Abstract

The Identification of lung malignant cells at premature stage remain as remarkable research area for researchers. Lung nodules are account as a normal reason for death in people all over the world. Identification of lung nodules at the initial stage can build the pace of endurance of patients. In this article computed tomography (CT) scan images as input to classify lung malignant cells of non-small cell lung cancer and categories according to subtypes of cancer by using the image processing technique with a convolutional neural network (CNN). The segmentation of the CT scan is performed to simplify the representation for meaningful and easier analysis. The feature extraction technique is used which is independent from the size and rotation of the image. These extracted features will use as an input to convolutional neural network (CNN), it pass through different layer of neural network at the end output layer classifies the affected and non-affected areas of the lung nodule with respect to subtypes (adenocarcinoma, squamous cell carcinoma, and large cell carcinoma). The deep learning algorithms VGG 16 show accuracy 85.01% while another deep learning algorithms VGG 19 show best accuracy 98.74% to correctly classify the nodules and subtypes.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call