EUVIMEDEUVIMED entdecken
Crossref

ResNet-SVM: Fusion based glioblastoma tumor segmentation and classification

Hanene Sahli, Amine Ben Slama, Abderrazek Zeraii, Salam Labidi, Mounir Sayadi

Journal of X-Ray Science and Technology: Clinical Applications of Diagnosis and Therapeutics · 27.01.2023 · 31 (1) · 27-48

DOI: 10.3233/xst-221240 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of X-Ray Science and Technology: Clinical Applications of Diagnosis and Therapeutics, online erschienen am 20.10.2022. Verfasst von Hanene Sahli und 4 weiteren Autor:innen. Beteiligte Einrichtung: Laboratory of Signal Image and Energy Mastery, National Higher Engineering School of Tunis, University of Tunis, Tunis, Tunisia. Hauptthemen laut MEDLINE: Glioblastoma, Brain Neoplasms. Die Arbeit wurde bisher 12-mal zitiert (Crossref) und nennt 52 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Computerized segmentation of brain tumor based on magnetic resonance imaging (MRI) data presents an important challenging act in computer vision. In image segmentation, numerous studies have explored the feasibility and advantages of employing deep neural network methods to automatically detect and segment brain tumors depicting on MRI. For training the deeper neural network, the procedure usually requires extensive computational power and it is also very time-consuming due to the complexity and the gradient diffusion difficulty. In order to address and help solve this challenge, we in this study present an automatic approach for Glioblastoma brain tumor segmentation based on deep Residual Learning Network (ResNet) to get over the gradient problem of deep Convolutional Neural Networks (CNNs). Using the extra layers added to a deep neural network, ResNet algorithm can effectively improve the accuracy and the performance, which is useful in solving complex problems with a much rapid training process. An additional method is then proposed to fully automatically classify different brain tumor categories (necrosis, edema, and enhancing regions). Results confirm that the proposed fusion method (ResNet-SVM) has an increased classification results of accuracy (AC = 89.36%), specificity (SP = 92.52%) and precision (PR = 90.12%) using 260 MRI data for the training and 112 data used for testing and validation of Glioblastoma tumor cases. Compared to the state-of-the art methods, the proposed scheme provides a higher performance by identifying Glioblastoma tumor type.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

GlioblastomaBrain NeoplasmsHumansSupport Vector MachineImage Processing, Computer-AssistedNeural Networks, ComputerMagnetic Resonance Imaging

Stichwörter der Autor:innen

GlioblastomaMRI imagesResNetSVM classifiersegmentation

Autor:innen und Institutionen

  • Laboratory of Signal Image and Energy Mastery, National Higher Engineering School of Tunis, University of Tunis, Tunis, Tunisia.
  • Laboratory of Biophysics and Medical Technologies, Higher Institute of Medical Technologies of Tunis, University of Tunis El Manar, Tunis, Tunisia.

Zitieren

APA

Sahli, H., Ben Slama, A., Zeraii, A., Labidi, S., & Sayadi, M. (2023). ResNet-SVM: Fusion based glioblastoma tumor segmentation and classification. Journal of X-Ray Science and Technology: Clinical Applications of Diagnosis and Therapeutics, 31(1), 27-48. https://doi.org/10.3233/xst-221240

Vancouver

Sahli H, Ben Slama A, Zeraii A, Labidi S, Sayadi M. ResNet-SVM: Fusion based glioblastoma tumor segmentation and classification. Journal of X-Ray Science and Technology: Clinical Applications of Diagnosis and Therapeutics. 2023;31(1):27-48. doi:10.3233/xst-221240

BibTeX
@article{Sahli2023,
  author = {Sahli, Hanene and Ben Slama, Amine and Zeraii, Abderrazek and Labidi, Salam and Sayadi, Mounir},
  title = {ResNet-SVM: Fusion based glioblastoma tumor segmentation and classification},
  journal = {Journal of X-Ray Science and Technology: Clinical Applications of Diagnosis and Therapeutics},
  year = {2023},
  volume = {31},
  number = {1},
  pages = {27--48},
  doi = {10.3233/xst-221240}
}
Kostenlos starten →