovascular diseases.
...
1
2
...

References

SHOWING 1-10 OF 21 REFERENCES
Logistic Regression-HSMM-Based Heart Sound Segmentation
TLDR
This paper addresses the problem of the accurate segmentation of the first and second heart sound within noisy real-world PCG recordings using an HSMM, extended with the use of logistic regression for emission probability estimation, and implements a modified Viterbi algorithm for decoding the most likely sequence of states.
Support vector machine hidden semi-Markov model-based heart sound segmentation
TLDR
This paper addresses the problem of the accurate segmentation of heart sounds within noisy, real-world PCGs using a HSMM, extended with the use of support vector machines (SVMs) for emission probability estimation.
Segmentation of heart sound recordings from an electronic stethoscope by a duration dependent Hidden-Markov Model
TLDR
The results suggest that the duration-dependent hidden Markov model could be a suitable method for segmentation of clinically recorded heart sounds.
Robust heart sound detection in respiratory sound using LRT with maximum a posteriori based online parameter adaptation.
An open access database for the evaluation of heart sound algorithms.
TLDR
A public heart sound database, assembled for an international competition, the PhysioNet/Computing in Cardiology (CinC) Challenge 2016, which comprises nine different heart sound databases sourced from multiple research groups around the world is described.
Classification of Continuous Heart Sound Signals Using the Ergodic Hidden Markov Model.
TLDR
This work proposes to use the ergodic HMM for the classification of the continuous heart sound signal, and performs successfully with an accuracy of about 99(%) requiring no segmentation information.
S1 and S2 Heart Sound Recognition Using Deep Neural Networks
TLDR
The proposed DNN-based method can achieve reliable S1 and S2 recognition performance based on acoustic characteristics without using an ECG reference or incorporating the assumptions of the individual durations of S2 and time intervals of S1–S2 and S1-S2–S1.
Classification of heart sounds using time-frequency method and artificial neural networks
TLDR
A time-frequency method known as the trimmed mean spectrogram (TMS) offers a promising methodology for classifying murmurs in pathological systolic murmurs.
A multi-spot exploration of the topological structures of the reconstructed phase-space for the detection of cardiac murmurs
TLDR
The experimental results show that fractal features are the most capable of describing the non-linear structure and the underlying dynamics of heart sounds among the all feature families tested.
...
1
2
3
...