Cancerous and Non-Cancerous Brain MRI Classification Method Based on Convolutional Neural Network and Log-Polar Transformation
Magnetic resonance imaging (MRI) offers visual representations of the interior of a body for clinical analysis and medical intervention. The MRI process is subjected to a variety of image processing and machine learning approaches to identify, diagnose, and classify brain diseases as well as detect...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-09-01
|
| Series: | Healthcare |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-9032/10/9/1801 |
| _version_ | 1797487809367375872 |
|---|---|
| author | Ferdaus Anam Jibon Mayeen Uddin Khandaker Mahadi Hasan Miraz Himon Thakur Fazle Rabby Nissren Tamam Abdelmoneim Sulieman Yahaya Saadu Itas Hamid Osman |
| author_facet | Ferdaus Anam Jibon Mayeen Uddin Khandaker Mahadi Hasan Miraz Himon Thakur Fazle Rabby Nissren Tamam Abdelmoneim Sulieman Yahaya Saadu Itas Hamid Osman |
| author_sort | Ferdaus Anam Jibon |
| collection | DOAJ |
| description | Magnetic resonance imaging (MRI) offers visual representations of the interior of a body for clinical analysis and medical intervention. The MRI process is subjected to a variety of image processing and machine learning approaches to identify, diagnose, and classify brain diseases as well as detect abnormalities. In this paper, we propose an improved classification method for distinguishing cancerous and noncancerous tumors from brain MRI images by using Log Polar Transformation (LPT) and convolutional neural networks (CNN). The LPT has been applied for feature extraction of rotation and scaling of distorted images, while the integration of CNN introduces a machine learning approach for the tumor classification of distorted images. The dataset was formed with images of seven different brain diseases, and the training set was formed by applying CNN with the extracted features. The proposed method is then evaluated in comparison to state-of-the-art algorithms, showing a definite improvement of the former. The obtained results show that the machine learning approach offers better classification with a success rate of about 96% in both plain brain MR images and rotation- and scale-invariant brain MR images. This work also successfully classified T-1 and T-2 weighted images of neoplastic and degenerative brain diseases. The obtained accuracy is perfected by several kernel procedures, while the combined performance of the two wavelet transformations and a strong dataset make our method robust and efficient. Since no earlier study on machine learning approaches with rotated and scaled brain MRI has come to our attention, it is expected that our proposed method introduces a new paradigm in this research field. |
| first_indexed | 2024-03-09T23:53:04Z |
| format | Article |
| id | doaj.art-eaa6023d5eaf4241953eddbd66a025f3 |
| institution | Directory Open Access Journal |
| issn | 2227-9032 |
| language | English |
| last_indexed | 2024-03-09T23:53:04Z |
| publishDate | 2022-09-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Healthcare |
| spelling | doaj.art-eaa6023d5eaf4241953eddbd66a025f32023-11-23T16:31:09ZengMDPI AGHealthcare2227-90322022-09-01109180110.3390/healthcare10091801Cancerous and Non-Cancerous Brain MRI Classification Method Based on Convolutional Neural Network and Log-Polar TransformationFerdaus Anam Jibon0Mayeen Uddin Khandaker1Mahadi Hasan Miraz2Himon Thakur3Fazle Rabby4Nissren Tamam5Abdelmoneim Sulieman6Yahaya Saadu Itas7Hamid Osman8Department of Computer Science and Engineering, University of Information Technology & Sciences (UITS), Dhaka 1000, BangladeshCentre for Applied Physics and Radiation Technologies, School of Engineering and Technology, Sunway University, Bandar Sunway 47500, Selangor, MalaysiaDepartment of Business Analytics, Sunway University, Bandar Sunway 47500, Selangor, MalaysiaDepartment of Electrical Electronic & Communication Engineering, Military Institute of Science & Technology (MIST), Dhaka 1000, BangladeshDepartment of Computer Science and Engineering, Sheikh Fazilatunnesa Mujib University (SFMU), Jamalpur 2000, BangladeshDepartment of Physics, College of Sciences, Princess Nourah Bint Abdulrahman University, Riyadh 11671, Saudi ArabiaDepartment of Radiology and Medical Imaging, College of Applied Medical Sciences, Prince Sattam Bin Abdulaziz University, Al-Kharj 11942, Saudi ArabiaDepartment of Physics, Bauchi State University Gadau, PMB 65, Gadau 751105, NigeriaDepartment of Radiological Sciences, College of Applied Medical Sciences, Taif University, Taif 21944, Saudi ArabiaMagnetic resonance imaging (MRI) offers visual representations of the interior of a body for clinical analysis and medical intervention. The MRI process is subjected to a variety of image processing and machine learning approaches to identify, diagnose, and classify brain diseases as well as detect abnormalities. In this paper, we propose an improved classification method for distinguishing cancerous and noncancerous tumors from brain MRI images by using Log Polar Transformation (LPT) and convolutional neural networks (CNN). The LPT has been applied for feature extraction of rotation and scaling of distorted images, while the integration of CNN introduces a machine learning approach for the tumor classification of distorted images. The dataset was formed with images of seven different brain diseases, and the training set was formed by applying CNN with the extracted features. The proposed method is then evaluated in comparison to state-of-the-art algorithms, showing a definite improvement of the former. The obtained results show that the machine learning approach offers better classification with a success rate of about 96% in both plain brain MR images and rotation- and scale-invariant brain MR images. This work also successfully classified T-1 and T-2 weighted images of neoplastic and degenerative brain diseases. The obtained accuracy is perfected by several kernel procedures, while the combined performance of the two wavelet transformations and a strong dataset make our method robust and efficient. Since no earlier study on machine learning approaches with rotated and scaled brain MRI has come to our attention, it is expected that our proposed method introduces a new paradigm in this research field.https://www.mdpi.com/2227-9032/10/9/1801convolutional neural networklog-polar transformationprincipal component analysisclassificationsegmentationMRI |
| spellingShingle | Ferdaus Anam Jibon Mayeen Uddin Khandaker Mahadi Hasan Miraz Himon Thakur Fazle Rabby Nissren Tamam Abdelmoneim Sulieman Yahaya Saadu Itas Hamid Osman Cancerous and Non-Cancerous Brain MRI Classification Method Based on Convolutional Neural Network and Log-Polar Transformation Healthcare convolutional neural network log-polar transformation principal component analysis classification segmentation MRI |
| title | Cancerous and Non-Cancerous Brain MRI Classification Method Based on Convolutional Neural Network and Log-Polar Transformation |
| title_full | Cancerous and Non-Cancerous Brain MRI Classification Method Based on Convolutional Neural Network and Log-Polar Transformation |
| title_fullStr | Cancerous and Non-Cancerous Brain MRI Classification Method Based on Convolutional Neural Network and Log-Polar Transformation |
| title_full_unstemmed | Cancerous and Non-Cancerous Brain MRI Classification Method Based on Convolutional Neural Network and Log-Polar Transformation |
| title_short | Cancerous and Non-Cancerous Brain MRI Classification Method Based on Convolutional Neural Network and Log-Polar Transformation |
| title_sort | cancerous and non cancerous brain mri classification method based on convolutional neural network and log polar transformation |
| topic | convolutional neural network log-polar transformation principal component analysis classification segmentation MRI |
| url | https://www.mdpi.com/2227-9032/10/9/1801 |
| work_keys_str_mv | AT ferdausanamjibon cancerousandnoncancerousbrainmriclassificationmethodbasedonconvolutionalneuralnetworkandlogpolartransformation AT mayeenuddinkhandaker cancerousandnoncancerousbrainmriclassificationmethodbasedonconvolutionalneuralnetworkandlogpolartransformation AT mahadihasanmiraz cancerousandnoncancerousbrainmriclassificationmethodbasedonconvolutionalneuralnetworkandlogpolartransformation AT himonthakur cancerousandnoncancerousbrainmriclassificationmethodbasedonconvolutionalneuralnetworkandlogpolartransformation AT fazlerabby cancerousandnoncancerousbrainmriclassificationmethodbasedonconvolutionalneuralnetworkandlogpolartransformation AT nissrentamam cancerousandnoncancerousbrainmriclassificationmethodbasedonconvolutionalneuralnetworkandlogpolartransformation AT abdelmoneimsulieman cancerousandnoncancerousbrainmriclassificationmethodbasedonconvolutionalneuralnetworkandlogpolartransformation AT yahayasaaduitas cancerousandnoncancerousbrainmriclassificationmethodbasedonconvolutionalneuralnetworkandlogpolartransformation AT hamidosman cancerousandnoncancerousbrainmriclassificationmethodbasedonconvolutionalneuralnetworkandlogpolartransformation |