Deep Neural Network Paradigms for Improved Brain Tumor Diagnosis in Magnetic Resonance Imaging
- DOI
- 10.2991/978-94-6463-716-8_15How to use a DOI?
- Keywords
- Medical Imaging; Convolutional Neural Networks (CNNs); Transformer-Based Models; Vision Transformers (ViTs); Hybrid Architectures; Generative Adversarial Networks (GANs); U-Net
- Abstract
This paper aims at discussing the roles of accurate and efficient diagnosis of brain tumors in enhancing patient diagnostic results and treatment plans. Magnetic Resonance Imaging (MRI) plays a significant role in the diagnosis of brain tumors because of high-resolution imaging of the brain region. But manual evaluation of MRI scans is a very time consuming and lacks reproducibility. Advanced architectures have come up as revolutionary solutions which involve deep neural network paradigms which improve diagnosis of tumor. Establishing the foundation of deep learning methods applied to segments, classify, or detect brain tumors, this paper covers a number of approaches: Convolution Neural Networks (CNNs); Transformer-based; CNN + Transformer; and generative. Certain tasks include spatial complexity, data deficiency, and noisy imaging conditions that U-Net, Vision Transformers, and GANs solve, provide high accuracy and efficiency. Furthermore, techniques, such as self-supervised and transfer learning enhance model generalization, even with limited amounts of data. This paper builds upon the last decade of developments in the deep neural network paradigms and demonstrates how they might transform the brain tumor diagnosis. These results suggest that further work should be done to build accurate, explainable, and clinically augmented models to make substantial contributions to realize precise medicine and medical imaging.
- Copyright
- © 2025 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - Mohammad Shahnawaz Shaikh AU - Aparajita Biswal AU - Neelam Agrawal AU - Nilesh Khodifad AU - Bhavesh Atul Bhai Vaghela PY - 2025 DA - 2025/05/26 TI - Deep Neural Network Paradigms for Improved Brain Tumor Diagnosis in Magnetic Resonance Imaging BT - Proceedings of the International Conference on Recent Advancements and Modernisations in Sustainable Intelligent Technologies and Applications (RAMSITA 2025) PB - Atlantis Press SP - 173 EP - 188 SN - 1951-6851 UR - https://doi.org/10.2991/978-94-6463-716-8_15 DO - 10.2991/978-94-6463-716-8_15 ID - Shaikh2025 ER -