We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
2D ENCODING CONVOLUTION NEURAL NETWORK ALGORITHM FOR BRAIN TUMOR PREDICTION.
- Authors
Paulin, F.; Lakshmi, P.
- Abstract
In contemporary times, biomedical imaging plays a pivotal role in addressing various patient-related concerns. It serves as a vital tool for enhancing the diagnosis and treatment of a wide array of medical conditions. Within the realm of medical image analysis, the examination of brain images takes precedence. Brain imaging, particularly through techniques like MRI, offers valuable insights crucial for surgical procedures, radiotherapy, treatment planning, and stereotactic neurosurgery. To facilitate the accurate identification of concerous cells within the brain using MRI, deep learning and image classification techniques have been deployed. These technologies have paved the way for the development of automated tumor detection methods, which not only save valuable time for radiologists but also consistently deliver proven levels of accuracy. In contrast, the conventional approach to defect detection in magnetic resonance brain images relies on manual human inspection, a method rendered impractical due to the sheer volume of data This paper outlines an approach aimed at detecting and classifying brain tumors within patient MRI images. Additionally, it conducts a performance comparison of Convolutional Neural Network (CNN) models in this context.
- Subjects
CONVOLUTIONAL neural networks; BRAIN tumor diagnosis; BRAIN imaging; DEEP learning; MAGNETIC resonance imaging
- Publication
Mapana Journal of Sciences, 2023, Vol 22, p1
- ISSN
0975-3303
- Publication type
Article
- DOI
10.12723/mjs.sp2.1