Kidney Diseases Classification Based on CT-Radiography Image Using Convolutional Neural Network ResNet-50

In 2022, kidney disease is impacting over 10% of the global population, which amounts over 800 million individuals. Kidney disease is projected to become the fifth most significant cause of mortality by 2040. Nephrolithiasis (kidney stones), kidney cysts, and Renal Cell Carcinoma (kidney tumor), are three kidney disease that can impair kidney function. Diagnosing kidney disease is crucial before any treatment can be given. Computer Tomography (CT) Radiography images can be used to determine the kind and severity of the disease. The obtained imaging data reveals normal findings and three specific kidney disease: cysts, tumors, and nephrolithiasis. The purpose of this research is to evaluate the efficacy of the Convolutional Neural Network (CNN) ResNet-50 with a hyperparameter tuning experiments in diagnose kidney disease based on the findings of kidney disease clasifyed. The greatest outcomes in this research were achieved with a learning rate of 0.001, dropout probability of 0.1, and mini batch size of 32. The experiments yielded perfect sensitivity, accuracy, and specificity, all reaching 100%. The computation time required was 15 hours, 53 minutes, and 34 seconds. The CNN ResNet-50 ability to accurately diagnose kidney disease is demonstrated by these result.

Authors

Institutions

Publication Details

Journal
Journal of Artificial Intelligence and Technology Information (JAITI)
Published
2026-11-14
DOI
https://doi.org/10.58602/jaiti.v4i4.458
Primary Topic
AI in cancer detection
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Kidney Diseases Classification Based on CT-Radiography Image Using Convolutional Neural Network ResNet-50

Icha Dwi Safira, Dian Candra Rini Novitasari
Journal of Artificial Intelligence and Technology Information (JAITI)
AI in cancer detection
article

Kidney Diseases Classification Based on CT-Radiography Image Using Convolutional Neural Network ResNet-50

Icha Dwi Safira, Dian Candra Rini Novitasari
article en

Abstract

In 2022, kidney disease is impacting over 10% of the global population, which amounts over 800 million individuals. Kidney disease is projected to become the fifth most significant cause of mortality by 2040. Nephrolithiasis (kidney stones), kidney cysts, and Renal Cell Carcinoma (kidney tumor), are three kidney disease that can impair kidney function. Diagnosing kidney disease is crucial before any treatment can be given. Computer Tomography (CT) Radiography images can be used to determine the kind and severity of the disease. The obtained imaging data reveals normal findings and three specific kidney disease: cysts, tumors, and nephrolithiasis. The purpose of this research is to evaluate the efficacy of the Convolutional Neural Network (CNN) ResNet-50 with a hyperparameter tuning experiments in diagnose kidney disease based on the findings of kidney disease clasifyed. The greatest outcomes in this research were achieved with a learning rate of 0.001, dropout probability of 0.1, and mini batch size of 32. The experiments yielded perfect sensitivity, accuracy, and specificity, all reaching 100%. The computation time required was 15 hours, 53 minutes, and 34 seconds. The CNN ResNet-50 ability to accurately diagnose kidney disease is demonstrated by these result.

Journal of Artificial Intelligence and Technology Information (JAITI)Vol. 4(4)
UIN Sunan Ampel Surabaya (ID)
AI in cancer detection
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon