A Comprehensive Framework for Kidney Stone Diagnosis: Merging CNN and SVM with GUI Integration

Main Article Content

Karthikeyan A, Pramodgouda N P, Preetham A G, Rakshith Kumar S M, Tushar B Javalli, Melwin D Souza,

Abstract

This research explores the application of deep learning for kidney stone detection, leveraging medical imaging data and artificial intelligence (AI) to identify and classify stones within medical images. By streamlining the diagnostic process, these AI-driven approaches reduce costs and time and facilitate early diagnosis and treatment. The model effectively detects kidney stones of varying sizes and shapes, addressing challenges posed by different stone compositions and human anatomical variability. With rapid processing speeds, the deep learning model is well-suited for real-time clinical applications. Employing convolutional neural networks (CNNs), recognized for their prowess in image recognition, the models are trained on annotated ultrasound images to automate kidney stone detection with high precision and sensitivity. The results indicate marked improvements in detection accuracy over traditional methods, showcasing the performance capabilities of the AI-enhanced system. This study offers valuable insights and methodologies that inform future advancements in AI-assisted medical imaging and healthcare, significantly enhancing the accuracy and efficiency of kidney stone detection, thereby benefiting both patients and healthcare practitioners globally

Article Details

Section
Articles