MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202641079719 A) filed by Sona College Of Technology on June 29, 2026, for Hardware-Integrated Dual-Path Deep Learning System For Automated Leukemia Cell Classification.
Inventors include Selvanathan N; Murali M; Karthick K; Dharshan K; Dhipak Darrsan R; and Jairam Kumar V.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: ABSTRACT The present invention relates to a hardware-integrated system and method for automated detection and classification of leukemia cells from microscopic blood smear images. The system comprises an image acquisition module configured to capture blood smear images, a preprocessing module for image standardization, a first feature extraction engine for extracting local cellular morphological features, and a second feature extraction engine for extracting global contextual morphological features. The outputs of the two feature extraction engines are processed through a correlation-based feature fusion module to generate a unified feature representation. A classification module analyzes the fused feature representation and assigns the image to one of a plurality of leukemia-related diagnostic categories. An output module generates diagnostic results, confidence scores, and reporting information. The parallel dual-path architecture enables simultaneous extraction of complementary cellular and contextual characteristics, thereby improving diagnostic accuracy, robustness, and reproducibility. The invention is suitable for deployment in clinical laboratories, digital pathology systems, and automated medical diagnostic platforms.
Disclaimer: Curated by HT Syndication.
