MUMBAI, India, Oct. 26 -- Intellectual Property India has published a patent application (202611113301 A) filed by Ajay Kumar Garg Engineering College on September 22, 2026, for Machine Learning System And Method For Classification Of Fetal Ultrasound Abnormalities.
Inventors include Devansh Gupta; Ateendra Pratap Solanki; Chanderant Sharma; Mohit Kekariya; and Dr. Sachin Jain.
The application for the patent was published on October 23, 2026, under issue no. 43/2026.
Abstract: A system (100) and method (200) for classification of fetal ultrasound abnormalities are disclosed. A fetal ultrasound image is preprocessed and supplied to a feature extraction module (106) comprising a frozen, pre-trained convolutional neural network, which generates a fixed-length feature vector. A stratified dataset splitting module (110) divides labelled feature vectors, obtained via an automated folder-based labelling module (124), into training and validation sets. A multi-classifier training module (116) trains a plurality of classical machine learning classifiers (116a, 116b, 116c) on the feature vectors, and a benchmarking and selection unit (118) evaluates and automatically selects the best-performing classifier (120) for deployment. A hardware adaptation module (122) enables execution on either GPU or CPU. The invention reduces computational overhead, reduces labelled-data requirements, and enables fast, consistent, deployable classification of fetal ultrasound images as Normal, Benign or Malignant. Referring to Figure 1 and 2
Disclaimer: Curated by HT Syndication.
