Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{190885,
        author = {Arshiya Lubna and Dr. Hasan Hussain Shahul Hameed},
        title = {Early brain tumor classification and segmentation through the use of deep reinforcement learning and deep learning techniques},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {8},
        pages = {5548-5554},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=190885},
        abstract = {Recent research publications from 2020 to 2023 have primarily focused on the before time identification and categorization of brain tumors, a critical concern for both adults and children due to their high level of danger. The predominant approach involves a amalgamation of transfer learning, DL, and supervised ML algorithms. Notably, deep reinforcement learning, semi-supervised learning, and generative adversarial networks have not been featured in these studies. Researchers have widely employed data augmentation techniques to enhance the volume of available data. The studies have relied on FLAIR, BraTS, and custom datasets. Segmentation techniques have encompassed K-means, CNN, HAAR Discrete Wavelet Transformer (DWT), and Otsu's watershed algorithms to refine the identification process.},
        keywords = {brain tumors, adults and children, Reinforcement Learning, Semi-supervised learning, generative AI.},
        month = {January},
        }