Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Techno Nusa Mandiri : Journal of Computing and Information Technology

COMPARATIVE CLASSIFICATION OF LUNG X-RAY IMAGES WITH CONVOLUTIONAL NEURAL NETWORK, VGG16, DENSENET121 Muhammad Ilham Prasetya; Yuris Alkhalifi; Rifki Sadikin; Yan Rianto
Jurnal Techno Nusa Mandiri Vol 19 No 1 (2022): Techno Nusa Mandiri : Journal of Computing and Information Technology Period of
Publisher : Lembaga Penelitian dan Pengabdian Pada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/techno.v19i1.3010

Abstract

Lungs are one of the organs of the human body, and lung tissue will ultimately affect human abilities. The respiratory system exchanges oxygen and carbon dioxide in the blood. Problems that often occur are polluted air quality, many bacteria that attack the lungs, and lung disease can cause shortness of breath, mobility difficulties, and hypoxia, so that if not detected immediately it can cause death. In this regard, the aim of this study is to compare the classification of normal lungs with those of those suffering from Cardiomegaly. The preparation of this dataset is a form of contribution in improving the quality of the disease classification system on X-ray images. CNN, VGG 16 and DenseNet methods were chosen as classification methods to ensure performance and which method is the best for classifying Lung Diseases. It can be concluded that by using the DenseNet121 model, X-Ray images in this research dataset get an accuracy of 67.06%, for the VGG16 model it gets an accuracy of 68.94% and for the CNN model it gets the highest accuracy of 80.54%.