Brain Tumor Segmentation Using Convolutional Neural Networks on MRI Images

Accurate and automatic segmentation of brain tumors in MRI images is a critical step for diagnosis, treatment planning, and monitoring of brain cancer. In this paper, we propose a deep learning-based approach using Convolutional Neural Networks (CNNs) for effective brain tumor segmentation. The model is trained and evaluated on publicly available MRI datasets, incorporating preprocessing steps such as normalization and data augmentation to enhance performance and generalization. The proposed CNN architecture captures spatial and contextual features, enabling precise delineation of tumor regions. Experimental results demonstrate high accuracy and robustness of the method compared to traditional segmentation techniques, confirming its potential for clinical application.

کلیدواژه ها:

Brain Tumor ، MRI ، Segmentation ، Convolutional Neural Networks ، Deep Learning