A Model for Screening Patients with Kidney Stones using Image Classification Techniques

Main Article Content

Anupong Sukprasert
Namfon Dangphongthong
Theerayuthr Chantra

Abstract

The research aims to create a model for screening patients with kidney stones in the kidney, using images of patients diagnosed. A total of 6,454 images were collected from various hospitals in the city of Thakarpa, Bangladesh. The data was analyzed using the cross industry standard process for data mining (CRISP-DM), using the 4 techniques of image classification: Support Vector Machines, k-Nearest Neighbors, Naive Bayes and Random Forest. To test the performance of Image classification using Accuracy, Sensitivity, Specificity, and F-measure. The research found that the K-NN nearest neighbor is the most suitable for building a model to screen kidney stones effectively and efficiently in patients.

Article Details

How to Cite
Sukprasert, A., Dangphongthong, N., & Chantra, T. (2024). A Model for Screening Patients with Kidney Stones using Image Classification Techniques. Journal of Science Innovation for Sustainable Development, 5(1), 12–23. retrieved from https://ph01.tci-thaijo.org/index.php/JSISD/article/view/252001
Section
Original Article

References

Laongkum, A., and Kumeechai, P. (2020). Implementation of classification system for Buddha amulet using GLCM and Wavelet Transform and using Neural Network for classify. Royal Thai Naval Academy Journal of Science and Technology, 3(1), 9-20. [In Thai].

Sukprasert, A. (2021). Data Mining with RapidMiner Studio. Mahasarakham University. Mahasarakham Business School. [In Thai].

Promkasikorn, L. (2015). The factors predicting the health behaviors related to the occurrence of kidney stone formation among kidney stone disease patients. (Master’s thesis). Thammasat University, Faculty of Nursing, Department of Adult Nursing and the Aged. [In Thai].

MD. Mehedi, K, H. (2022). CT kidney dataset: normal-cyst-tumor and stone. Retrieved from https://www.kaggle.com/datasets/nazmul0087/ct-kidney-dataset-normal-cyst-tumor-and-stone.

Nonsiri, N., Chaichitwanidchakol, P., and Somkantha, K. (2022). Data classification for diabetes risk diagnosis using majority voting ensemble method and forward feature selection method. Udon Thani Rajabhat University Journal of Sciences and Technology, 10(2), 107–122. [In Thai].

Qadri, S. (2021). Role of machine vision for identification of kidney stones using multi features analysis. Lahore Garrison University Research Journal of Computer Science and Information Technology, 5(3), 1-14.

Verma, J., Nath, M., Tripathi, P. & Saini, K. K. (2017). Analysis and identification of kidney stone using Kth Nearest Neighbour (KNN) and Support Vector Machine (SVM) classification techniques. Pattern Recognition and Image Analysis, 27, 574-580.

Pakkasung, Y., Methakanjanasak, N., and Theeranut, A. (2019). Illness perception of patient with recurrent renal stone and chronic kidney disease. Journal of Nursing and Health Care, 37(1), 249-257. [In Thai].