A Cell Classification Method Based on EMD Feature Extraction and Sparse Representation

Abstract

A cell classification method based on EMD feature extraction and sparse representation, this method adopts an EMD-based cell feature extraction method. Firstly, the orthogonal subspace projection (OSP) method is used to select the bands of medical hyperspectral images, reduce the dimensionality, and reduce data redundancy. Then use the two-dimensional EMD method to perform feature extraction on the data after dimensionality reduction, and decompose the data into a series of IMF components arranged from high to low in frequency. The sparse representation-based classifier SRC is used to classify the data, and the samples are classified by comparing the residuals. The smaller the calculated residuals, the samples are classified into this category. In the cell classification method based on EMD feature extraction and sparse representation, EMD shows good time-frequency characteristics, and has obvious potential and advantages in feature extraction of hyperspectral data. At the same time, the classifier SRC based on sparse representation is used to ensure the classification accuracy to a greater extent.

Description

technical field [0001] The invention relates to an EMD (empirical mode decomposition)-based cell feature extraction method, which is classified and identified by a sparse representation classification method, and belongs to the field of medical hyperspectral classification and identification. Background technique [0002] The traditional medical detection method is a series of chemical analysis methods, staining the tissue sections, the experimental process is complicated, the cycle is long, the speed is slow, the intensity is large, the error is large, and the repeatability of the measurement is poor. The identification of cancer cells is realized through human eye observation. Affected by the subjectivity of the experimenter, it is easy to cause misdiagnosis. With the development of imaging technology, medical diagnosis is increasingly dependent on imaging technology. Imaging modalities include magnetic resonance imaging (MRI), computed tomography (CT), sonography, nuclea...

AI Technical Summary

Problems solved by technology

In traditional medical treatment, doctors use the naked eye to observe the shape of lesion areas on medical images, and many medical images are generated every day, which is time-consuming and has low accuracy.

Images