Using VGG16 Algorithms for classification of lung cancer in CT scans Image

TL;DR

This paper develops a VGG16-based deep learning model to classify lung nodules in CT scans, achieving high accuracy and sensitivity, aiding early lung cancer detection.

Contribution

The study applies VGG16 for lung nodule classification, demonstrating its effectiveness in distinguishing malignant, benign, and healthy cases with high accuracy.

Findings

92.08% sensitivity in nodule detection

91% overall classification accuracy

AUC of 93% for the model

Abstract

Lung cancer is the leading reason behind cancer-related deaths within the world. Early detection of lung nodules is vital for increasing the survival rate of cancer patients. Traditionally, physicians should manually identify the world suspected of getting carcinoma. When developing these detection systems, the arbitrariness of lung nodules' shape, size, and texture could be a challenge. Many studies showed the applied of computer vision algorithms to accurate diagnosis and classification of lung nodules. A deep learning algorithm called the VGG16 was developed during this paper to help medical professionals diagnose and classify carcinoma nodules. VGG16 can classify medical images of carcinoma in malignant, benign, and healthy patients. This paper showed that nodule detection using this single neural network had 92.08% sensitivity, 91% accuracy, and an AUC of 93%.