MUMBAI, India, June 30 -- Intellectual Property India has published a patent application (202641073906 A) filed by Sona College Of Technology on June 15, 2026, for System And Method For Adaptive Parkinson’s Disease Screening Using Hand-Drawn Spiral And Wave Image Analysis.
Inventors include Sakthivel P; Jayaprakash D; Syed Fiaz A S; Mohanraj B; Sindhu L; Sanjay P; Vishnu M; and Vimal M.
The application for the patent was published on June 26, 2026, under issue no. 26/2026.
Abstract: ABSTRACT The present invention relates to a computer-implemented system and method for adaptive screening of Parkinson’s Disease (PD) using hand-drawn spiral and wave image biomarkers. The system comprises an image acquisition module configured to receive digitized drawings, a preprocessing module for performing noise reduction, contrast enhancement, segmentation, and normalization, and a feature extraction module for generating multi-domain features including geometric, stroke- based, frequency-domain, texture, and complexity descriptors. A classification module employing an ensemble of machine learning models, including Support Vector Machine (SVM), Random Forest (RF), and Convolutional Neural Network (CNN), is configured to classify the extracted features. A reinforcement learning (RL) controller dynamically optimizes preprocessing parameters, feature selection, and classification pathways based on a reward-feedback mechanism. The system iteratively updates a policy to adapt to varying input conditions and improve diagnostic reliability. The invention enables non-invasive, scalable, and adaptive screening of Parkinson’s Disease with reduced dependency on static processing pipelines and manual parameter tuning.
Disclaimer: Curated by HT Syndication.
