Brain tumors recognition based on deep learning
Brain tumors are fatal diseases that require proper treatment, making accurate and timely diagnosis critical for successful treatment. Deep learning (DL) has emerged as a powerful tool for improving the accuracy of brain tumor recognition and underscores the importance of optimizing training paramet...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-06-01
|
| Series: | e-Prime: Advances in Electrical Engineering, Electronics and Energy |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2772671124000822 |
| _version_ | 1797256278246948864 |
|---|---|
| author | Mohammed H. Al-Jammas Emad A. Al-Sabawi Ayshaa Mohannad Yassin Aya Hassan Abdulrazzaq |
| author_facet | Mohammed H. Al-Jammas Emad A. Al-Sabawi Ayshaa Mohannad Yassin Aya Hassan Abdulrazzaq |
| author_sort | Mohammed H. Al-Jammas |
| collection | DOAJ |
| description | Brain tumors are fatal diseases that require proper treatment, making accurate and timely diagnosis critical for successful treatment. Deep learning (DL) has emerged as a powerful tool for improving the accuracy of brain tumor recognition and underscores the importance of optimizing training parameters and dataset size. These findings demonstrate the feasibility of using DL for accurate and efficient brain tumor recognition, which has significant implications for improving patient outcomes. Accurate and timely diagnosis can greatly improve treatment outcomes and potentially save lives. This paper investigated the impact of DL on brain tumor recognition by utilizing a convolution neural network (CNN) algorithm and Magnetic Resonance Imaging (MRI) dataset of 4000 samples, each with a size of (224×224). The results show that increasing the dataset size led to better performance, with increasing accuracy and generalization of the model. Furthermore, increasing the number of epochs during training improves the accuracy; with 60 epochs as our choice for the DL model, we achieved 97.28℅ accuracy. |
| first_indexed | 2024-04-24T22:19:12Z |
| format | Article |
| id | doaj.art-745e011228d94a0eb66a129a3a75e9e6 |
| institution | Directory Open Access Journal |
| issn | 2772-6711 |
| language | English |
| last_indexed | 2024-04-24T22:19:12Z |
| publishDate | 2024-06-01 |
| publisher | Elsevier |
| record_format | Article |
| series | e-Prime: Advances in Electrical Engineering, Electronics and Energy |
| spelling | doaj.art-745e011228d94a0eb66a129a3a75e9e62024-03-20T06:12:06ZengElseviere-Prime: Advances in Electrical Engineering, Electronics and Energy2772-67112024-06-018100500Brain tumors recognition based on deep learningMohammed H. Al-Jammas0Emad A. Al-Sabawi1Ayshaa Mohannad Yassin2Aya Hassan Abdulrazzaq3Corresponding author.; Ninevah University, Mosul, IraqNinevah University, Mosul, IraqNinevah University, Mosul, IraqNinevah University, Mosul, IraqBrain tumors are fatal diseases that require proper treatment, making accurate and timely diagnosis critical for successful treatment. Deep learning (DL) has emerged as a powerful tool for improving the accuracy of brain tumor recognition and underscores the importance of optimizing training parameters and dataset size. These findings demonstrate the feasibility of using DL for accurate and efficient brain tumor recognition, which has significant implications for improving patient outcomes. Accurate and timely diagnosis can greatly improve treatment outcomes and potentially save lives. This paper investigated the impact of DL on brain tumor recognition by utilizing a convolution neural network (CNN) algorithm and Magnetic Resonance Imaging (MRI) dataset of 4000 samples, each with a size of (224×224). The results show that increasing the dataset size led to better performance, with increasing accuracy and generalization of the model. Furthermore, increasing the number of epochs during training improves the accuracy; with 60 epochs as our choice for the DL model, we achieved 97.28℅ accuracy.http://www.sciencedirect.com/science/article/pii/S2772671124000822Deep learningConvolution neural networkMagnetic resonance imagingBrain tumor recognition |
| spellingShingle | Mohammed H. Al-Jammas Emad A. Al-Sabawi Ayshaa Mohannad Yassin Aya Hassan Abdulrazzaq Brain tumors recognition based on deep learning e-Prime: Advances in Electrical Engineering, Electronics and Energy Deep learning Convolution neural network Magnetic resonance imaging Brain tumor recognition |
| title | Brain tumors recognition based on deep learning |
| title_full | Brain tumors recognition based on deep learning |
| title_fullStr | Brain tumors recognition based on deep learning |
| title_full_unstemmed | Brain tumors recognition based on deep learning |
| title_short | Brain tumors recognition based on deep learning |
| title_sort | brain tumors recognition based on deep learning |
| topic | Deep learning Convolution neural network Magnetic resonance imaging Brain tumor recognition |
| url | http://www.sciencedirect.com/science/article/pii/S2772671124000822 |
| work_keys_str_mv | AT mohammedhaljammas braintumorsrecognitionbasedondeeplearning AT emadaalsabawi braintumorsrecognitionbasedondeeplearning AT ayshaamohannadyassin braintumorsrecognitionbasedondeeplearning AT ayahassanabdulrazzaq braintumorsrecognitionbasedondeeplearning |