Hybrid Image Processing and Deep Learning System for Early Detection and Classification of Kidney Stones with IoT-Based Patient Monitoring

Author(s)	Dr. Rajshree
Country	India
Abstract	Kidney stone disease (urolithiasis) is a prevalent urological disorder that often remains undetected in its early stages, leading to severe pain and long-term renal complications. Accurate diagnosis requires expert interpretation of medical images, which is not suitable for continuous monitoring. This paper proposes a hybrid framework that integrates advanced image processing, convolutional neural network (CNN) classification, and Internet of Things (IoT)–enabled patient monitoring. Renal ultrasound and CT images undergo preprocessing, including median filtering, contrast-limited adaptive histogram equalization (CLAHE), and intensity normalization, followed by hybrid segmentation to enhance stone visibility. The CNN classifies images into four categories based on stone size: no stone, small, medium, and large. IoT sensors continuously monitor physiological and lifestyle parameters and transmit data to a cloud platform for real-time analysis and alert generation. The proposed hybrid framework achieved 94.3% accuracy, outperforming CNN-only approaches by 4.7%, demonstrating improved early-stage kidney stone detection and real-time patient monitoring.
Keywords	Urolithiasis, kidney stone detection, hybrid image processing, deep learning, CNN, IoT healthcare monitoring, medical imaging
Field	Computer
Published In	Volume 7, Issue 4, July-August 2025
Published On	2025-08-09
DOI	https://doi.org/10.36948/ijfmr.2025.v07i04.67397

About IJFMR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9687-828-838	editor@ijfmr.com

International Journal For Multidisciplinary Research