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{158763,
        author = {Sanjana Joshi and Aditi Ravi and Aishwarya D K and Ruth Sandra J and Pathanjali C},
        title = {A Retrospective Study on Brain Tumor Image Generation using various GAN Architectures},
        journal = {International Journal of Innovative Research in Technology},
        year = {},
        volume = {9},
        number = {10},
        pages = {673-679},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=158763},
        abstract = {Brain tumors can have a lethal impact on humans. An estimate of 24,000 people lose their lives per year due to this abnormality. Several research papers were studied to gather valuable insights on the working of multiple combinations of GAN frameworks, which yielded a deeper understanding of the mechanism. U-Net architecture is one of the most commonly implemented frameworks of CNN particularly for medical images. Different approaches of testing on datasets were carried out to yield the respective results. This research is a cumulative study of various techniques on GAN models.},
        keywords = {Generative adversarial networks, Generator, Discriminator, Brain Tumor.},
        month = {},
        }