Mehdhar S. A. M. Al-gaashani

Classification framework for medical diagnosis of brain tumor with an effective hybrid transfer learning model

• Authors Details :  
• Nagwan Abdel Samee,  
• Noha F. Mahmoud,  
• Ghada Atteia,  
• Hanaa A. Abdallah,  
• Maali Alabdulhafith,  
• Mehdhar S. A. M. Al-gaashani,  
• Shahab Ahmad And Mohammed Saleh Ali Muthanna

Journal title : Diagnostics

Publisher : MDPI AG

Online ISSN : 2075-4418

Page Number : 2541

Journal volume : 12

Journal issue : 10

267 Views Original Article

Brain tumors (BTs) are deadly diseases that can strike people of every age, all over the world. Every year, thousands of people die of brain tumors. Brain-related diagnoses require caution, and even the smallest error in diagnosis can have negative repercussions. Medical errors in brain tumor diagnosis are common and frequently result in higher patient mortality rates. Magnetic resonance imaging (MRI) is widely used for tumor evaluation and detection. However, MRI generates large amounts of data, making manual segmentation difficult and laborious work, limiting the use of accurate measurements in clinical practice. As a result, automated and dependable segmentation methods are required. Automatic segmentation and early detection of brain tumors are difficult tasks in computer vision due to their high spatial and structural variability. Therefore, early diagnosis or detection and treatment are critical. Various traditional Machine learning (ML) techniques have been used to detect various types of brain tumors. The main issue with these models is that the features were manually extracted. To address the aforementioned insightful issues, this paper presents a hybrid deep transfer learning (GN-AlexNet) model of BT tri-classification (pituitary, meningioma, and glioma). The proposed model combines GoogleNet architecture with the AlexNet model by removing the five layers of GoogleNet and adding ten layers of the AlexNet model, which extracts features and classifies them automatically. On the same CE-MRI dataset, the proposed model was compared to transfer learning techniques (VGG-16, AlexNet, SqeezNet, ResNet, and MobileNet-V2) and ML/DL. The proposed model outperformed the current methods in terms of accuracy and sensitivity (accuracy of 99.51% and sensitivity of 98.90%).

Article DOI & Crossmark Data

DOI : https://doi.org/10.3390/diagnostics12102541

Article Subject Details

• Artificial Intelligence
• Computer Science
• Computer Science Applications

Article Keywords Details

• A brain tumor; hybrid transfer learning; machine learning; deep learning; magnetic resonance imaging

Article File

Full Text PDF

Article References

• (1). 10.3322/caac.20069
• (2). 10.1007/s40708-017-0075-5
• (3). 10.1155/2014/712783
• (4). 10.1210/jc.2003-030395
• (5). 10.1056/NEJM200101113440207
• (6). 10.1007/s00401-016-1545-1
• (7). 10.1007/s11042-020-08898-3
• (8). 10.1016/j.jocs.2018.12.003
• (9). 10.1007/s00034-019-01246-3
• (10). 10.1007/s11063-017-9759-3
• (11). 10.3390/electronics11071146
• (12). 10.1109/BIBM.2015.7359716
• (13). 10.3390/math10193631
• (14). 10.1016/j.matpr.2020.11.495
• (15). 10.1088/1757-899X/853/1/012054
• (16). 10.3390/electronics11172767
• (17). 10.1155/2022/8141530
• (18). 10.1155/2022/6486570
• (19). 10.1109/ACCESS.2022.3189676
• (20). 10.1155/2021/6013448
• (21). 10.3934/mbe.2020328
• (22). 10.1007/s40747-021-00563-y
• (23). 10.1109/ICICS49469.2020.239522
• (24). 10.1109/ICCCI50826.2021.9457019
• (25). 10.1109/CONIT51480.2021.9498384
• (26). 10.1109/INCET51464.2021.9456347
• (27). 10.1016/j.irbm.2021.06.003
• (28). 10.1016/j.compmedimag.2019.05.001
• (29). 10.1016/j.bbe.2020.05.009
• (30). 10.1016/j.compbiomed.2019.103345
• (31). 10.1016/j.bbe.2020.01.006
• (32). 10.1155/2017/9749108
• (33). Resize Function https://www.mathworks.com/products/matlab.html
• (34). 10.1145/3065386
• (35). 10.1155/2019/1065652
• (36). 10.1109/ICASERT.2019.8934561
• (37). 10.1155/2022/1830010
• (38). 10.1109/SSPS.2017.8071613

---

More Article by Mehdhar S. A. M. Al-Gaashani