Evaluating Deep Learning Techniques for Detecting Aneurysmal Subarachnoid Hemorrhage: A Comparative Analysis of Convolutional Neural Network and Transfer Learning Models.

Journal: World neurosurgery
Published Date:

Abstract

OBJECTIVE: Machine learning and deep learning techniques offer a promising multidisciplinary solution for subarachnoid hemorrhage (SAH) detection. The novel transfer learning approach mitigates the time constraints associated with the traditional techniques and demonstrates a superior performance. This study aims to evaluate the effectiveness of convolutional neural networks (CNNs) and CNN-based transfer learning models in differentiating between aneurysmal SAH and nonaneurysmal SAH.

Authors

  • Mustafa Umut Etli
    Department of Neurosurgery, Ümraniye Training And Research Hospital, İstanbul, Turkey. Electronic address: umutetli@gmail.com.
  • Muhammet Sinan Başarslan
    Department of Computer Engineering, Faculty of Engineering and Natural Sciences, İstanbul Medeniyet University, İstanbul, Turkey.
  • Eyüp Varol
    Department of Neurosurgery, Ümraniye Training And Research Hospital, İstanbul, Turkey.
  • Hüseyin Sarıkaya
    Department of Neurosurgery, Ümraniye Training And Research Hospital, İstanbul, Turkey.
  • Yunus Emre Çakıcı
    Department of Neurosurgery, Ümraniye Training And Research Hospital, İstanbul, Turkey.
  • Gonca Gül Öndüç
    Department of Neurosurgery, Ümraniye Training And Research Hospital, İstanbul, Turkey.
  • Fatih Bal
    Department of Software Engineering, Faculty of Engineering, Kırklareli University, Kırklareli, Turkey.
  • Ali Erhan Kayalar
    Department of Neurosurgery, Ümraniye Training And Research Hospital, İstanbul, Turkey.
  • Ömer Aykılıç
    Department of Computer Engineering, Faculty of Engineering and Natural Sciences, İstanbul Medeniyet University, İstanbul, Turkey.