Higher Diploma Research at the Northern Technical University Discusses an Intelligent System for MRI Image Classification Using Artificial Intelligence

The Administrative Technical College / Mosul held the discussion of a Higher Diploma research submitted by Wurood Hadi Ahmid, entitled:
“A Method for Classifying MRI Images of Brain Atrophy Using Artificial Intelligence Techniques – Support Vector Machine (SVM) Model,”
which took place at Al-Hikma Hall at 9:00 a.m. on Tuesday, January 20, 2026.

The research presents an intelligent system for classifying brain tumors from Magnetic Resonance Imaging (MRI) images using machine learning algorithms. The system was designed from the outset as a digital medical data management platform that supports digital transformation in hospitals, aiming to improve diagnostic accuracy, support clinical decision-making, and manage the medical data lifecycle in accordance with best practices.

The study aimed to develop a classification system that enhances the traditional medical diagnostic process by strengthening physicians’ ability to detect brain tumors and accurately identify case types. This contributes to faster diagnosis and timely initiation of treatment. The methodology involved several stages, including data collection, preprocessing, feature extraction, training and testing machine learning algorithms, and performance evaluation.

Key Findings:

• Three machine learning algorithms were employed:
  K-Nearest Neighbors (KNN),
  Support Vector Machine (SVM), and
  Neural Network (NN).

• The KNN algorithm achieved the highest classification accuracy at 94.26%,
  followed by NN with 92.62%,
  while SVM recorded an accuracy of 91.53%.

• The results demonstrate that combining accurate modeling with data governance enhances classification reliability, accelerates clinical decision-making, and improves integration with health information systems within a secure, standards-compliant environment.

The study recommends expanding the dataset to include multi-center medical data, incorporating model interpretability metrics, and linking clinical performance indicators to analytical dashboards. These steps would further support digital medical data management initiatives and promote the practical adoption of the system in hospital settings.

Discussion Committee:

1. Prof. Dr. Nibal Younis Mohammed — Chair

2. Asst. Prof. Dr. Harith Akram Hamdoon — Member

3. Asst. Prof. Dr. Ahmed Sabeeh Yousif — Member & Supervisor