Hyperparameter Tuning Exploration to Maximize MobileNet Performance in Classification Kidney Tumor

Sandy Putra Siregar; M. Safii; Sundari Retno Andani

doi:10.31154/cogito.v11i2.960.447-461

Authors

Sandy Putra Siregar STIKOM Tunas Bangsa
M. Safii STIKOM Tunas Bangsa
Sundari Retno Andani STIKOM Tunas Bangsa

DOI:

https://doi.org/10.31154/cogito.v11i2.960.447-461

Keywords:

Kidney Tumor, Classification, MobileNet, Hyperparameter, Deep Learning

Abstract

The main focus in this research is how to develop the MobileNet architecture in order to produce a kidney tumor classification model that is accurate, resistant to overfitting, and remains consistent with variations in datasets and training parameters. This study aims to develop MobileNet architecture to produce a software model that can precisely identify with high accuracy, perform kidney tumor classification, and avoid failure in generalizing new data called overfitting, as well as evaluate the difference in accuracy generated from several variations of datasets and parameters. The method used in this study is MobileNet with hyperparameter tuning and fine-tuning, and it was compared with the MobileNet Baseline method. The dataset consists of 12,446 images classified as Normal, Cyst, Stone, and Tumor, collected from Kaggle. The findings of this study on the division of the 80:10:10 ratio of the proposed method image data resulted in 100% accuracy, 100% precision, 100% recall, and 100% F1-Score. This study is expected to produce architecture modifications that can classify kidney tumors with high accuracy so that the hypothesis is achieved. In addition, various approaches in medical image analysis using deep learning have shown better results in identifying various tumors, especially this research in the classification and detection of kidney tumors.

References

P. E. Stevens et al., “KDIGO 2024 Clinical Practice Guideline for the Evaluation and Management of Chronic Kidney Disease,” Kidney Int., vol. 105, no. 4, pp. S117–S314, 2024, doi: 10.1016/j.kint.2023.10.018.

A. Zarbock et al., “Sepsis-associated acute kidney injury: consensus report of the 28th Acute Disease Quality Initiative workgroup,” Nat. Rev. Nephrol., vol. 19, no. 6, pp. 401–417, 2023, doi: 10.1038/s41581-023-00683-3.

K. L. Lentine et al., “OPTN/SRTR 2020 Annual Data Report: Kidney,” Am. J. Transplant., vol. 22, no. S2, pp. 21–136, 2022, doi: 10.1111/ajt.16982.

G. Ietto, M. Gritti, G. Pettinato, G. Carcano, and D. D. Gasperina, “Tumors after kidney transplantation: a population study,” World J. Surg. Oncol., vol. 21, no. 1, 2023, doi: 10.1186/s12957-023-02892-3.

M. N. Islam, M. Hasan, M. K. Hossain, M. G. R. Alam, M. Z. Uddin, and A. Soylu, “Vision transformer and explainable transfer learning models for auto detection of kidney cyst, stone and tumor from CT-radiography,” Sci. Rep., vol. 12, no. 1, 2022, doi: 10.1038/s41598-022-15634-4.

D. Alzu’Bi et al., “Kidney Tumor Detection and Classification Based on Deep Learning Approaches: A New Dataset in CT Scans,” J. Healthc. Eng., vol. 2022, 2022, doi: 10.1155/2022/3861161.

M. Li, L. He, J. Zhu, P. Zhang, and S. Liang, “Targeting tumor-associated macrophages for cancer treatment,” Cell Biosci., vol. 12, no. 1, pp. 1–13, 2022, doi: 10.1186/s13578-022-00823-5.

Z. Z. Ji et al., “Tumour-associated macrophages: versatile players in the tumour microenvironment,” Front. Cell Dev. Biol., vol. 11, no. October, pp. 1–18, 2023, doi: 10.3389/fcell.2023.1261749.

B. Zhou et al., “The Global, Regional, and National Burden of Pancreatitis From 1990 to 2021: A Systematic Analysis for the Global Burden of Disease Study 2021,” J. Gastroenterol. Hepatol., vol. 40, no. 5, pp. 1297–1306, 2025, doi: 10.1111/jgh.16906.

B. L. Neuen et al., “National health policies and strategies for addressing chronic kidney disease: Data from the International Society of Nephrology Global Kidney Health Atlas,” PLOS Glob. Public Heal., vol. 3, no. 2, pp. 1–13, 2023, doi: 10.1371/journal.pgph.0001467.

G. Schiano et al., “Allelic effects on uromodulin aggregates drive autosomal dominant tubulointerstitial kidney disease,” EMBO Mol. Med., vol. 15, no. 12, pp. 1–21, 2023, doi: 10.15252/emmm.202318242.

H. Mabillard, J. A. Sayer, and E. Olinger, “Clinical and genetic spectra of autosomal dominant tubulointerstitial kidney disease,” Nephrol. Dial. Transplant., vol. 38, no. 2, pp. 271–282, 2023, doi: 10.1093/ndt/gfab268.

E. Fasler-Kan et al., “Cytokine Signaling in Pediatric Kidney Tumor Cell Lines WT-CLS1, WT-3ab and G-401,” Int. J. Mol. Sci., vol. 25, no. 4, 2024, doi: 10.3390/ijms25042281.

J. Peng et al., “Dual-targeting of artesunate and chloroquine to tumor cells and tumor-associated macrophages by a biomimetic PLGA nanoparticle for colorectal cancer treatment,” Int. J. Biol. Macromol., vol. 244, 2023, doi: 10.1016/j.ijbiomac.2023.125163.

B. Toledo, L. Zhu Chen, M. Paniagua-Sancho, J. A. Marchal, M. Perán, and E. Giovannetti, “Deciphering the performance of macrophages in tumour microenvironment: a call for precision immunotherapy,” J. Hematol. Oncol., vol. 17, no. 1, pp. 1–34, 2024, doi: 10.1186/s13045-024-01559-0.

N. Karunanayake et al., “Dual-Stage AI Model for Enhanced CT Imaging: Precision Segmentation of Kidney and Tumors,” Tomography, vol. 11, no. 1, pp. 1–15, 2025, doi: 10.3390/tomography11010003.

A. Abdelrahman and S. Viriri, “Kidney Tumor Semantic Segmentation Using Deep Learning: A Survey of State-of-the-Art,” J. Imaging, vol. 8, no. 3, 2022, doi: 10.3390/jimaging8030055.

V. Anand, S. Gupta, and D. Koundal, “Detection and Classification of Skin Disease Using Modified Mobilenet Architecture,” ECS Trans., vol. 107, no. 1, pp. 5059–5067, Apr. 2022, doi: 10.1149/10701.5059ecst.

A. L. C. Ottoni, M. S. Novo, and M. S. Oliveira, “A Statistical Approach to Hyperparameter Tuning of Deep Learning for Construction Machine Classification,” Arab. J. Sci. Eng., vol. 49, no. 4, pp. 5117–5128, 2024, doi: 10.1007/s13369-023-08330-6.

A. Pimpalkar, D. K. J. B. Saini, N. Shelke, A. Balodi, G. Rapate, and M. Tolani, “Fine-tuned deep learning models for early detection and classification of kidney conditions in CT imaging,” Sci. Rep., vol. 15, no. 1, pp. 1–20, 2025, doi: 10.1038/s41598-025-94905-2.

A. Amini, M. Dolatshahi, and R. Kerachian, “Effects of Automatic Hyperparameter Tuning on the Performance of Multi-Variate Deep Learning-Based Rainfall Nowcasting,” Water Resour. Res., vol. 59, no. 1, 2023, doi: 10.1029/2022WR032789.

S. S. L. Parvathi and H. Jonnadula, “An Efficient and Optimal Deep Learning Architecture using Custom U-Net and Mask R-CNN Models for Kidney Tumor Semantic Segmentation,” Int. J. Adv. Comput. Sci. Appl., vol. 13, no. 6, pp. 314–320, 2022, doi: 10.14569/IJACSA.2022.0130639.

D. Lubis et al., “Deteksi Ginjal Berdasarkan Citra CT Scan Dengan Algoritma Convolution Neural Network Kidney CYST Detection Based On CT Scan Image With Convolution Neural Network Algorithm,” J. Pendidik. dan Teknol. Indones., vol. 4, no. 11, pp. 369–375, 2024.

M. N. Islam and M. H. K. Mehedi, “CT KIDNEY DATASET: Normal-Cyst-Tumor and Stone,” 2022. https://www.kaggle.com/datasets/nazmul0087/ct-kidney-dataset-normal-cyst-tumor-and-stone.

M. N. Islam, M. Hasan, M. K. Hossain, M. G. R. Alam, M. Z. Uddin, and A. Soylu, “Vision transformer and explainable transfer learning models for auto detection of kidney cyst, stone and tumor from CT-radiography,” Sci. Rep., vol. 12, no. 1, pp. 1–14, 2022, doi: 10.1038/s41598-022-15634-4.