Classification of Lung Cancer in Segmented CT Images Using Pre-Trained Deep Learning Models

Abstract

Many Diagnosis systems have been designed and used for diagnosing different types of cancer. Identification of carcinoma at an earlier stage is more important, and it is made possible due to the use of processing of medical images and deep learning techniques. Lung cancer is seen to develop often to be increased, and Computed Tomography (CT) scan images were utilized in the investigation to locate and classify lung cancer and also to determine the severity of cancer. This work is aimed at employing pre-trained deep neural networks for lung cancer classification. A Gaussian-based approach is used to segment CT scan images. This work exploits a transfer learning-based classification method for the chest CT images acquired from Cancer Image Archive and available in the Kaggle platform. The dataset includes lung CT images from the Cancer Image Archive for classifying lung cancer types. Pre-trained models such as VGG, RESNET, and INCEPTION were used to classify segmented chest CT images, and their performance was evaluated using different optimization algorithms.