Quantum Transfer Learning for Diagnosis of Diabetic Retinopathy

doi:10.1109/ICITIIT54346.2022.9744184

Paper

Quantum Transfer Learning for Diagnosis of Diabetic Retinopathy

Published Feb 12, 2022 · S. S, K. T, Sayantan Bhattacharjee

2022 International Conference on Innovative Trends in Information Technology (ICITIIT)

11

Citations

0

Influential Citations

Full textSemantic Scholar

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.

Study Snapshot

Quantum Transfer Learning (QTL) model provides accurate and faster diagnosis of diabetic retinopathy from optical coherence tomography images, outperforming existing methods with limited datasets.

PopulationOlder adults (50-71 years)

Sample size24

MethodsObservational

OutcomesBody Mass Index projections

ResultsSocial networks mitigate obesity in older groups.

Quantum Transfer Learning for Diagnosis of Diabetic Retinopathy

References

Citations