Data processing method in intelligent lymph gland disease diagnostic system

Abstract

The invention discloses a data processing method in an intelligent lymph gland disease diagnostic system. The data processing method is characterized by comprising the following steps that (1) normalization processing is conducted on sample data so that the sample data can be in a preset section range, wherein the sample data comprise the M patient data and the N non-patient data; (2) characteristic selection is conduced on the normalized data based on the P-value algorithm; (3) the characteristics selected in the step (2) are further screened based on forward characteristic selection; (4) an LS-SVM training model is structured according to the characteristics screened out in the step (3); (5) normalization processing is conducted on test data according to the mode in the step (1), the characteristics screened out in the step (3) are selected and brought in the LS-SVM training model structured in the step (4) to conduct classified recognition, and classifying results are output. According to the data processing method, the characteristic dimensions of the data are few when the training model is structured, the diagnostic time is shortened, and meanwhile the accuracy of the diagnostic system is ensured.

Description

technical field [0001] The invention belongs to a data processing method based on classification and identification, more specifically, a data processing method in an intelligent diagnosis system for lymph node diseases. Background technique [0002] Lymph node disease is one of the diseases that affect human health. In lymph node disease, the harm of lymph node tumor is more obvious. Therefore, in order to select an appropriate treatment plan for patients, it is very important to accurately diagnose the lymph nodes and lymph node lesions of tumor patients. Due to the huge cost of biopsy at the site of lymph node resection and the invasive nature of this operation, it will cause many negative effects; therefore, early diagnosis is particularly important for lymphadenopathy. Recently, the artificial lymph node disease diagnosis method based on medical images has played an important role in the diagnosis of lymph node diseases. It uses non-invasive technology to evaluate the...

AI Technical Summary

Problems solved by technology

[0003] With the rapid development of artificial diagnosis methods for medical images, in order to be able to analyze and process increasingly complex medical images, the support vector machine method has become a research hotspot in artificial intelligence diagnosis in recent years. However, due to the many parameter characteristics of lymph node diseases, Directly use the training model of support vector machine for diagnosis and recognition, the data processing is complicated, the diagnosis time is long, and it is difficult to meet the clinical application

Images