Auxiliary Diagnosis of Benign and Malignant Pulmonary Nodules Based on Convolutional Neural Network

Abstract

With the development of PET/CT technology, more and more patients begin to choose PET/CT examination. The amount of image data of lung scans is very huge. The number of scanned images of a single patient can reach dozens or even hundreds of layers, which brings a huge workload to imaging workers, thereby increasing the probability of missed diagnosis and misdiagnosis. As a result, the early screening of lung cancer is very difficult. This paper applies this technology to the auxiliary diagnosis of benign and malignant lung nodules, using convolutional neural networks and support vector machines, etc., to propose an intelligent diagnosis model for the CT image characteristics of lung nodules.