A risk prediction system for pulmonary nodules based on ss-elm

Abstract

The invention provides aSS-ELM based pulmonary nodule disease risk prediction system and method.The system includes a pulmonary nodule image processing unit, a gray level co-occurrence matrix structure unit, a Haralick feature parameter calculation unit, a Haralick feature set structure unit and a pulmonary nodule disease risk prediction unit. The method comprises the steps that a pulmonary nodule image with a label, a label-free pulmonary nodule image and a pulmonary nodule image to be diagnosed are obtained as target images; gray level processing is conducted on the target images; the target images undergoing the gray level processing generate gray levelco-occurrence matrixes in the four directions of 0 degree, 45 degrees, 90 degrees and 135 degrees respectively; Haralick feature parameters of the target images in the four directions of 0 degree, 45 degrees, 90 degrees and 135 degrees are determined; Haralick feature sets of the target images are determined; the risk probability that the nature of the pulmonary nodule image to be diagnosed shows malignant is obtained by utilizing an SS-ELM algorithm. The SS-ELM based pulmonary nodule disease risk prediction system can effectively improve the pulmonary nodule disease risk prediction performance.

Description

technical field [0001] The invention belongs to the technical field of computer-aided diagnosis, and in particular relates to an SS-ELM-based pulmonary nodule disease risk prediction system. Background technique [0002] At present, lung cancer has become the malignant tumor with the highest mortality rate, mainly because it is difficult to detect in the early stage and difficult to cure in the late stage. The early manifestation of lung cancer is pulmonary nodules. Early detection, early diagnosis and early treatment of pulmonary nodules are of great significance. Clinically, the most commonly used method for the diagnosis of pulmonary nodules is the imaging diagnosis method of computerized tomography (CT). However, with the development of CT imaging technology, more and more pulmonary nodules can be detected, and it is very difficult to find and diagnose pulmonary nodules only by the visual observation of radiologists. Therefore, the risk prediction system for pulmonary ...

AI Technical Summary

Problems solved by technology

The traditional benign and malignant pulmonary nodule classification carrier uses a supervised classification algorithm, which needs to learn the information contained in the labeled pulmonary nodule data, and classify the unlabeled data after obtaining the classification model, but it needs to obtain the labeled data. It is usually difficult to obtain a large amount of labeled data with a certain amount of manpower and material resources. However, with the rapid development of information technology, it is quite easy to collect a large amount of unlabeled data.

Images