Smart Brain Tumor Segmentation and Classification Using Inception ResNet‐V2 and Eagle Eye Vision in IoMT
Applied Computational Intelligence and Soft Computing · 2026-01 · 2026 (1)
DOI: 10.1155/acis/2622873 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Computational Intelligence and Soft Computing, online erschienen am 30.06.2026. Verfasst von A. Ashwini und 4 weiteren Autor:innen. Die Arbeit nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Brain tumors develop due to the unregulated proliferation of nerve tissues. Nonetheless, despite progress in deep learning models for medical image analysis, the precise segmentation of tumor patches and categorization of tumor types remain unresolved. This issue is worsened by the variability in tumor morphology, dimensions, and characteristics observed in MRI images. Identifying human brain tumors is a challenging issue in medical research. Current methodologies inadequately yield precise and distinct contours for classification, leading to unsatisfactory outcomes. Therefore, healthcare services are increasingly focusing on the internet of medical things (IoMT). This research introduces an Inception ResNet‐V2 (IR‐V2) utilizing the Online Eagle Eye Vision Region (OEEVR)–based segmentation to tackle these challenges. The suggested OEEVR method addresses these issues by utilizing real‐time automatic segmentation techniques to delineate tumor boundaries and transfer data through the IoMT for real‐time applications. The dual tasks of segmentation and classification were evaluated on the Kaggle Brain Tumor dataset with 7023 image scans, including pituitary, glioma, meningioma, and nontumor subtypes. The proposed methodologies exhibited an overall accuracy of 99.23%, sensitivity of 95.73%, precision of 93.98%, and F 1‐score of 94.92%. The IR‐V2 classification functions as a novel algorithm for brain tumor classification. Classification accuracies of 100%, 93.8%, 100%, and 100% were achieved for pituitary tumors, gliomas, meningiomas, and nontumors, respectively.
Zitieren
APA
Ashwini, A., Chirchi, E. R. M., Kumari, V. S., Senthilvel, P. G., & Ayalew, F. (2026). Smart Brain Tumor Segmentation and Classification Using Inception ResNet‐V2 and Eagle Eye Vision in IoMT. Applied Computational Intelligence and Soft Computing, 2026(1). https://doi.org/10.1155/acis/2622873
Vancouver
Ashwini A, Chirchi ERM, Kumari VS, Senthilvel PG, Ayalew F. Smart Brain Tumor Segmentation and Classification Using Inception ResNet‐V2 and Eagle Eye Vision in IoMT. Applied Computational Intelligence and Soft Computing. 2026;2026(1). doi:10.1155/acis/2622873
BibTeX
@article{Ashwini2026,
author = {Ashwini, A. and Chirchi, Emmanvel Raj M. and Kumari, V. Sheeja and Senthilvel, P. Gururama and Ayalew, Frie},
title = {Smart Brain Tumor Segmentation and Classification Using Inception ResNet‐V2 and Eagle Eye Vision in IoMT},
journal = {Applied Computational Intelligence and Soft Computing},
year = {2026},
volume = {2026},
number = {1},
doi = {10.1155/acis/2622873}
}
EUVIMED