Kidney Disease Classification Using Machine Learning Approach on DenseNet201 Model using Xray Images

Kidney Disease Classification involves classifying kidney images or patient data into different disease categories, such as chronic kidney disease (CKD) stages, polycystic kidney disease (PKD), kidney stones, renal tumours, or other kidney-related disorders. Machine learning algorithms can be traine...

Full description

Saved in:
Bibliographic Details
Published in2023 First International Conference on Advances in Electrical, Electronics and Computational Intelligence (ICAEECI) pp. 1 - 4
Main Authors Gill, Kanwarpartap Singh, Anand, Vatsala, Gupta, Rupesh
Format Conference Proceeding
LanguageEnglish
Published IEEE 19.10.2023
Subjects
Chronic kidney disease
Classification
CNN
Confusion matrix
Deep learning
DenseNet201 Model
Ethics
Kidney Disease
Lesions
Machine learning algorithms
Model Training
Planning
Teamwork
Online AccessGet full text

Cover

More Information
Summary:Kidney Disease Classification involves classifying kidney images or patient data into different disease categories, such as chronic kidney disease (CKD) stages, polycystic kidney disease (PKD), kidney stones, renal tumours, or other kidney-related disorders. Machine learning algorithms can be trained on labelled datasets to automatically identify and classify these conditions. Kidney Disease Classification focuses specifically on classifying kidney tumours or lesions into different types, such as renal cell carcinoma (RCC), angiomyolipoma (AML), oncocytoma, or other benign or malignant tumour subtypes. This classification can assist in the diagnosis and treatment planning for patients with kidney tumours. For patients who have undergone kidney transplantation, Kidney Disease Classification involves classifying biopsy samples to determine whether the transplanted kidney is experiencing rejection. The classification can include categories like acute cellular rejection, acute antibody-mediated rejection, chronic rejection, or no rejection. The development of new features or feature combinations that might improve classification accuracy is made possible by social research in this area and improve quality of life. Doing a Xray classification based on deep learning that can detect kidney disease and that is the goal of this project to improve patient's health. With a 97% accuracy rate, our DenseNet201 model was shown to have strong classification skills for diagnosing renal illness.
DOI:10.1109/ICAEECI58247.2023.10370846