• Mustafa Umut Etli, Muhammet Sinan Başarslan, Eyüp Varol, Hüseyin Sarıkaya, Yunus Emre Çakıcı, ÖndüçGonca GülGGDepartment of Neurosurgery, Ümraniye Training And Research Hospital, İstanbul, Turkey., Fatih Bal, Ali Erhan Kayalar, and Ömer Aykılıç.
• Department of Neurosurgery, Ümraniye Training And Research Hospital, İstanbul, Turkey. Electronic address: umutetli@gmail.com.
• World Neurosurg. 2024 Jul 1; 187: e807e813e807-e813.

ObjectiveMachine 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.MethodsData from Istanbul Ümraniye Training and Research Hospital, which included 15,600 digital imaging and communications in medicine images from 123 patients with aneurysmal SAH and 7793 images from 80 patients with nonaneurysmal SAH, were used. The study employed 4 models: Inception-V3, EfficientNetB4, single-layer CNN, and three-layer CNN. Transfer learning models were customized by modifying the last 3 layers and using the Adam optimizer. The models were trained on Google Collaboratory and evaluated based on metrics such as F-score, precision, recall, and accuracy.ResultsEfficientNetB4 demonstrated the highest accuracy (99.92%), with a better F-score (99.82%), recall (99.92%), and precision (99.90%) than the other methods. The single- and three-layer CNNs and the transfer learning models produced comparable results. No overfitting was observed, and robust models were developed.ConclusionsCNN-based transfer learning models can accurately diagnose the etiology of SAH from computed tomography images and is a valuable tool for clinicians. This approach could reduce the need for invasive procedures such as digital subtraction angiography, leading to more efficient medical resource utilization and improved patient outcomes.Copyright © 2024 Elsevier Inc. All rights reserved.

13 keywords...

hide…