• Prof. Mote A. G.
• Miss.Kandepalli A.K.

Kidney disease represents a significant global health issue, often identified at later stages due to mild early indicators. This research presents a deep Convolutional Neural Network (CNN) methodology for multi-classifying kidney ailments—Cyst, Tumor, Stone, and Normal—through the use of computed tomography (CT) images. Utilizing a dataset consisting of 12,446 labeled CT images, the model incorporates sophisticated CNN layers along with batch normalization and max-pooling techniques for effective feature extraction and classification. The confusion matrix and F1-scores validate the model's effectiveness, with optimal performance noted in identifying Cysts and Tumors. The introduced model also shows efficiency regarding parameter count (approximately 2.87 million), making it appropriate for clinical use on devices with limited resources.The model was trained and validated using a preprocessed dataset, resulting in an overall accuracy of 99.68%, along with precision and recall rates surpassing 99% for every class. This study underscores the capability of CNNs to improve diagnostic precision and assist in the early identification of kidney issues, ultimately enhancing patient outcomes and aiding radiologists in their clinical decisions.The CNN framework consists of several convolutional layers, batch normalization, and dense layers ending with a softmax classification. This model facilitates the automation of diagnosing kidney disease, which could significantly change the screening procedures in healthcare environments.

tomography, dataset, diagnosis..

"An Enhanced Deep CNN Approach for Accurate Multi-Class Classification of Kidney Abnormalities in CT Imaging.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.12, Issue 7, page no.h354-h356, July-2025, Available :http://www.jetir.org/papers/JETIR2507745.pdf

"An Enhanced Deep CNN Approach for Accurate Multi-Class Classification of Kidney Abnormalities in CT Imaging.", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.12, Issue 7, page no. pph354-h356, July-2025, Available at : http://www.jetir.org/papers/JETIR2507745.pdf