Medical image pulmonary nodule detection method based on a cyclic feature pyramid

Abstract

The invention discloses a medical image pulmonary nodule detection method based on a cyclic feature pyramid, and mainly solves the problem of low detection precision caused by high extraction difficulty of pulmonary nodules and ground glass nodules in the prior art. The method comprises the following implementation steps: 1) acquiring a medical image; 2) preprocessing the medical image, and expanding a sample data set; 3) constructing a circular feature pyramid detection model by combining the feature map; 4) training the detection model by using the extended data set sample to obtain a targetdetection model; and 5) inputting the test set in the data set into the trained detection model to carry out pulmonary nodule detection. The method constructs a new feature extraction network, accelerates the network training speed, enhances the sensitivity to nodules of different sizes, improves the detection precision of pulmonary nodules of medical images, and can be used for a computer-aidedmedical diagnosis system.

Description

technical field [0001] The invention belongs to the field of computer vision, in particular to a method for detecting pulmonary nodules in medical images, which can be used to identify medical images. Background technique [0002] According to the National Cancer Center, the incidence of lung cancer ranks second among cancers, and its early symptoms are mostly in the form of pulmonary nodules. Therefore, the detection and diagnosis of lung nodules is of great significance to save lung cancer patients. In recent years, with the deterioration of people's living environment and changes in living habits, the number of people with lung cancer has shown an increasing trend. At the same time, the high mortality rate of lung cancer has made the society pay more and more attention to it. The number of CT loaders in major hospitals in my country has increased significantly. Combined with the high-resolution CT images of the lungs they provide, the detection method based on the feature...

AI Technical Summary

Problems solved by technology

The common defect of these methods is that it needs to rely on the user's prior knowledge and a lot of attempts to determine the rules and select parameters, which increases the complexity of the classifier, easily causes over-fitting of the training, and leads to easy missed detection during the detection process. section, low detection accuracy

Images