ITM Web Conf.
Volume 53, 20232nd International Conference on Data Science and Intelligent Applications (ICDSIA-2023)
|Number of page(s)||14|
|Section||Machine Learning / Deep Learning|
|Published online||01 June 2023|
Classification and Detection of Brain Tumors by Aquila Optimizer Hybrid Deep Learning Based Latent Features with Extreme Learner
Greenwood High International School, Bangalore, 560087, India
* Corresponding author: email@example.com
Brain cancer is a potentially fatal illness that affects the brain. To preserve lives, early tumour detection is now crucial. Imaging in medicine is one method for diagnosing brain tumours. To help find brain tumours, researchers are turning to deep learning. Error in individual early diagnosis of the condition has been demonstrated to be reduced using deep learning algorithms. In the case of brain tumours, even a slight misdiagnosis might have serious consequences. When it comes to processing medical images, spotting brain tumours is still a difficult task. It’s difficult to spot the tumour on a brain scan. The precision of the image is impacted by many disturbances and a delay. We used deep learning methods to describe brain disorders in our paper. Brain disease detection utilizing deep learning methods is related to the study of new information. Proposed TL-based DenseNet121 model achieved accuracy, sensitivity, specificity, F1Score, precision, and IoU of 98.38, 97.33, 99.1, 98.23, 98.62, and 96.62 respectively. The results obtained on the brain tumor data set demonstrate that the proposed method outperforms others in terms of F1-score, Precision, Sensitivity, Accuracy, Specificity, and IoU.
© The Authors, published by EDP Sciences, 2023
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.