Classification method and system based on imbalanced medical image data set

Abstract

The invention discloses a classification method and system based on an imbalanced medical image data set. The method comprises a step of extracting the green channel component of an original medical image, a step of using the histogram equalization to correct an extracted gray image, a step of extracting a texture feature, a wavelet feature and an auxiliary wheel feature from the corrected image, a step of ranking extracted feature samples according to a distance between the samples, a step of dividing uniform feature subsets on the ranked samples, and ensuring the difference between the subsets, a step of using an SVM algorithm and a BP neural network algorithm to train the feature subsets to produce sub classifiers, a step of combining the sub classifiers, and voting to obtain a final classification result. By using the technical scheme of the invention, the negative sample classification accuracy in multi-classification integrated learning is improved significantly, and the high skew of data set sample distribution and the negative sample accuracy in multi-classifier training in the medical field are improved obviously. The reduction of misdiagnosis is helped, and thus the practical value of the classifier is improved.

Description

technical field [0001] The invention belongs to the field of machine learning, and in particular relates to a classification method and system based on an unbalanced medical image data set. Background technique [0002] In many real-world machine learning classification tasks, the training data set of the classifier often has a highly uneven distribution problem, that is, the number of samples of some classes is much larger than that of other classes. Traditional learning algorithms often tend to misclassify the minority class into the majority class for the overall classification accuracy of the classifier. However, in many practical problems, the classification accuracy of the minority class is more important. Such as disease diagnosis, credit card fraud detection, network intrusion detection. For such classification problems, a common feature of data sets in the medical field is that the distribution of data set samples is highly skewed, and the number of positive sample...

AI Technical Summary

Problems solved by technology

[0011] Aiming at the unbalanced training set problem in integrated learning, the present invention provides a classification method and system based on unbalanced medical image datasets

Images