Histopathology of lung cancer classification using convolutional neural network with gamma correction

Wahyudi Setiawan, Muhammad Mushlih Suhadi, Husni -, Yoga Dwitya Pramudita

Abstract


Lung cancer is a degenerative disease that causes the growth of abnormal tissue to become autonomous and malignant. There are two types of lung cancer: adenocarcinoma and squamous cell carcinoma. Both types of cancer can be examined with varied techniques, one of them is histopathological examination. This examination is performed by expert analysts who can distinguish normal tissue from others. Manual inspection requires a long observation time and energy, therefore a computer-based classification system is created. In this study, Convolutional Neural Network (CNN) with gamma correction was implemented. Gamma correction is a process to adjust the image light, while CNN is for feature extraction and classification. The CNN built consists of one gamma correction layer, three convolution layers, three max-pooling layers, and two fully connected layers. The data consists of 3,000 images from the public dataset Lc25000. It has a normal and two lung cancer classes i.e adenocarcinoma and squamous cell carcinoma. In this study, we used gamma values ​​of 0.8, 1.0, and 1.2. The testing was carried out using five-fold cross-validation. It obtained the highest accuracy of 87.16% with a gamma value of 1.2.

Full Text: PDF

Published: 2022-08-22

How to Cite this Article:

Wahyudi Setiawan, Muhammad Mushlih Suhadi, Husni -, Yoga Dwitya Pramudita, Histopathology of lung cancer classification using convolutional neural network with gamma correction, Commun. Math. Biol. Neurosci., 2022 (2022), Article ID 81

Copyright © 2022 Wahyudi Setiawan, Muhammad Mushlih Suhadi, Husni -, Yoga Dwitya Pramudita. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Commun. Math. Biol. Neurosci.

ISSN 2052-2541

Editorial Office: office@scik.org

 

Copyright ©2023 CMBN