MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541124385 A) filed by Vishnu Institute Of Technology, Kovvada, Andhra Pradesh, on Dec. 10, 2025, for 'deep convolutional neural network for optimized skin cancer classification.'
Inventor(s) include Abdul Rahman Shaik; and K. Kiran.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The invention discloses a deep convolutional neural network (DCNN) with fine-tuned hyperparameters for accurate classification of skin cancer using dermoscopic images. The system includes a preprocessing module for image normalization and augmentation, followed by a multi-layer DCNN architecture designed to extract hierarchical lesion features. Hyperparameters such as learning rate, kernel size, dropout ratio, batch size, and epochs are optimized to improve convergence, reduce overfitting, and enhance diagnostic accuracy. A softmax-based classifier identifies malignant and benign lesions with high reliability. The invention overcomes limitations of conventional CNN and transfer-learning models by offering improved robustness across diverse datasets and enabling scalable deployment in clinical, telemedicine, and mobile diagnostic environments."
Disclaimer: Curated by HT Syndication.
