A Robust End-to-End Deep Learning-Based Approach for Effective and Reliable BTD Using MR Images
Detection of a brain tumor in the early stages is critical for clinical practice and survival rate. Brain tumors arise in multiple shapes, sizes, and features with various treatment options. Tumor detection manually is challenging, time-consuming, and prone to error. Magnetic resonance imaging (MRI)...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/19/7575 |
| _version_ | 1797476887052681216 |
|---|---|
| author | Naeem Ullah Mohammad Sohail Khan Javed Ali Khan Ahyoung Choi Muhammad Shahid Anwar |
| author_facet | Naeem Ullah Mohammad Sohail Khan Javed Ali Khan Ahyoung Choi Muhammad Shahid Anwar |
| author_sort | Naeem Ullah |
| collection | DOAJ |
| description | Detection of a brain tumor in the early stages is critical for clinical practice and survival rate. Brain tumors arise in multiple shapes, sizes, and features with various treatment options. Tumor detection manually is challenging, time-consuming, and prone to error. Magnetic resonance imaging (MRI) scans are mostly used for tumor detection due to their non-invasive properties and also avoid painful biopsy. MRI scanning of one patient’s brain generates many 3D images from multiple directions, making the manual detection of tumors very difficult, error-prone, and time-consuming. Therefore, there is a considerable need for autonomous diagnostics tools to detect brain tumors accurately. In this research, we have presented a novel TumorResnet deep learning (DL) model for brain detection, i.e., binary classification. The TumorResNet model employs 20 convolution layers with a leaky ReLU (LReLU) activation function for feature map activation to compute the most distinctive deep features. Finally, three fully connected classification layers are used to classify brain tumors MRI into normal and tumorous. The performance of the proposed TumorResNet architecture is evaluated on a standard Kaggle brain tumor MRI dataset for brain tumor detection (BTD), which contains brain tumor and normal MR images. The proposed model achieved a good accuracy of 99.33% for BTD. These experimental results, including the cross-dataset setting, validate the superiority of the TumorResNet model over the contemporary frameworks. This study offers an automated BTD method that aids in the early diagnosis of brain cancers. This procedure has a substantial impact on improving treatment options and patient survival. |
| first_indexed | 2024-03-09T21:10:07Z |
| format | Article |
| id | doaj.art-6d47a82c139a4ca48d1582b6bf9a000b |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T21:10:07Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-6d47a82c139a4ca48d1582b6bf9a000b2023-11-23T21:51:23ZengMDPI AGSensors1424-82202022-10-012219757510.3390/s22197575A Robust End-to-End Deep Learning-Based Approach for Effective and Reliable BTD Using MR ImagesNaeem Ullah0Mohammad Sohail Khan1Javed Ali Khan2Ahyoung Choi3Muhammad Shahid Anwar4Department of Software Engineering, University of Engineering and Technology, Taxila 47050, PakistanDepartment of Computer Software Engineering, University of Engineering and Technology Mardan, Mardan 23200, PakistanDepartment of Software Engineering, University of Science and Technology Bannu, Bannu 28100, PakistanDepartment of AI, Software Gachon University, Seongnem-si 13120, KoreaDepartment of AI, Software Gachon University, Seongnem-si 13120, KoreaDetection of a brain tumor in the early stages is critical for clinical practice and survival rate. Brain tumors arise in multiple shapes, sizes, and features with various treatment options. Tumor detection manually is challenging, time-consuming, and prone to error. Magnetic resonance imaging (MRI) scans are mostly used for tumor detection due to their non-invasive properties and also avoid painful biopsy. MRI scanning of one patient’s brain generates many 3D images from multiple directions, making the manual detection of tumors very difficult, error-prone, and time-consuming. Therefore, there is a considerable need for autonomous diagnostics tools to detect brain tumors accurately. In this research, we have presented a novel TumorResnet deep learning (DL) model for brain detection, i.e., binary classification. The TumorResNet model employs 20 convolution layers with a leaky ReLU (LReLU) activation function for feature map activation to compute the most distinctive deep features. Finally, three fully connected classification layers are used to classify brain tumors MRI into normal and tumorous. The performance of the proposed TumorResNet architecture is evaluated on a standard Kaggle brain tumor MRI dataset for brain tumor detection (BTD), which contains brain tumor and normal MR images. The proposed model achieved a good accuracy of 99.33% for BTD. These experimental results, including the cross-dataset setting, validate the superiority of the TumorResNet model over the contemporary frameworks. This study offers an automated BTD method that aids in the early diagnosis of brain cancers. This procedure has a substantial impact on improving treatment options and patient survival.https://www.mdpi.com/1424-8220/22/19/7575brain tumor detectiondeep learningMRITumorResNet |
| spellingShingle | Naeem Ullah Mohammad Sohail Khan Javed Ali Khan Ahyoung Choi Muhammad Shahid Anwar A Robust End-to-End Deep Learning-Based Approach for Effective and Reliable BTD Using MR Images Sensors brain tumor detection deep learning MRI TumorResNet |
| title | A Robust End-to-End Deep Learning-Based Approach for Effective and Reliable BTD Using MR Images |
| title_full | A Robust End-to-End Deep Learning-Based Approach for Effective and Reliable BTD Using MR Images |
| title_fullStr | A Robust End-to-End Deep Learning-Based Approach for Effective and Reliable BTD Using MR Images |
| title_full_unstemmed | A Robust End-to-End Deep Learning-Based Approach for Effective and Reliable BTD Using MR Images |
| title_short | A Robust End-to-End Deep Learning-Based Approach for Effective and Reliable BTD Using MR Images |
| title_sort | robust end to end deep learning based approach for effective and reliable btd using mr images |
| topic | brain tumor detection deep learning MRI TumorResNet |
| url | https://www.mdpi.com/1424-8220/22/19/7575 |
| work_keys_str_mv | AT naeemullah arobustendtoenddeeplearningbasedapproachforeffectiveandreliablebtdusingmrimages AT mohammadsohailkhan arobustendtoenddeeplearningbasedapproachforeffectiveandreliablebtdusingmrimages AT javedalikhan arobustendtoenddeeplearningbasedapproachforeffectiveandreliablebtdusingmrimages AT ahyoungchoi arobustendtoenddeeplearningbasedapproachforeffectiveandreliablebtdusingmrimages AT muhammadshahidanwar arobustendtoenddeeplearningbasedapproachforeffectiveandreliablebtdusingmrimages AT naeemullah robustendtoenddeeplearningbasedapproachforeffectiveandreliablebtdusingmrimages AT mohammadsohailkhan robustendtoenddeeplearningbasedapproachforeffectiveandreliablebtdusingmrimages AT javedalikhan robustendtoenddeeplearningbasedapproachforeffectiveandreliablebtdusingmrimages AT ahyoungchoi robustendtoenddeeplearningbasedapproachforeffectiveandreliablebtdusingmrimages AT muhammadshahidanwar robustendtoenddeeplearningbasedapproachforeffectiveandreliablebtdusingmrimages |