Karim, Dewan ZiaulHridoy, Md. Farhan RakibAsif, AhnafMahmud, MashrufRahman, RashadSiraj, Md Sahin2024-11-212024-11-21©20242024-05ID 18201070ID 18201075ID 18201084ID 18301004ID 18201104http://hdl.handle.net/10361/24813Catalogued from PDF version of thesis.Includes bibliographical references (pages 30-31).This thesis is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2024.Chronic kidney disease (CKD) is a significant global health concern, impacting more than 800 million people globally. Prompt identification and precise categorization are crucial for optimal therapy. The primary objective of this study is to create a sophisticated machine learning algorithm that can effectively identify and categorise Chronic Kidney Disease (CKD). We use a convolutional neural network (CNN) to examine medical imaging data, namely CT scan pictures. The full dataset was partitioned into training, validation, and testing subsets, and the performance of several pre-trained models, including VGG16, ResNet50, and EfficientNetB0, was assessed. The CNN model suggested obtained exceptional outcomes, showcasing substantial promise in differentiating between normal and diseased kidney states and precisely categorising CKD phases. The model attained a training accuracy of 97.05% and a validation accuracy of 91.79%. The findings emphasise the capability of our technology to aid healthcare practitioners in making prompt and precise choices about the diagnosis and treatment of CKD.41 pagesenBrac University theses are protected by copyright. They may be viewed from this source for any purpose, but reproduction or distribution in any format is prohibited without written permission.Disease detectionKidney diseaseCNNConvolutional neural networkMachine learningImage analysisArtificial intelligence--Medical applications.Neural networks (Computer science).Kidneys--Diseases--Diagnosis.Thesis