An Accurate Aneurysm Detection Model based on Artificial Intelligence

Abstract

Cerebral aneurysms are a major, life threatening cerebrovascular disease, and accurate interpretation of Computed Tomography Angiography (CTA) is critical for early diagnosis and treatment. This study evaluates the effectiveness of deep learning in reducing radiologist related interpretation errors by applying 15 different Convolutional Neural Networks (CNNs) to 1,211 CTA images. Prior to classification, images underwent various preprocessing and filtering operations, and comparative performance metrics were obtained. The best result, representing the highest accuracy reported to date of 99.72%, was achieved with a smoothing filtered image dataset using the VGG19 architecture. In the VGG19 test set, model outputs consisted of 272 true negatives (tn), 1 false negative (fn), 0 false positives (fp), and 90 true positives (tp). These findings demonstrate that appropriate image preprocessing and filtering significantly enhance CNN based aneurysm detection performance and play a crucial role in improving classification accuracy.