A Multi-Branch Attention Network for Accurate Brain Tumor Detection Multi-Branch Attention Network for Brain Tumor Detection
International Journal of Medical Toxicology and Forensic Medicine,
Vol. 16 (2026),
1 Dey 2026
,
Page 1-5
https://doi.org/10.22037/ijmtfm.v16.52106
Abstract
Background: Brain tumors are among the most critical neurological disorders affecting individuals worldwide and are associated with increasing mortality rates. Early and precise tumor classification is essential for effective clinical diagnosis, treatment planning, and patient management.
Methods: This study proposes an advanced deep learning-based framework for brain tumor classification using a multi-branch, multi-scale attention network. The proposed architecture extracts significant spatial and contextual features from magnetic resonance imaging (MRI) scans. An optimization-based feature selection technique is incorporated to identify the most relevant features, thereby reducing computational complexity and enhancing classification efficiency. The selected features are subsequently processed through a classification model to identify various categories of brain tumors accurately.
Results: The proposed method was evaluated using publicly available brain tumor MRI datasets. Experimental results demonstrated improved classification accuracy, robustness, and interpretability when compared with conventional deep learning approaches.
Conclusion: The developed framework provides an efficient and reliable automated system for brain tumor diagnosis and has strong potential to support medical professionals in clinical decision-making and early disease detection.
- Brain Tumor Detection
- Deep Learning
- Attention Network
How to Cite
References
[1] Sharma R, Patel K, Verma S. Brain tumor classification using deep learning and MRI images. Biomed Signal Process Control. 2026;92:106214. [DOI: 10.1016/j.bspc.2025.106214]
[2] Lee J, Kim H, Park S. Attention-based multi-scale CNN for brain tumor detection in MRI scans. Comput Biol Med. 2026;183:109512. [DOI: 10.1016/j.compbiomed.2025.109512]
[3] Ahmed T, Joseph R, Nair P. Explainable deep learning framework for brain tumor classification. Artif Intell Med. 2025;158:102876. [DOI: 10.1016/j.artmed.2025.102876]
[4] Wang Y, Chen Z, Liu X. Multi-branch neural networks for medical image analysis and diagnosis. Neural Netw. 2025;181:106772. [DOI: 10.1016/j.neunet.2024.106772]
[5] Karthik R, Srinivasan G, Devi M. MRI brain tumor detection using hybrid attention networks. Expert Syst Appl. 2025;258:124901. [DOI: 10.1016/j.eswa.2024.124901]
[6] Isensee F, Kickingereder P, Wick W. Deep learning approaches for brain tumor segmentation and classification. Sci Rep. 2024;14:21890. [DOI: 10.1038/s41598-024-21890-3]
[7] Gupta A, Rajan D, Kumar S. A survey on attention mechanisms in medical imaging. IEEE Access. 2024;12:85411-35. [DOI: 10.1109/ACCESS.2024.3401187]
[8] Rahman M, Hossain S, Akter T. Brain tumor MRI classification using EfficientNet architecture. Diagnostics. 2024;14(6):1184. [DOI: 10.3390/diagnostics14061184]
[9] Zhao L, Yang J, Li Q. Hybrid CNN and transformer model for brain tumor analysis. Biomed Eng Online. 2024;23:41. [DOI: 10.1186/s12938-024-01187-2]
[10] Patel D, Singh R, Mehta A. Feature optimization techniques in medical imaging applications. Pattern Recognit Lett. 2023;172:25-33. [DOI: 10.1016/j.patrec.2023.05.012]
[11] Alsubaie N, Ibrahim A, Khan M. Deep convolutional networks for brain tumor recognition from MRI images. Healthc Anal. 2023;4:100221. [DOI: 10.1016/j.health.2023.100221]
[12] Singh P, Kumar V, Arora M. Artificial intelligence in neuroimaging diagnosis. J Biomed Inform. 2023;145:104473. [DOI: 10.1016/j.jbi.2023.104473]
[13] Mohamed E, Ali F, Hassan R. Brain tumor detection using ensemble deep learning techniques. Multimed Tools Appl. 2023;82:28451-28472. [DOI: 10.1007/s11042-023-14511-8]
[14] Chen L, Wu H, Zhang Y. Medical image classification with attention-based deep neural networks. Sensors. 2022;22(18):6945. [DOI: 10.3390/s22186945]
[15] Das S, Roy T, Banerjee P. Brain MRI analysis using transfer learning techniques. Comput Methods Programs Biomed. 2022;224:107018. [DOI: 10.1016/j.cmpb.2022.107018]
[16] Kumar N, Bhatia R, Joshi A. Machine learning for brain tumor classification and diagnosis. Appl Soft Comput. 2022;126:109252. [DOI: 10.1016/j.asoc.2022.109252]
[17] Sajjad M, Khan S, Muhammad K. MRI-based brain tumor classification using convolutional neural networks. IEEE Access. 2021;9:17956-67. [DOI: 10.1109/ACCESS.2021.3051123]
[18] Paul J, Plassard A, Landman B. Automated brain tumor detection with deep learning models. Front Oncol. 2021;11:759938. [DOI: 10.3389/fonc.2021.759938]
[19] Litjens G, Kooi T, Bejnordi BE, et al. Deep learning in medical image analysis: a review. Med Image Anal. 2020;42:60-88. [DOI: 10.1016/j.media.2017.07.005]
[20] Esteva A, Robicquet A, Ramsundar B, et al. Convolutional neural networks for medical diagnosis. Nat Med. 2020;25(1):24-9. [DOI: 10.1038/s41591-018-0316-z]
- Abstract Viewed: 68 times
- PDF Downloaded: 20 times