Comparative Analysis of Various CNN Models for Lung Cancer Prediction
This paper describe about the prediction of lung cancer disease. Lung cancer has the highest increasing rate with zero recovery. In this paper Deep learning deep neural networks are used. Which work as human and exactly imitates like them. Convolutional Neural Network (CNN) is used for forecast lung...
Saved in:
Published in | 2024 3rd International Conference for Innovation in Technology (INOCON) pp. 1 - 6 |
---|---|
Main Authors | , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
01.03.2024
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | This paper describe about the prediction of lung cancer disease. Lung cancer has the highest increasing rate with zero recovery. In this paper Deep learning deep neural networks are used. Which work as human and exactly imitates like them. Convolutional Neural Network (CNN) is used for forecast lung cancer, these algorithms of deep learning will increase the rate of recovery in patients by predicting the symptoms at the early stages. CNN works as human brain with different convolution layers or hidden layers to solve the problem. Lung cancer is a social as well as economic cause for the people who are unable to treat this disease due to lack of convenience of money. Due to the increase of this major diseases environment is also demolish in day to day life. Medical area of research is having advancement with deep learning and its different algorithms. In this paper chest X-ray will take two directories named as normal and pneumonia with three different stages like, test, train and validation (val) with two similar directories named as Normal and pneumonia. This paper uses Sequential, Vgg16, ResNet and InceptionNet models with different prediction values and also compare the difference of the models which works better in the area of lung cancer. ResNet model works better than all other models with 85% accuracy. |
---|---|
DOI: | 10.1109/INOCON60754.2024.10511872 |