Year: 2025
Type: article
Abstract: ABSTRACT Early diagnosis and treatment of brain tumors depend on their identification and classification. Manual MRI interpretation is laborious and prone to mistakes. In order to categorize MRI scans into four groups glioma, meningioma, pituitary tumor, and no tumor this study employs a deep learning technique using the ResNet152V2 model. Compared to conventional CNNs, the model is more efficient in extracting important features. Its 96% accuracy with data augmentation provided a quick and dependable automated system. Transfer learning preserved good accuracy while cutting down on computational expense and training time. The system provides robustness, reduces human error, and may be incorporated into clinical processes to assist radiologists and enhance patient care results. It has been validated on benchmark datasets. Keywords : ResNet152v2, CNNs, tumor, Augmentation, Deep-learning
DOI: 10.55041/ijsrem52761
Authors: Poornima B H, Akshatha R, Basavanna M
Language: English
Subfield: Neurology
Field: Neuroscience
Domain: Life Sciences
Open Access status: bronze
OpenAlex ID: W4414508292