Detection of abdominal aortic aneurysm from radiological images using artificial intelligence

Artificial intelligence has revolutionized the healthcare field with its growing importance in medical imaging. This thesis focuses on the effective use of artificial intelligence methods for detecting Abdominal Aortic Aneurysm (AAA). AAA is a critical condition that can lead to fatal outcomes if not diagnosed early. The primary hypothesis of the study is that AI-based analyses of radiological images can enable faster and more accurate detection of AAA. In the thesis, datasets derived from computed tomography (CT) scans were processed, and Convolutional Neural Network (CNN)-based deep learning models were applied. During the preprocessing phase, noise reduction, contrast enhancement, and feature extraction steps were performed. The trained models were evaluated for sensitivity, specificity, and accuracy during the training and testing phases. The findings revealed that the proposed AI models offered higher success rates compared to traditional methods. This study emphasizes the usability of AI technologies in radiological imaging and aims to contribute to the scientific knowledge in this field. Moreover, it has the potential to improve patient outcomes by saving time and reducing costs in medical diagnoses.