Document Details

Document Type : Thesis 
Document Title :
CLASSIFICATION OF LUNGS IMAGES FOR DETECTING NODULES BY USING MACHINE LEARNING
تصنيف صور الرئتين لاكتشاف العقيدات الرئوية باستخدام تعليم الآلة
 
Subject : Faculty of Engineering 
Document Language : Arabic 
Abstract : Lung nodules are a common small masses of tissue located in the lungs. The nodule can be benign or malignant, Benign nodules are noncancerous while the Malignant nodules are cancerous and can grow so quickly. For a long time, X-ray images of the chest have been utilized to diagnose lung cancer. We developed a computer aid diagnosis system (CAD) to atomically classify a set of lung x-ray images into with nodule and no-nodule cases. 180 images were used in this work. The images are in full size, and no filtering or segmenting process were applied. 75 of the images are for normal cases while the other 105 are for abnormal cases, at the same time 120 of the images have been used to train the classifiers and 60 for testing. Our classifiers were fed with a variety of features, including LBP (local binary pattern) and statistical features. And a classifier was able to identify cases with nodule from cases without nodule with an accuracy (ACC) of 86.7%. 
Supervisor : Dr. UMAR ALQASEMI 
Thesis Type : Master Thesis 
Publishing Year : 1444 AH
2023 AD 
Added Date : Thursday, June 29, 2023 

Researchers

Researcher Name (Arabic)Researcher Name (English)Researcher TypeDr GradeEmail
حسين حمدانHamdan, Hussein ResearcherMaster 

Files

File NameTypeDescription
 49217.pdf pdf 

Back To Researches Page