The Master’s thesis defense of Mr. Raad Hamed Latif was held at the Department of Biomedical Engineering on Thursday, 10th July 2025. His thesis is titled:

“Automated Segmentation of Lung Lesions in Chest using Hybrid Approaches”

The examination committee consisted of:

• Chair: Prof. Dr. Sadiq Kamil Garkan – College of Electrical Engineering Technology / Middle Technical University

• Member: Asst. Prof. Dr. Aseel Mohammed Ali Hussein – College of Engineering / Al-Nahrain University

• Member: Lecturer Dr. Atheel Nawfal Mohammed Taher – College of Engineering / Al-Nahrain University

The thesis was supervised by:

• Asst. Prof. Dr. Ahmed Faeq Hussein – College of Engineering / Al-Nahrain University

The thesis was scientifically evaluated by:

• First scientific reviewer: Asst. Prof. Dr. Mohammed Sabah Jirjees – Northern Technical University / College of Engineering Technology – Mosul

• Second scientific reviewer: Asst. Prof. Dr. Israa Badr Nasser – College of Engineering / Al-Nahrain University

It was also linguistically reviewed by:

• Lecturer Dr. Samar Ali Jabir – College of Engineering / Al-Nahrain University

This study aims to develop a hybrid model for segmenting lung lesions in chest CT images using deep learning techniques alongside traditional methods.
The model combines conventional segmentation techniques with a modified SKICU-Net architecture, which incorporates attention mechanisms and selective kernel blocks to enhance segmentation accuracy.

The work also included the use of qualitative analysis tools such as Grad-CAM++, the Canny Edge Detection algorithm, and histogram analysis to visually evaluate segmentation quality.

The results demonstrated that the proposed model outperforms traditional and other deep learning models such as U-Net and VGG19 in terms of segmentation accuracy and various performance metrics including DSC, IoU, and F1-score.

The thesis was accepted as it fulfilled the requirements for obtaining the Master’s degree.