Higher Diploma Research at the Northern Technical University Discusses an Intelligent System for Breast Tumor Classification Using Neural Networks

2026-02-15

IMG

The Administrative Technical College / Mosul held the discussion of a Higher Diploma research in Electronic Management Technologies, submitted by Omar Rifaat Hazem Ismail, entitled:
“A Proposed Method for Classifying Breast Tumors Using Neural Network Technology,” on Sunday, February 15, 2026.

The research aimed to design and develop an intelligent system for breast cancer classification using deep learning models and Transfer Learning techniques. The system analyzes ultrasound breast images and classifies them into three categories: normal, benign tumors, and malignant tumors.

The study was based on the BUSI Dataset, which includes 300 images equally distributed among the three categories. Several deep neural network models were implemented using the MATLAB environment, including:
AlexNet, DenseNet201, VGG16, ResNet18, and GoogLeNet.

The deep learning models demonstrated high performance in medical image classification. GoogLeNet achieved the highest classification accuracy and showed superior capability in distinguishing between different cases.

The findings confirm that deep learning models based on transfer learning provide an effective tool for supporting early diagnosis and reducing reliance on traditional diagnostic methods.

The study concluded by emphasizing the importance of integrating artificial intelligence technologies to support medical decision-making and enhance the efficiency of diagnostic systems in healthcare institutions.