Comparative Analysis of CNN Architectures and Optimizers for ALL Classification
DOI:
https://doi.org/10.29207/resti.v10i7506Keywords:
CNN, deep learning, optimizer, RMSProp, XceptionAbstract
Deep learning has become an important approach for medical image analysis, particularly for automated image classification. Among its various architectures, Convolutional Neural Networks (CNNs) are frequently employed to extract and distinguish visual patterns from medical images. However, the performance of a CNN may vary depending on the optimization algorithm used during the training process. This study investigates the effect of four optimization methods on different CNN architectures for the classification of Peripheral Blood Smear (PBS) images. A publicly available Kaggle dataset comprising 3,242 images and four diagnostic categories was used in the experiments. Six architectures, namely ResNet50V2, Xception, EfficientNetB2, EfficientNetB4, EfficientNetV2-S, and EfficientNetV2-M, were evaluated in combination with Adam, AdamW, NAdam, and RMSprop. Before training, the images underwent resizing, normalization, and augmentation procedures. The dataset was subsequently partitioned into training, validation, and test subsets using proportions of 80%, 10%, and 10%, respectively. Classification performance was analyzed using accuracy, loss, and confusion matrix-based evaluation. Among all tested combinations, Xception with RMSprop produced the best result, obtaining 99.69% accuracy and a loss value of 0.0194. Conversely, the lowest result was observed for ResNet50V2 with RMSprop, which achieved 93.85% accuracy. The experimental findings indicate that the optimizer can substantially influence CNN classification performance, and the effectiveness of an optimization method is dependent on the architecture with which it is combined.
Downloads
References
[1] N. Khadem, A. Nashir, and S. Rahmatyar, “The Role of Deep Learning in Advancing Computer Vision Applications: A Comprehensive Systematic Review,” Journal of Advanced Computer Knowledge and Algorithms, vol. 3, no. 1, pp. 1–8, 2025, doi: https://doi.org/10.29103/jacka.v3i1.24732.
[2] J. Chai, H. Zeng, A. Li, and E. W. T. Ngai, “Deep learning in computer vision: A critical review of emerging techniques and application scenarios,” Machine Learning with Applications, vol. 6, p. 100134, 2021, doi: https://doi.org/10.1016/j.mlwa.2021.100134.
[3] I. D. Mienye and T. G. Swart, “A Comprehensive Review of Deep Learning: Architectures, Recent Advances, and Applications,” Information, vol. 15, no. 12, 2024, doi: 10.3390/info15120755.
[4] X. Zhao, L. Wang, Y. Zhang, X. Han, M. Deveci, and M. Parmar, “A review of convolutional neural networks in computer vision,” Artif Intell Rev, vol. 57, no. 4, p. 99, 2024, doi: 10.1007/s10462-024-10721-6.
[5] M. Trigka and E. Dritsas, “A Comprehensive Survey of Deep Learning Approaches in Image Processing,” Sensors, vol. 25, no. 2, 2025, doi: 10.3390/s25020531.
[6] M. Krichen, “Convolutional Neural Networks: A Survey,” Computers, vol. 12, no. 8, 2023, doi: 10.3390/computers12080151.
[7] L. Chen, S. Li, Q. Bai, J. Yang, S. Jiang, and Y. Miao, “Review of Image Classification Algorithms Based on Convolutional Neural Networks,” Remote Sens (Basel), vol. 13, no. 22, 2021, doi: 10.3390/rs13224712.doi: 10.3390/rs13224712.
[8] J. N. Haus et al., “MEMS Vibrometer for Structural Health Monitoring Using Guided Ultrasonic Waves,” Sensors, vol. 22, no. 14, 2022, doi: 10.3390/s22145368.doi: 10.3390/s22145368.
[9] D. Park and J.-H. Lee, “Feasibility Evaluation of Computational Fluid Dynamics Approach for Inhalation Exposure Assessment: Case Study for Biocide Spray,” Applied Sciences, vol. 11, no. 2, 2021, doi: 10.3390/app11020634.
[10] M. Tan and Q. Le, “EfficientNetV2: Smaller Models and Faster Training,” in Proceedings of the 38th International Conference on Machine Learning, M. Meila and T. Zhang, Eds., in Proceedings of Machine Learning Research, vol. 139. PMLR, 2021, pp. 10096–10106.
[11] L. Fan et al., “Modulation Characteristics of High-Speed Transistor Lasers,” Applied Sciences, vol. 12, no. 9, 2022, doi: 10.3390/app12094475.
[12] P.-M. Boarescu et al., “Multi-Organ Protective Effects of Curcumin Nanoparticles on Drug-Induced Acute Myocardial Infarction in Rats with Type 1 Diabetes Mellitus,” Applied Sciences, vol. 11, no. 12, 2021, doi: 10.3390/app11125497.
[13] K. Khotimah, S. Surono, and A. Thobirin, “Optimizing EfficientNet for imbalanced medical image classification using grey wolf optimization,” Computer Science and Information Technologies, vol. 6, no. 2, pp. 112–121, 2025, doi: 10.11591/csit.v6i2.pp112-121.
[14] M. Tan and Q. V. Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” Sep. 2020.
[15] M. Lavassani, J. Åkerberg, and M. Björkman, “Modeling and Profiling of Aggregated Industrial Network Traffic,” Applied Sciences, vol. 12, no. 2, 2022, doi: 10.3390/app12020667.
[16] Z. Yang and X. Liu, “Roundoff Error Analysis of an Algorithm Based on Householder Bidiagonalization for Total Least Squares Problems,” Mathematics, vol. 9, no. 20, 2021, doi: 10.3390/math9202550.
[17] A. Sabban, “Wearable Circular Polarized Antennas for Health Care, 5G, Energy Harvesting, and IoT Systems,” Electronics (Basel), vol. 11, no. 3, 2022, doi: 10.3390/electronics11030427.
[18] N. Campos Macias, W. Düggelin, Y. Ruf, and T. Hanne, “Building a Technology Recommender System Using Web Crawling and Natural Language Processing Technology,” Algorithms, vol. 15, no. 8, 2022, doi: 10.3390/a15080272.
[19] W. Hu, “Stability of Impulsive Stochastic Delay Systems with Markovian Switched Delay Effects,” Mathematics, vol. 10, no. 7, 2022, doi: 10.3390/math10071110.
[20] E. Rytel, A. Tajner-Czopek, A. Kita, A. Tkaczyńska, A. Z. Kucharska, and A. Sokół-Łętowska, “The Influence of the Production Process on the Anthocyanin Content and Composition in Dried Potato Cubes, Chips, and French Fries Made from Red-Fleshed Potatoes,” Applied Sciences, vol. 11, no. 3, 2021, doi: 10.3390/app11031104.
[21] S. Azimi, C. De Sio, D. Rizzieri, and L. Sterpone, “Analysis of Single Event Effects on Embedded Processor,” Electronics (Basel), vol. 10, no. 24, 2021, doi: 10.3390/electronics10243160.
[22] Y. Zheng et al., “Infrared Clinical Enamel Crack Detector Based on Silicon CCD and Its Application: A High-Quality and Low-Cost Option,” J Imaging, vol. 7, no. 12, 2021, doi: 10.3390/jimaging7120259.
[23] S. K. Zhou et al., “A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises.,” Proc IEEE Inst Electr Electron Eng, vol. 109, no. 5, pp. 820–838, May 2021, doi: 10.1109/JPROC.2021.3054390.
[24] M. Asadi-Aghbolaghi et al., “Learning generalizable AI models for multi-center histopathology image classification,” NPJ Precis Oncol, vol. 8, no. 1, p. 151, 2024, doi: 10.1038/s41698-024-00652-4.
[25] I. Park, W. H. Kim, and J. Ryu, “Style-KD: Class-imbalanced medical image classification via style knowledge distillation,” Biomed Signal Process Control, vol. 91, p. 105928, 2024, doi: https://doi.org/10.1016/j.bspc.2023.105928.
[26] H. Inaba and C.-H. Pui, “Advances in the Diagnosis and Treatment of Pediatric Acute Lymphoblastic Leukemia,” J Clin Med, vol. 10, no. 9, 2021, doi: 10.3390/jcm10091926.
[27] P. Jeneessha and V. K. Balasubramanian, “Domain knowledge-infused pre-trained deep learning models for efficient white blood cell classification,” Sci Rep, vol. 15, no. 1, p. 15608, 2025, doi: 10.1038/s41598-025-00563-9.
[28] A. Thiriveedhi, S. Ghanta, S. Biswas, and A. K. Pradhan, “ALL-Net: integrating CNN and explainable-AI for enhanced diagnosis and interpretation of acute lymphoblastic leukemia.,” PeerJ Comput Sci, vol. 11, p. e2600, 2025, doi: 10.7717/peerj-cs.2600.
[29] A. A. Abd El-Aziz, M. A. Mahmood, and S. Abd El-Ghany, “A Robust EfficientNetV2-S Classifier for Predicting Acute Lymphoblastic Leukemia Based on Cross Validation,” Symmetry (Basel), vol. 17, no. 1, 2025, doi: 10.3390/sym17010024.
[30] M. Ghaderzadeh, M. Aria, A. Hosseini, F. Asadi, D. Bashash, and H. Abolghasemi, “A fast and efficient CNN model for B-ALL diagnosis and its subtypes classification using peripheral blood smear images,” International Journal of Intelligent Systems, vol. 37, no. 8, pp. 5113–5133, Aug. 2022, doi: https://doi.org/10.1002/int.22753.
[31] D. Muduli et al., “Deep learning-based detection and classification of acute lymphoblastic leukemia with explainable AI techniques,” Array, vol. 26, p. 100397, 2025, doi: https://doi.org/10.1016/j.array.2025.100397.
[32] S. B. Mohan, S. Sathya, S. Rajalaksmi, G. Gurumoorthy, and R. Sivanraju, “Efficient convolutional neural networks for acute lymphoblastic leukaemia prediction in computer vision,” Sci Rep, 2025, doi: 10.1038/s41598-025-30777-w.
[33] A. Hosseini et al., “A mobile application based on efficient lightweight CNN model for classification of B-ALL cancer from non-cancerous cells: A design and implementation study,” Inform Med Unlocked, vol. 39, p. 101244, 2023, doi: https://doi.org/10.1016/j.imu.2023.101244.
[34] N. Guetta, A. Shabtai, I. Singh, S. Momiyama, and Y. Elovici, “Dodging Attack Using Carefully Crafted Natural Makeup,” Sep. 2021, [Online]. Available: http://arxiv.org/abs/2109.06467
[35] H. Naveed, S. Anwar, M. Hayat, K. Javed, and A. Mian, “Survey: Image Mixing and Deleting for Data Augmentation,” Feb. 2023, [Online]. Available: http://arxiv.org/abs/2106.07085
[36] X. Zhao, L. Wang, Y. Zhang, X. Han, M. Deveci, and M. Parmar, “A review of convolutional neural networks in computer vision,” Artif Intell Rev, vol. 57, no. 4, Apr. 2024, doi: 10.1007/s10462-024-10721-6.
[37] M. Tan and Q. V. Le, “EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks,” Sep. 2020, [Online]. Available: http://arxiv.org/abs/1905.11946
[38] M. Tan and Q. V. Le, “EfficientNetV2: Smaller Models and Faster Training,” Jun. 2021, [Online]. Available: http://arxiv.org/abs/2104.00298
[39] H. Jiyan Mustaqim and O. Suria, “Comparative Analysis of ResNet50V2, ResNet152V2, and MobileNetV2 Architectures in Monkeypox Classification,” 2025. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
[40] F. Chollet, “Xception: Deep Learning with Depthwise Separable Convolutions.”
[41] M. Reyad and A. M. Sarhan, “A modified Adam algorithm for deep neural network optimization,” Neural Comput Appl, vol. 35, no. 23, pp. 17095–17112, 2023, doi: 10.1007/s00521-023-08568-z.
[42] Y. Wang, Z. Xiao, and G. Cao, “A convolutional neural network method based on Adam optimizer with power-exponential learning rate for bearing fault diagnosis,” Journal of Vibroengineering, vol. 24, no. 4, pp. 666–678, Jun. 2022, doi: 10.21595/jve.2022.22271.
[43] P. Zhou, X. Xie, Z. Lin, K.-C. Toh, and S. Yan, “Win: Weight-Decay-Integrated Nesterov Acceleration for Faster Network Training,” 2024. [Online]. Available: https://github.com/sail-sg/win.
[44] J. Tu, A. Yasin, and N. S. Mansor, “NadamClip: A Novel Optimization Algorithm for Improving Prediction Accuracy and Training Stability,” Processes, vol. 13, no. 7, Jul. 2025, doi: 10.3390/pr13072145.
[45] R. Abdulkadirov, P. Lyakhov, and N. Nagornov, “Survey of Optimization Algorithms in Modern Neural Networks,” Jun. 01, 2023, MDPI. doi: 10.3390/math11112466.
[46] S. Farhadpour, T. A. Warner, and A. E. Maxwell, “Selecting and Interpreting Multiclass Loss and Accuracy Assessment Metrics for Classifications with Class Imbalance: Guidance and Best Practices,” Remote Sens (Basel), vol. 16, no. 3, Feb. 2024, doi: 10.3390/rs16030533.
[47] M. M. Alam, F. S. Pribadi, R. A. Aprilianto, and A. R. Nurul’aini, “Stacking Ensemble Learning Model for Intrusion Detection in Electrical Substation,” Jurnal RESTI, vol. 9, no. 5, pp. 1030–1037, Oct. 2025, doi: 10.29207/resti.v9i5.6502.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Copyright in each article belongs to the author
- The author acknowledges that the RESTI Journal (System Engineering and Information Technology) is the first publisher to publish with a license Creative Commons Attribution 4.0 International License.
- Authors can enter writing separately, arrange the non-exclusive distribution of manuscripts that have been published in this journal into other versions (eg sent to the author's institutional repository, publication in a book, etc.), by acknowledging that the manuscript has been published for the first time in the RESTI (Rekayasa Sistem dan Teknologi Informasi) journal ;
