Classification and Reconstruction of Biomedical Signals Based on Convolutional Neural Network
Zijiang Zhu1,2, Hang Chen3, Song Xie1
1School of Computer Science, South China Business College, Guangdong University of Foreign Studies, Guangzhou 510545, Guangdong, China.
Computational Intelligence and Neuroscience
|August 1, 2022
Summary
This study introduces deep learning methods using Convolutional Neural Networks (CNNs) for analyzing biomedical signals. The research achieved high accuracy in classifying breast masses from mammograms and analyzing electroencephalogram (EEG) signals.
Area of Science:
- Biomedical Engineering
- Medical Imaging
- Signal Processing
Background:
- Efficient biological signal processing is crucial for understanding life mechanisms and promoting biological discoveries.
- High-precision medical signal analysis aids clinical diagnosis, disease prevention, and treatment planning, reducing patient suffering.
Purpose of the Study:
- To develop and evaluate deep learning-based methods for classifying biomedical signals, specifically mammography and EEG signals.
- To enhance the accuracy and efficiency of analyzing complex medical data for improved diagnostic and research outcomes.
Main Methods:
- Proposed a multi-layer Convolutional Neural Network (CNN) for classifying breast masses in mammograms, incorporating a physician-like feature decision mechanism.
- Developed a spatiotemporal fusion CNN for electroencephalogram (EEG) signal classification, integrating spatial and temporal information processing.
Main Results:
- Achieved a highest classification accuracy of 97.0% for identifying benign and malignant breast masses using the proposed CNN method.
- Demonstrated the effectiveness of the spatiotemporal fusion CNN for EEG signal classification through comparative experiments, showing high accuracy and efficiency.
Conclusions:
- The developed CNN-based methods offer high accuracy and effectiveness for the classification and reconstruction of biomedical signals.
- These advanced signal processing strategies can significantly support researchers and clinicians in medical diagnosis and biological discovery.
Related Concept Videos
01:30Classification of Signals
820
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
820
01:10Reconstruction of Signal using Interpolation
315
Signal processing techniques are essential for accurately converting continuous signals to digital formats and vice versa. When a continuous signal is sampled with a period T, the resulting sampled signal exhibits replicas of the original spectrum in the frequency domain, spaced at intervals equal to the sampling frequency. To handle this sampled signal, a zero-order hold method can be applied, which creates a piecewise constant signal by retaining each sample's value until the next...
315
01:20Deconvolution
242
Deconvolution, also known as inverse filtering, is the process of extracting the impulse response from known input and output signals. This technique is vital in scenarios where the system's characteristics are unknown, and they must be inferred from the observable signals.
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
Deconvolution involves several mathematical techniques to derive the impulse response. One common approach is polynomial division. In this method, the input and output sequences are treated as coefficients of...
242
01:24Convolution: Math, Graphics, and Discrete Signals
368
In any LTI (Linear Time-Invariant) system, the convolution of two signals is denoted using a convolution operator, assuming all initial conditions are zero. The convolution integral can be divided into two parts: the zero-input or natural response and the zero-state or forced response, with t0 indicating the initial time.
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
To simplify the convolution integral, it is assumed that both the input signal and impulse response are zero for negative time values. The graphical convolution process...
368