Assessing attention mechanisms' impact on automatic brain tumor classification
DOI:
https://doi.org/10.59681/2175-4411.v16.iEspecial.2024.1276Keywords:
Convolutional Neural Network, Deep Learning, Brain TumorAbstract
Objective: To compare a conventional convolutional neural network model and its attention-enhanced counterpart. Method: We trained both models on the same dataset images of gliomas, meningiomas, pituitary adenomas, and non-tumorous images; then, we compared both models using interpretable approaches, highlighting the regions used for their predictions. Results: Our analysis found that the attention-enhanced model focused more on tumor regions, with 99% accuracy. Conclusion: The outcome of this research underscores the importance of continued exploration into advanced neural network features to elevate the standards of diagnostic accuracy and efficiency in medical practice.
References
Felipe C, Alva T, Winck A, Becker C. An approach in brain tumor classification: The development of a new convolutional neural network model. In: Anais do XX Encontro Nacional de Inteligência Artificial e Computacional. Porto Alegre: SBC; 2023. p. 28-42. doi:10.5753/eniac.2023.233530.
An J, Joe I. Attention map-guided visual explanations for deep neural networks. Applied Sciences. 2022;12(8):3846. Available from: https://doi.org/10.3390/app12083846
Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE International Conference on Computer Vision; 2017 Oct 22-29; Venice, Italy. p. 618-26.
Mercaldo F, Brunese L, Martinelli F, Santone A, Cesarelli M. Explainable Convolutional Neural Networks for Brain Cancer Detection and Localisation. Sensors (Basel). 2023;23(17):7614. Published 2023 Sep 2. doi:10.3390/s23177614
Hussain T, Shouno H. Explainable Deep Learning Approach for Multi-Class Brain Magnetic Resonance Imaging Tumor Classification and Localization Using Gradient-Weighted Class Activation Mapping. Information. 2023; 14(12):642. https://doi.org/10.3390/info14120642
Alzahrani SM. ConvAttenMixer: Brain tumor detection and type classification using convolutional mixer with external and self-attention mechanisms. J King Saud Univ Comput Inf Sci. 2023;35(10):101810. doi: 10.1016/j.jksuci.2023.101810.
Nickparvar M. Brain tumor MRI dataset [Data set]. Kaggle. 2021. Available from: https://doi.org/10.34740/KAGGLE/DSV/2645886
Jun W, Liyuan Z. Brain Tumor Classification Based on Attention Guided Deep Learning Model. Int J Comput Intell Syst. 2022;15:35. https://doi.org/10.1007/s44196-022-00090-9
Hu J, Shen L, Sun G. Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2018 Jun 18-23; Salt Lake City, UT, USA. p. 7132-41.
Figshare Brain Tumor Classification [Data set]. Kaggle. Available from: https://www.kaggle.com/datasets/rahimanshu/figshare-brain-tumor-classification. Last accessed 2023 May 17.
Sousa HS, Pereira Neto AA, Paula Júnior IC de, Melo CR de. Segmentação de infecções pulmonares de COVID-19 com a rede Mask R-CNN. J Health Inform [Internet]. 2023 Jul 20 [cited 2024 Mar 22];15(Especial). Available from: https://jhi.sbis.org.br/index.php/jhi-sbis/article/view/1100
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Submission of a paper to Journal of Health Informatics is understood to imply that it is not being considered for publication elsewhere and that the author(s) permission to publish his/her (their) article(s) in this Journal implies the exclusive authorization of the publishers to deal with all issues concerning the copyright therein. Upon the submission of an article, authors will be asked to sign a Copyright Notice. Acceptance of the agreement will ensure the widest possible dissemination of information. An e-mail will be sent to the corresponding author confirming receipt of the manuscript and acceptance of the agreement.
