EUVIMEDEUVIMED entdecken
Crossref

Brain Tumour Classification: Methods, Technologies and a Comparative Review

Gururaj J.P

International Journal of Innovative Research in Computer and Communication Engineering · 06.08.2026 · 14 (07)

DOI: 10.15680/ijircce.2026.1407071 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Innovative Research in Computer and Communication Engineering, online erschienen am 06.08.2026. Verfasst von Gururaj J.P.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

One of the most dangerous neurological conditions is brain tumours, and patient survival and treatment planning are directly impacted by early and accurate diagnosis. The main non-invasive method for visualizing tumours is still magnetic resonance imaging (MRI), and computer-aided diagnosis (CAD) systems based on deep learning and machine learning have gradually automated the classification of meningioma, glioma, pituitary, and other tumour types. The main paradigms for brain tumour classification are compared in this review in an organized, mathematically grounded manner: (i) deep Convolutional Neural Networks (CNNs) and transfer-learning architectures such as VGG16/19, ResNet50, InceptionV3, Xception, DenseNet, MobileNet, and EfficientNet; (ii) classical machine learning pipelines that rely on handcrafted texture and statistical features such as the Gray-Level Co-occurrence Matrix (GLCM), Discrete Wavelet Transform (DWT), and Principal Component Analysis (PCA). (g). ResViT, UNetFormer, TECNN); and (iv) ensemble and hybrid approaches that combine learned and manually created features. The underlying mathematical formulation for each family of methods is derived and explained, and performance figures from recent literature are tabulated on widely used benchmark datasets (Figshare CE-MRI, BraTS, Kaggle Brain Tumour MRI Dataset, Br35H, and SARTAJ). A comparison of accuracy-complexity trade-offs, an overview of unresolved issues, and future directions like multimodal fusion, explainable AI, and quantum machine learning round out the review.

Zitieren

APA

J.P, G. (2026). Brain Tumour Classification: Methods, Technologies and a Comparative Review. International Journal of Innovative Research in Computer and Communication Engineering, 14(07). https://doi.org/10.15680/ijircce.2026.1407071

Vancouver

J.P G. Brain Tumour Classification: Methods, Technologies and a Comparative Review. International Journal of Innovative Research in Computer and Communication Engineering. 2026;14(07). doi:10.15680/ijircce.2026.1407071

BibTeX
@article{JP2026,
  author = {J.P, Gururaj},
  title = {Brain Tumour Classification: Methods, Technologies and a Comparative Review},
  journal = {International Journal of Innovative Research in Computer and Communication Engineering},
  year = {2026},
  volume = {14},
  number = {07},
  doi = {10.15680/ijircce.2026.1407071}
}
Kostenlos starten →