Quantum Transfer Learning for Diagnosis of Diabetic Retinopathy
Abstract
India is on track to become the world’s diabetes capital thus demanding accurate diagnosis of Diabetic retinopathy from optical coherence tomography (OCT) retinal images. Accurate and faster diagnosis is difficult as it depends on quality of image, operator handling and also the growing number of patients. In this paper we propose the use of quantum transfer learning model to accomplish diagnosis of Diabetic Retinopathy. Quantum Transfer Learning (QTL), is a hybrid combination of classical transfer learning and quantum computing. Unlike classical computers, quantum computers provide faster computation and better accuracy. The concept of QTL is mainly used where the dataset size is limited. The QTL model, diagnostically significant image features are extracted with Resnet18 Convolutional Neural NEtwork (CNN) model, which is reduced to 4-bit feature vector to be encoded as qubit and is finally classified by utilizing Variational Quantum Circuit (VQC). The proposed model gave a better accuracy than existing state of the art methods in terms of high accuracy despite with a smaller set of images in the training phase.
Read the paper
Related studies
- In silico toxicology protocols
- QM7-X, a comprehensive dataset of quantum-mechanical properties spanning the chemical space of small organic molecules
- Quantum Informed Machine-Learning Potentials for Molecular Dynamics Simulations of CO2's Chemisorption and Diffusion in Mg-MOF-74
- In-silico strategies in nano-drug design: Bridging nanomaterials and pharmacological applications
- mRNA codon optimization with quantum computers
- The computational power of the human brain
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.