1. Image classification of brain tumors using deep learning.
- Author
-
Jagtap, Shivani, Bhoyar, Dinesh. B., Mohod, Swati, Khobragade, Rajesh, Umate, Roshan, and Patil, Arvind Bhagat
- Subjects
- *
CANCER diagnosis , *IMAGE recognition (Computer vision) , *MAGNETIC resonance imaging , *BRAIN tumors , *BENIGN tumors - Abstract
Brain tumor classification plays an important role in disease progression analysis and monitoring. Magnetic resonance imaging (MRI) is a widely used method for detecting brain tumors. Following the MRI, qualified experts perform a physical examination of the MRI filters to ascertain the presence of brain tumors in patients. This process is crucial in the accurate diagnosis of brain tumors and plays a key role in the effective treatment of patients. The interpretation of MRI scans by specialists may yield divergent results as a consequence of the application of distinct formulae for evaluation. It is pertinent to note that identifying a tumor alone does not suffice, as a comprehensive assessment of the scan is essential for accurate diagnosis and treatment planning. To ensure prompt treatment, identifying the tumor type is crucial. The current research proposes a machine learning-based approach to accurately classify brain tumors and determine their malignancy status. The objective of this study is to improve the diagnosis and treatment of brain tumors by using a robust classifier that can effectively differentiate between benign and malignant tumors. The proposed method utilizes a variety of features extracted from magnetic resonance images to train and optimize the performance of the classifier. If successful, this method has the potential to provide an accurate and reliable diagnosis of brain tumors, leading to better patient outcomes. To improve the speed, objectivity, and reliability of tumor detection, we evaluated the effectiveness of various deep-learning models. we used a dataset of images for training 187092 and for testing 45183. [ABSTRACT FROM AUTHOR]
- Published
- 2025
- Full Text
- View/download PDF