MUMBAI, India, Oct. 5 -- Intellectual Property India has published a patent application (202641115717 A) filed by Vellore Institute Of Technology on September 28, 2026, for System And Method For Multi-Stage Classification Of Ear Conditions Using Otoscopic Images.
Inventors include Priya Ponnuswamy; and Renuka A.
The application for the patent was published on October 02, 2026, under issue no. 40/2026.
Abstract: The present invention relates to a system and method for multi-stage classification of ear conditions using otoscopic images. The system (100) comprises an otoscopic image upload module (102), an image preprocessing module (104), a deep learning processing module (106), a first-stage classification module (108), an abnormal- condition routing module (114), a disease identification module (116), a prediction confidence generation module (118), a visualization module (120), a segmentation mask generation module (122), a region-of-interest display module (124), and a result generation module (128). The preprocessing module (104) standardizes received otoscopic images for analysis. The first-stage classification module (108) performs binary classification, and the disease identification module (116) performs classification among multiple ear condition categories. The visualization module (120) generates class-discriminative visual outputs, while the segmentation mask generation module (122) generates segmented regions of interest. The invention provides an integrated framework for hierarchical classification, visualization, segmentation, and result generation from otoscopic image data.
Disclaimer: Curated by HT Syndication.
