Document Details
Document Type |
: |
Thesis |
Document Title |
: |
COMPUTER AIDED DIAGNOSIS SYSTEM FOR LUNG CANCER FROM COMPUTED TOMOGRAPHY IMAGE نظام تشخيص بمساعدة الحاسوب لسرطان الرئة من صور الأشعة المقطية |
Subject |
: |
Faculty of Engineering |
Document Language |
: |
Arabic |
Abstract |
: |
Saudi Arabia vision 2030 moving with achievable dreams with revolution of the lifestyle and industrial country with potential of increase the pollution and the smoking lifestyle came as innovation and industrial area lunch projects, in the other side the side effect on the healthcare could be increased especially in lung cancer, as per the previous study from world health organization the lung cancer is the most common diseases in the world as following 3rd incident worldwide and 1st incident for male in Saudi Arabia, and through our research we are developed the CAD system to follow the revolution from treatment to preventive action for the patient by pre-deduct the lung cancer with pulmonary nodules through CT Scan images using latest and useful features, starting from the database using the standard archiving organization -TCIA to be a stander references with select the region of interest - ROI 31x31 for each images took from CT scan - the computed tomography images, MATLAB software was the best program support us in this research to get perfect result during using the features extraction and selection methodology by sequential forward selection and backward selection followed by classification KNN, SVM with comparing the result from the previous research since 1997 till today with my proposed, with get all the result 100% accuracy, sensitivity, specificity, AUC/ROC, and 100% for true positive - TP and true negative - TN, 0% false positive -FP and false negative - FN, and we found the Gabor wavelet features is not useful for pulmonary nodules detection using CAD software, this is abstract the CAD development in lung cancer using CT scan images.
Key Wards: Lung Cancer, Computer Aided Diagnosis, features extraction, Features Selection, Classifiers, KNN, SVM, Naïve Bayes, Gabor Wavelet, Support Vector Machine, Nearest Neighbor, Computed Tomography, Pulmonary Nodules, LIDC. |
Supervisor |
: |
Dr. Omar Al Qasimi |
Thesis Type |
: |
Master Thesis |
Publishing Year |
: |
1442 AH
2020 AD |
Added Date |
: |
Saturday, September 12, 2020 |
|
Researchers
أحمد عبدالمجيد قشقري | Qashgari, Ahmed Abdulmajeed | Researcher | Master | |
|
Back To Researches Page
|