Revolutionizing Kidney Disease Diagnosis: A Comprehensive CNN-Based Framework for Multi-Class CT Classification
Gunjan Sharma, Vatsala Anand, Rahul Singh Chauhan, Hemant Singh Pokhariya, Sheifali Gupta, G Sunil · 2024
A major global health concern, kidney infections are linked to rising death rates, especially when they worsen and cause the breakdown of the kidneys. Kidney function is seriously threatened by common kidney disorders such as nephrolithiasis, kidney tumors, and cyst development. Kidney failure, which can be brought on by conditions including tumors, stones, and cysts, can be avoided with prompt diagnosis and treatment. Computer-aided diagnostics are essential due to the rising incidence of chronic renal illness, the lack of specialists, and the increased need for evaluation and monitoring. Though artificial intelligence (AI) methods, such as machine and deep learning, have been investigated for the identification of renal illness, their effectiveness is still lacking. In order to fill this gap, this study implements a deep learning-based Convolutional Neural Network (CNN) model for kidney illness prognosis and classification using a benchmark kidney dataset from Computed Tomography. CNN uses data reprocessing to extract features from the CT images. The results show how effective the suggested method is in correctly classifying renal illness, with a noteworthy accuracy of 99.88%, precision of 99.8%, recall of 99.7%, and an F1-score of 0.98. This work represents a potential development in the field of computer-assisted renal health diagnostics by supporting the use of the refined CNN model as a trustworthy instrument for kidney illness identification. This research can be applied in the medical field for the diagnosis of kidney diseases.