z-logo
open-access-imgOpen Access
Detection of Lung Cancer from MRI Scan Images Using Image Processing Techniques
Author(s) -
Pushpalatha S. Nikkam
Publication year - 2021
Publication title -
international journal for research in applied science and engineering technology
Language(s) - English
Resource type - Journals
ISSN - 2321-9653
DOI - 10.22214/ijraset.2021.36638
Subject(s) - artificial intelligence , computer science , image processing , preprocessor , grayscale , computer vision , convolutional neural network , pattern recognition (psychology) , feature extraction , digital image processing , binary image , image segmentation , median filter , artificial neural network , segmentation , image (mathematics)
Lung cancer is one of the causes of death. Early detection of lung cancer can save the life of a patient. The detection is done by many different techniques i.e, image processing, Computer-Aided Design, etc. Digital image processing is the latest emerging tool in the medical field where researchers used for the early detection of cancer. Magnetic resonance imaging(MRI stands) of the lungs of the patient from the lung image database is used as input data for image preprocessing. In preprocessing stage conversion of the RGB image to the grayscale image takes place. Grayscale images are further converted to binary images. After image-processing, the input images become more efficient and refined. These input images are used for the convolution neural network. Convolution filtering, Max pooling filtering steps are been in CNN which will train the dataset to predict whether lung image is cancerous (Malignant) or Non-cancerous(Benign).In this paper image processing procedures such as image preprocessing, segmentation feature extraction have been implemented for different algorithms such as Support Vector Machine, K- Nearest Neighbour, Convolution Neural Network, Artificial Neural Network using the image and the CSV files with the result of 100%, 66%, 97.70%, and 83% respectively.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.
Having issues? You can contact us here