The College of Engineering, University of Baghdad, witnessed the public discussion of the master’s student (Walaa Jassim Fayyadh) from the Department of Computer Engineering. Her thesis was entitled “Detection and Classification of Skin Diseases Using Artificial Intelligence Techniques.”
On Monday, September 1, 2025, in the discussion hall of the Department of Computer Engineering, under the supervision of Assistant Professor Ahlam Hanoon Shanin.
The discussion committee consisted of the professors listed below:
Chair: Al-Mustansiriya University / College of Engineering / Department of Computer Engineering, Electrical Engineering / Intelligent Systems, Prof. Dr. Walaa Muhammad Hassan Khalaf
Member: University of Baghdad / College of Engineering / Department of Electrical Engineering, Electrical Engineering, Asst. M. Zainab Ibrahim Abood
Member: University of Baghdad / College of Engineering / Department of Computer Engineering, Computer Engineering / Software, Asst. M. Dr. Mohammed Sadoon Hathel.
This thesis aimed to build an intelligent system based on modern artificial intelligence techniques, combining preprocessing methods, feature extraction, and machine learning and deep learning algorithms, to improve the accuracy and efficiency of skin lesion detection and classification, and provide a reliable support tool for physicians in clinical diagnosis.
The thesis also included a comprehensive study covering the preprocessing stages of medical images, feature extraction using statistical and histological techniques (GLCM and LBP), and the application of machine learning algorithms (SVM, DT, RF), in addition to relying on the latest deep learning algorithms (YOLOv8) to accurately detect and classify skin lesions. The results demonstrated the high efficiency of the proposed system in terms of accuracy and reliability, confirming its potential for use in medical applications to assist physicians.
The thesis concluded with a set of recommendations, including:
- The need to expand the use of broader and more diverse databases to ensure the model’s ability to generalize.
- Integrating explainable artificial intelligence (XAI) techniques such as Grad-CAM and LIME to enhance transparency and confidence in clinical results.
- Conducting realistic clinical trials to verify the system’s effectiveness in a real-world medical setting, such as clinics or telemedicine systems.
After a scientific discussion by the members of the discussion committee, listening to the researcher’s defense, and evaluating the thesis, the researcher was awarded a master’s degree in computer engineering.
