Performance Comparison of SqueezeNet Implementing a Dendritic Neural Model for Brain Disease Image Classification
DOI:
https://doi.org/10.30871/jaic.v10i2.12196Keywords:
Brain Disease, CNN, Deep Learning, Dendritic Neural Model, SqueezeNetAbstract
In this study, a comparative analysis is conducted between a pre-trained SqueezeNet v1.1 model and a modified SqueezeNet architecture integrating a dendritic neural model (DNM) into the classifier layer for eight-class brain disease classification using MRI images. The proposed modification replaces the standard linear classifier with a dendritic-based processing mechanism to enhance nonlinear representation at the classification stage. Experiments are performed on an MRI-based brain medical image dataset, and model performance is evaluated using accuracy, precision, recall, F1-score, and confusion matrix analysis. The results show that the SqueezeNet model integrated with DNM achieves a significant accuracy improvement of approximately 5%, increasing from 90.33% to 95.61%, compared to the standard SqueezeNet model. This performance gain is accompanied by a moderate increase in model complexity, with the parameter count rising by approximately 1.69% (from 726.6K to 738.9K) and a longer convergence time (40 epochs versus 22 epochs). Overall, the findings indicate that incorporating DNM into a lightweight CNN architecture such as SqueezeNet can effectively improve medical image classification performance while maintaining reasonable computational efficiency.
Downloads
References
[1] S. S. Yadav and S. M. Jadhav, “Deep convolutional neural network based medical image classification for disease diagnosis,” J Big Data, vol. 6, no. 1, Dec. 2019, doi: 10.1186/s40537-019-0276-2.
[2] M. Aamir, Z. Rahman, U. A. Bhatti, W. A. Abro, J. A. Bhutto, and Z. He, “An automated deep learning framework for brain tumor classification using MRI imagery,” Sci Rep, vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-02209-2.
[3] A. Suganya and S. L. Aarthy, “Application of Deep Learning in the Diagnosis of Alzheimer’s and Parkinson’s Disease: A Review,” Curr Med Imaging, vol. 20, Jan. 2024, doi: 10.2174/1573405620666230328113721.
[4] S. Ahmed, S. K. Sakib, and A. B. Das, “Can Large Language Models Challenge CNNs in Medical Image Analysis?,” Jun. 2025, [Online]. Available: http://arxiv.org/abs/2505.23503
[5] M. Li, Y. Jiang, Y. Zhang, and H. Zhu, “Medical image analysis using deep learning algorithms,” Front Public Health, vol. 11, 2023, doi: 10.3389/fpubh.2023.1273253.
[6] A. O. A. Deheyab et al., “AN OVERVIEW of CHALLENGES in MEDICAL IMAGE PROCESSING,” in ACM International Conference Proceeding Series, Association for Computing Machinery, Dec. 2022, pp. 511–516. doi: 10.1145/3584202.3584278.
[7] F. N. Iandola, S. Han, M. W. Moskewicz, K. Ashraf, W. J. Dally, and K. Keutzer, “SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size,” Nov. 2016, [Online]. Available: http://arxiv.org/abs/1602.07360
[8] M. Tsivgoulis, T. Papastergiou, and V. Megalooikonomou, “An improved SqueezeNet model for the diagnosis of lung cancer in CT scans,” Machine Learning with Applications, vol. 10, p. 100399, Dec. 2022, doi: 10.1016/J.MLWA.2022.100399.
[9] X. Wen, M. Zhou, A. Albeshri, L. Huang, X. Luo, and D. Ning, “Improving Classification Performance in Dendritic Neuron Models through Practical Initialization Strategies,” Sensors, vol. 24, no. 6, Mar. 2024, doi: 10.3390/s24061729.
[10] Y. ; Yang et al., “Yet Another Effective Dendritic Neuron Model Based on the Activity of Excitation and Inhibition,” Mathematics 2023, Vol. 11, Page 1701, vol. 11, no. 7, p. 1701, Apr. 2023, doi: 10.3390/MATH11071701.
[11] Q. Du, Z. Liu, Y. Song, N. Wang, Z. Ju, and S. Gao, “A Lightweight Dendritic ShuffleNet for Medical Image Classification,” IEICE Trans Inf Syst, vol. E108D, no. 7, pp. 744–751, Jul. 2025, doi: 10.1587/transinf.2024EDP7059.
[12] N. Wang, Q. Du, Z. Yuan, Y. Gao, R.-L. Wang, and S. Gao, “Dendritic Aggregated Residual Deep Learning for Meningioma MRI Diagnosis,” IEICE Trans Inf Syst, vol. E108.D, no. 8, pp. 1016–1019, Aug. 2025, doi: 10.1587/transinf.2024edl8049.
[13] Y. Ding, J. Yu, C. Gu, S. Gao, and C. Zhang, “A Multi-In and Multi-Out Dendritic Neuron Model and its Optimization,” Sep. 2023, [Online]. Available: http://arxiv.org/abs/2309.07791
[14] L. Fischer et al., “Dendritic Mechanisms for In Vivo Neural Computations and Behavior,” in Journal of Neuroscience, Society for Neuroscience, Nov. 2022, pp. 8460–8467. doi: 10.1523/JNEUROSCI.1132-22.2022.
[15] A. O. Komendantov and G. A. Ascoli, “Dendritic excitability and neuronal morphology as determinants of synaptic efficacy,” J Neurophysiol, vol. 101, no. 4, pp. 1847–1866, Apr. 2009, doi: 10.1152/jn.01235.2007.
[16] N. A. Ranggianto, A. P. Segara, D. Wijonarko, A. Andrianto, and M. H. Arief, “Procedural Content Generation pada Level Gim Sokoban Menggunakan Model Hybrid GPT2 dan Algoritma Genetika,” remik, vol. 9, no. 3, pp. 963–974, Aug. 2025, doi: 10.33395/remik.v9i3.15188.
[17] A. M. Taha, S. A. Aly, and M. F. Darwish, “Detecting Glioma, Meningioma, and Pituitary Tumors, and Normal Brain Tissues based on Yolov11 and Yolov8 Deep Learning Models,” Mar. 2025, Accessed: Oct. 10, 2025. [Online]. Available: https://arxiv.org/pdf/2504.00189v1
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Riandika Fathur Rochim, I GN Lanang Wijayakusuma, I Putu Winada Gautama
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
