Klasifikasi Batu Ginjal Berbasis MobileNetv2 Graph Neural Network dengan Perbandingan Fungsi Aktivasi
DOI:
https://doi.org/10.30872/atasi.v5i2.5017Keywords:
Batu Ginjal, MobileNetv2, Graph Neural Network, Fungsi Aktivasi, Klasifikasi Citra CTAbstract
Batu ginjal merupakan gangguan urologi yang umum dan dapat menimbulkan komplikasi serius apabila tidak terdeteksi secara tepat. Interpretasi citra computed tomography (CT) secara manual masih menghadapi kendala akibat ukuran batu yang kecil, kontras rendah, serta variasi citra antar pasien. Penelitian ini mengusulkan model klasifikasi batu ginjal pada citra CT yang menggabungkan MobileNetV2 sebagai backbone ekstraksi fitur dengan graph module berbasis GraphConvLayer untuk mempelajari relasi antarfitur. Citra melalui tahap preprocessing dan augmentasi data sebelum diklasifikasikan melalui GlobalAveragePooling2D, dense layer, dan classifier head. Penelitian ini juga membandingkan dua fungsi aktivasi, yaitu ReLU dan Swish, guna mengetahui pengaruhnya terhadap kinerja model. Hasil pengujian menunjukkan bahwa ReLU memberikan performa terbaik dengan akurasi 96,59%, presisi 96,94%, recall 96,59%, dan skor F1 96,67%, sedangkan Swish mencapai AUC-ROC tertinggi sebesar 99,74%. Temuan ini menegaskan bahwa pemilihan fungsi aktivasi berpengaruh signifikan terhadap kinerja arsitektur MobileNetV2-Graph dalam klasifikasi batu ginjal, dengan ReLU sebagai konfigurasi paling stabil dan efektif.
References
Akram, M., Jahrreiss, V., Skolarikos, A., Geraghty, R., Tzelves, L., Emilliani, E., Davis, N. F., & Somani, B. K. (2024). Urological Guidelines for Kidney Stones: Overview and Comprehensive Update. Journal of Clinical Medicine 2024, Vol. 13, Page 1114, 13(4), 1114. https://doi.org/10.3390/JCM13041114
Asif, S., Zheng, X., & Zhu, Y. (2024). An optimized fusion of deep learning models for kidney stone detection from CT images. Journal of King Saud University - Computer and Information Sciences, 36(7), 102130. https://doi.org/10.1016/J.JKSUCI.2024.102130
Batheja, V., & Summers, R. (2025). Progress in fully automated abdominal CT interpretation-an update over the past decade. Abdominal Radiology 2025 51:2, 51(2), 1016–1034. https://doi.org/10.1007/S00261-025-05094-5
Bhuvanya, R., Kujani, T., Padmavathy, R., Matheswaran, P., & Punitha, P. (2024). Beyond ReLU: Unlocking Superior Plant Disease Recognition with Swish. Https://Doi.Org/10.1142/S0219877024410013, 21(8). https://doi.org/10.1142/S0219877024410013
Bichri, H., Chergui, A., & Hain, M. (2024). Investigating the Impact of Train / Test Split Ratio on the Performance of Pre-Trained Models with Custom Datasets. IJACSA) International Journal of Advanced Computer Science and Applications, 15(2). www.ijacsa.thesai.org
Chowdhury, S. T., Kumpati, N. S., & Mukhopadhyay, S. (2024). Mutual Learning for News Classification. Lecture Notes in Networks and Systems, 1066 LNNS, 37–54. https://doi.org/10.1007/978-3-031-66428-1_3/SAVE-RESEARCH
Fan, J., Ma, J., & Gai, H. (2026). MAC2STI: Mamba network with autoregressive clustering for two-stage spatio-temporal imputation. Complex and Intelligent Systems, 12(1), 19-. https://doi.org/10.1007/S40747-025-02130-1/FIGURES/15
Fontenelle, L. F., & Sarti, T. D. (2019). Kidney Stones: Treatment and Prevention. American Family Physician, 99(8), 490–496. https://www.aafp.org/afp/2019/0415/p490
Houssein, E. H., Abdelkareem, D. A., Hu, G., Hameed, M. A., Ibrahim, I. A., & Younan, M. (2024). An effective multiclass skin cancer classification approach based on deep convolutional neural network. Cluster Computing, 27(9), 12799–12819. https://doi.org/10.1007/S10586-024-04540-1/TABLES/8
Hridoy. (2025). Kidney Stone Dataset. Kaggle. https://www.kaggle.com/datasets/harshghadiya/kidneystone
Khan, E., Rehman, M. Z. U., Ahmed, F., Alfouzan, F. A., Alzahrani, N. M., & Ahmad, J. (2022). Chest X-ray Classification for the Detection of COVID-19 Using Deep Learning Techniques. Sensors, 22(3). https://doi.org/10.3390/s22031211
Kumar, Y., Brar, T. P. S., Kaur, C., & Singh, C. (2024). A Comprehensive Study of Deep Learning Methods for Kidney Tumor, Cyst, and Stone Diagnostics and Detection Using CT Images. Archives of Computational Methods in Engineering, 31(7), 4163–4188. https://doi.org/10.1007/S11831-024-10112-8/METRICS
Lu, G., Tian, J., Shi, F., Zhang, D. G., & Wang, D. (2025). Association of cardiovascular-kidney-metabolic syndrome stages with kidney stone prevalence: a population-based analysis of NHANES 2007–2020. BMJ Open, 15(5), e096533. https://doi.org/10.1136/BMJOPEN-2024-096533
Manjunath, R. V., Ghanshala, A., & Kwadiki, K. (2024). Deep learning algorithm performance evaluation in detection and classification of liver disease using CT images. Multimedia Tools and Applications, 83(1), 2773–2790. https://doi.org/10.1007/s11042-023-15627-z
Mohammad, F., Sharma, G., Khandelwal, K., Arif, A., Vani, M. S., & Sathyanarayana, C. (2024). Development of a Predictive Model for Kidney Stone Formation Using Deep Learning Techniques. Proceedings of the 2024 International Conference on Artificial Intelligence and Emerging Technology, Global AI Summit 2024, 485–489. https://doi.org/10.1109/GLOBALAISUMMIT62156.2024.10947936
Morozov, A. V., Levkivskyi, V. L., & Plechystyy, D. D. (2024). Activation Functions in Neural Networks: Overview and Comparison. Scientific Notes of Taurida National V.I. Vernadsky University. Series: Technical Sciences, 1(3), 144–151. https://doi.org/10.32782/2663-5941/2024.3.1/22
Panchbhai, K. G., & Lanjewar, M. G. (2026). KiCNN: A lightweight CNN model for kidney disease detection using spatial attention mechanisms. Multimedia Tools and Applications, 85(3), 277-. https://doi.org/10.1007/S11042-026-21398-0/METRICS
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L. C. (2018). MobileNetV2: Inverted Residuals and Linear Bottlenecks. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 4510–4520. https://doi.org/10.1109/CVPR.2018.00474
Sultana, J., Sen, J., Tasnim, N., & Rahman, M. M. (2025). CyStoneNet: Pseudo-Color Enhanced SE-Attention MobileNetV2 for Kidney Stone and Cyst Detection. 2025 28th International Conference on Computer and Information Technology (ICCIT), 4723–4728. https://doi.org/10.1109/ICCIT68739.2025.11491240
Vasudeva, N., Dhaka, V. S., & Sinwar, D. (2025). Enhancing kidney stone diagnosis with AI-driven radiographic imaging: a review. Discover Artificial Intelligence, 5(1), 200-. https://doi.org/10.1007/S44163-025-00434-2/TABLES/3
Vazirinejad, R., Ahmadinia, H., Heydari Khoormizi, S. M., Jamshidi, M., Khanamani Falahati-pour, S., Mohammadi-Shahrokhi, V., Safarian Neamatabad, M., Mohammadi Nematabad, V., & Abbasi-Dokht-Rafsanjani, M. (2026). Hypertension and incidence of kidney stones: a prospective study based on the data of the Rafsanjan cohort study. Scientific Reports 2026. https://doi.org/10.1038/s41598-026-60737-x
Verma, S., & Singh, P. K. (2025). Automated Kidney Stone Detection and Classification utilizing Dynamic Generative Residual Graph Convolutional Neural Networks for Computed Tomography-Based Medical Imaging. Biomedical Materials and Devices, 1–18. https://doi.org/10.1007/S44174-025-00525-9/METRICS
Yang, Z., Jiao, B., & Ren, X. (2026). RAC-Net: Interpretable Medical Small Target Segmentation Network with X-ray Radiation Attenuation Characterization. IEEE Transactions on Pattern Analysis and Machine Intelligence. https://doi.org/10.1109/TPAMI.2026.3705213
Zhang, Z., Hou, J., & Lin, Z. (2024). Exploring Integration methods for Image Data Augmentation. 2024 6th International Conference on Internet of Things, Automation and Artificial Intelligence, IoTAAI 2024, 707–713. https://doi.org/10.1109/IoTAAI62601.2024.10692583
Zhao, X., Wang, L., Zhang, Y., Han, X., Deveci, M., & Parmar, M. (2024). A review of convolutional neural networks in computer vision. Artificial Intelligence Review, 57(4), 99-. https://doi.org/10.1007/S10462-024-10721-6/FIGURES/33
Zuo, J., Zhang, Z., Chen, J., Gou, K., Zhou, J., Wen, L., Wei, H., Li, X., Zhan, P., Chen, P., Li, H., Zhao, J., Wang, H., Fu, S., Chen, J., & Wang, J. (2026). The Application of Nanomaterials in Kidney Stone Disease: Emerging Strategies for Early Diagnosis, Targeted Therapy, and Prevention. International Journal of Nanomedicine, 21. https://doi.org/10.2147/IJN.S610906
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Adopsi Teknologi dan Sistem Informasi (ATASI)
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
