EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-SA 4.0

Scalable and Efficient Multi-Class Brain Tumor Classification with a Compact Hybrid Deep Learning Model for Real-Time Applications

Sohaib R. Awad, Amar I. Daood, Akram A. Dawood

ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY · 03.05.2025 · 13 (1) · 162-174

DOI: 10.14500/aro.12017 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY, online erschienen am 03.05.2025. Verfasst von Sohaib R. Awad und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-SA 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Medical diagnostics require brain tumor classification to operate in real-time so the task demands accurate results with efficientprocessing abilities. A new hybrid deep learning solution merges convolutional neural networks (CNNs) with support vector machines(SVMs) to improve classification results as this paper describes. A total of four tumor categories including glioma, meningioma, andpituitary tumors together with no tumor appearance contribute to the magnetic resonance imaging (MRI) dataset are used for analysis. We applied and organized three pre-trained deep learning models: Alex-Net, DarkNet-19, and ResNet-50 for comparison. Anewly engineered compact CNN model linked with an SVM classifier brought decreased model dimensions while keeping excellent accuracy rates. Aproposed compact CNN model delivers 97.50% accuracy through its smaller 2.38 MB size and an additional SVM integration results in 97.45% accuracy using 1.43 MB. A Graphical User Interface (GUI) system comprising automated tumor classification capabilities is created to improve real-time systems that visualize MRI scans and illustrate predicted labels in addition to displaying confidence scores. A GUI enables smooth access to the trained model while being suitable for medical practice mobile healthcare environments and edge computing needs. The proposed system shows that lightweight architectures work excellently in real-time system applications especially when used for edge computing and mobile healthcare frameworks. The proposed solution demonstrates superiority over established models through its ability to scale efficiently.

Zitieren

APA

Awad, S. R., Daood, A. I., & Dawood, A. A. (2025). Scalable and Efficient Multi-Class Brain Tumor Classification with a Compact Hybrid Deep Learning Model for Real-Time Applications. ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY, 13(1), 162-174. https://doi.org/10.14500/aro.12017

Vancouver

Awad SR, Daood AI, Dawood AA. Scalable and Efficient Multi-Class Brain Tumor Classification with a Compact Hybrid Deep Learning Model for Real-Time Applications. ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY. 2025;13(1):162-174. doi:10.14500/aro.12017

BibTeX
@article{Awad2025,
  author = {Awad, Sohaib R. and Daood, Amar I. and Dawood, Akram A.},
  title = {Scalable and Efficient Multi-Class Brain Tumor Classification with a Compact Hybrid Deep Learning Model for Real-Time Applications},
  journal = {ARO-THE SCIENTIFIC JOURNAL OF KOYA UNIVERSITY},
  year = {2025},
  volume = {13},
  number = {1},
  pages = {162--174},
  doi = {10.14500/aro.12017}
}
Kostenlos starten →