Innovative Pixel Division and Block Summing (PDBC) Model For Image Feature Extraction and Kidney Disease Classification

Efficient and precise feature extraction is critical in medical image analysis for accurate illness Classification. Traditional approaches frequently fail to strike a compromise between computational efficiency and important feature conservation. Given the kidney’s crucial role in filtering waste from the blood and maintaining general physiological balance, accurate and timely identification of renal illnesses is critical. This paper describes the Innovative Pixel Division and Block Summing (PDBS) Model, a novel method for improving image feature extraction and kidney disease Classification by transforming pixel values to encode spatial relationships between pixels, thereby increasing computational efficiency while preserving critical information. The PDBS model’s efficacy is carefully tested on a kidney disease dataset. Our results demonstrate the PDBS model’s superior performance, achieving a 100% training accuracy and a test accuracy of 99.92%, significantly outperforming traditional models such as CNNs, VGG-16, and ResNet. The PDBS model shows substantial promise in various applications, including medical imaging, enhancing diagnostic accuracy and efficiency in renal disease management.