Bi-clustering mining and AdaBoost-based tumor classification method

Abstract

The invention discloses a bi-clustering mining and AdaBoost-based tumor classification method. The method comprises the following steps of: firstly selecting digitalized scoring data of tumor lesion features to construct an original data set, screening features effective for distinguishing benign and malignant tumors from original features according to feature statistic information, mining important tumor diagnosis modes hidden behind the feature scoring data from the feature scoring data by utilizing a bi-clustering algorithm, and determining benign and malignant attributes of the diagnosis modes by adoption of support rate indexes according to benign and malignant priori knowledges, so as to convert locally consistent modes into effective diagnosis rules; constructing a simple weak classifier which is capable of carrying out classification in different feature spaces by adoption of a method of pairwise coupling benign and malignant rules, wherein the weak classifier takes similarity of matching between test samples and the benign and malignant rules as a classification rule; and finally training a high-correctness strong classifier from the weak classifier by adoption of an AdaBoost integration algorithm. The method plays an important role in improving the clinical diagnosis correctness of tumors.

Description

technical field [0001] The invention relates to the field of ultrasonic tumor identification and diagnosis, in particular to a tumor classification method based on double cluster mining and AdaBoost. Background technique [0002] As the primary cause of human death, tumors are a serious threat to human life and health, and have received extensive attention from the medical community. With the development of computer technology, many medical imaging techniques emerged as the times require, which were quickly accepted by doctors and patients and widely used clinically. The current main medical imaging techniques are: ultrasound imaging, magnetic resonance imaging, X-ray imaging. Compared with other imaging technologies, ultrasound imaging has the advantages of low cost, high cost performance, no radiation, fast and convenient, and less side effects on the human body. It has gradually been accepted by patients and doctors and has become the main imaging method for clinical app...

AI Technical Summary

Problems solved by technology

However, the limitations of this type of technical research are very obvious: first, the low-level features calculated by using image pixel grayscale and texture are used for classification, which is quite different from the high-level semantic features that doctors describe and judge tumors clinically; second, the algorithm It is too complicated and involves many links such as preprocessing, image filtering, image segmentation, lesion area recognition, texture feature extraction and analysis, training classifier, etc. If the output of any link is not ideal, it will affect the final diagnosis result

Images