ABSTRACT

Lung cancer is among the most fatal disease in developed countries, and early diagnosis of the disease is difficult. Lung cancer diagnosis and treatment has been one of the most daunting challenges humans have encountered in recent decades. Early tumor diagnosis will continue to save a vast amount of lives around the world on a daily basis. This paper describes a method for classifying lung tumors as malignant or benign that combines a Convolutional Neural Network (CNN) with the AlexNet Network Model. AlexNet CNN is one of the transfer learning models. As compared to accuracy achieved by conventional neural network systems, the proposed CNN achieves a high degree of accuracy, which is more effective.

PROPOSED METHODOLOGY

The proposed study uses AlexNet-CNN to classify lung cancer from CT images.

•  Extract the green channel from the original colour CT image in the first stage. It aids us in making more informed choices.
  The second step is to extract lung regions from a CT image using a multilevel thresholding process.
•  Third, the affected and non-affected regions are separated using the Thresholding and Morphological segmentation methods.
•  Finally, the segmented tumor regions are fed into the AlexNet-CNN architecture, which classifies the tumor as malignant or benign. The AlexNet CNN model combines feature extraction and classification in one model.

Software Requirements:

Front End – Anaconda IDE

Backend – SQL

Language – Python 3.8

Hardware Requirements:

•Hard Disk: Greater than 500 GB

•RAM: Greater than 4 GB

•Processor: I3 and Above