MUMBAI, India, Aug. 31 -- Intellectual Property India has published a patent application (202641100126 A) filed by Karpagam College Of Engineering; Karpagam Academy Of Higher Education; Dr. P. Shanthi; and Mr S Yogesh on August 19, 2026, for A Resource-Efficient Hybrid Quantum–classical Framework For Multi-Class Skin Disease Classification.
Inventors include Dr. P. Shanthi; and Mr S Yogesh.
The application for the patent was published on August 28, 2026, under issue no. 35/2026.
Abstract: Skin diseases are among the most common health problems worldwide, and their accurate identification is often challenging due to the strong visual similarity between different disease categories. Conventional deep learning models used for automated skin disease classification require large labelled datasets and high computational resources, making them unsuitable for resource-constrained environments. To overcome these limitations, this project proposes a resource-efficient hybrid quantum–classical framework for multi-class skin disease classification. In the proposed system, a pre-trained ResNet50 model is used for deep feature extraction from skin lesion images. The extracted high-dimensional feature vectors are reduced using Principal Component Analysis (PCA) to make them compatible with quantum processing and to minimize quantum resource requirements. The compressed features are then encoded into quantum states and processed using a Variational Quantum Classifier (VQC). The parameters of the quantum circuit are optimized using the Simultaneous Perturbation Stochastic Approximation (SPSA) algorithm, which is well suited for noisy intermediate-scale quantum (NISQ) environments. The hybrid approach effectively combines the strengths of classical deep learning and quantum machine learning to improve classification performance while maintaining computational efficiency. The proposed system is scalable, cost-effective, and suitable for implementation on near-term quantum devices, thereby supporting the development of intelligent and low-cost medical diagnostic solutions.
Disclaimer: Curated by HT Syndication.
