Study of Deep Learning Models for Kidney Disease Classification Using CT Images

Salokhe, Dheeraj Atul (2024) Study of Deep Learning Models for Kidney Disease Classification Using CT Images. Masters thesis, Dublin, National College of Ireland.

Preview	PDF (Master of Science) Download (1MB) | Preview
Preview	PDF (Configuration Manual) Download (1MB) | Preview

Abstract

Kidney disease represents a major global health problem that is commonly caused by diabetes and hypertension and, if not addressed early, can be serious. In this study, deep learning is used to automate the classification of kidney conditions—normal, cyst, stone, and tumor— on CT images. The research aims at using deep learning models for the classification of the kidney states: normal, cyst, stone, and tumor using a dataset of CT scans of 12,446 labels sourced from Kaggle. Based on the deep learning architecture, the performance of four categories of models for kidney disease classification was analyzed, including MobileNetV2, InceptionV3, EfficientNetB0, and ResNet50. To enhance interpretability, Grad-CAM visualizations were used to detect areas of pathology within CT images. Among the models, the model called InceptionV3 provides the highest classification accuracy and is equal to 99.82%, which is higher than the results of similar studies on the use of InceptionV3, according to which the accuracy of their work was 94%. This further shows how InceptionV3 can manage advanced medical imaging data information. The outcomes reveal that the contemporary deep learning frameworks can be used as dependable diagnostic assets to increase diagnostic precision and lessen the ambiguity for superior consequences compared to CNN conventional approaches. This study shows the significance of applying advanced models for evaluating difficulties in medical imaging to enhance diagnostics and determine further therapy for kidney diseases.

Item Type:	Thesis (Masters)
Supervisors:	Name Email Singh, Jaswinder UNSPECIFIED
Subjects:	Q Science > QA Mathematics > Electronic computers. Computer science T Technology > T Technology (General) > Information Technology > Electronic computers. Computer science R Medicine > Healthcare Industry Q Science > Q Science (General) > Self-organizing systems. Conscious automata > Machine learning
Divisions:	School of Computing > Master of Science in Data Analytics
Depositing User:	Ciara O'Brien
Date Deposited:	04 Sep 2025 13:41
Last Modified:	04 Sep 2025 13:41
URI:	https://norma.ncirl.ie/id/eprint/8792

Actions (login required)

View Item