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.
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.
Diabetic Retinopathy (DR) is a common complication among diabetes patients that can cause vision impairment owing to lesions on the retina. Late-stage discovery of DR often leads to irreversible blindness. The usual approach of diagnosing DR through retinal fundus imaging by ophthalmologists is both time-consuming and costly. Although classical transfer learning methods have been extensively employed for computer-aided DR detection, their high maintenance costs can restrict their performance. In contrast, Quantum Transfer Learning is projected to provide a more effective solution to this difficulty, acting on heuristic principles and being highly optimized for the task. Our suggested method will exploit this hybrid quantum transfer learning mechanism to detect DR. We propose to utilize the Blindness Detection dataset from Kaggle to develop our model, leveraging pre-trained classical neural networks for initial feature extraction. For the classification stage, we will utilize a Variational Quantum Classifier. This future effort seeks to prove that quantum computing, coupled with quantum machine learning, can do tasks with a level of power and efficiency unattainable by classical computers alone. By harnessing these new technologies, we intend to greatly enhance the identification and diagnosis of Diabetic Retinopathy, perhaps saving many from the risk of blindness
Diabetic Retinopathy (DR), a diabetes-related eye condition, damages retinal blood vessels and can lead to vision loss if undetected early. Precise diagnosis is challenging due to subtle, varied symptoms. While classical deep learning (DL) models like CNNs and ResNet's are widely used, they face resource and accuracy limitations. Quantum computing, leveraging quantum mechanics, offers revolutionary potential for faster problem-solving across fields like cryptography, optimization, and medicine. This research introduces QuantumNet, a hybrid model combining classical DL and quantum transfer learning to enhance DR detection. QuantumNet demonstrates high accuracy and resource efficiency, providing a transformative solution for DR detection and broader medical imaging applications. The method is as follows:•Evaluate three classical deep learning models-CNN, ResNet50, and MobileNetV2-using the APTOS 2019 blindness detection dataset on Kaggle to identify the best-performing model for integration.•QuantumNet combines the best-performing classical DL model for feature extraction with a variational quantum classifier, leveraging quantum transfer learning for enhanced diagnostics, validated statistically and on Google Cirq using standard metrics.•QuantumNet achieves 94.11 % accuracy, surpassing classical DL models and prior research by 11.93 percentage points, demonstrating its potential for accurate, efficient DR detection and broader medical imaging applications.
Diabetic Retinopathy (DR) is a common complication of diabetes mellitus that causes lesions on the retina that affect vision. Late detection of DR can lead to irreversible blindness. The manual diagnosis process of DR retina fundus images by ophthalmologists is time consuming and costly. While, Classical Transfer learning models are extensively used for computer aided detection of DR; however, their maintenance costs limits detection performance rate. Therefore, Quantum Transfer learning is a better option to address this problem in an optimized manner. The significance of Hybrid quantum transfer learning approach includes that it performs heuristically. Thus, our proposed methodology aims to detect DR using a hybrid quantum transfer learning approach. To build our model we extract the APTOS 2019 Blindness Detection dataset from Kaggle and used inception-V3 pre-trained classical neural network for feature extraction and Variational Quantum classifier for stratification and trained our model on Penny Lane default device, IBM Qiskit BasicAer device and Google Cirq Simulator device. Both models are built based on PyTorch machine learning library. We bring about a contrast performance rate between classical and quantum models. Our proposed model achieves an accuracy of 93%–96% on the quantum hybrid model and 85% accuracy rate on the classical model. So, quantum computing can harness quantum machine learning to do work with power and efficiency that is not possible for classical computers.
Diabetic Retinopathy (DR) is a severe complication of diabetes, characterized by damage to the blood vessels in the retina, leading to an increased risk of vision loss or blindness. Patients with diabetes who develop DR face a significant risk of visual impairment, underscoring the need for advanced and reliable diagnostic tools. This research addresses this need by introducing a hybrid Quantum Convolutional Neural Network (QCNN) model, designed specifically for the automated detection of DR. By leveraging quantum principles and classical deep learning, this model provides a powerful approach to screening for diabetic retinopathy. In a Convolutional Neural Network (CNN), convolutional layers are primarily responsible for feature extraction from images, capturing intricate details essential for accurate classification. However, the proposed hybrid QCNN introduces quantum layers in addition to traditional convolutional layers, combining the strengths of both quantum computing and classical neural network structures. Quantum computing principles, such as superposition and entanglement, allow the QCNN to encode and process information in unique ways, enhancing the efficiency of feature extraction and the overall performance of the model. Superposition enables the QCNN to represent and manipulate multiple states simultaneously, while entanglement allows for a more complex, interconnected representation of image features. These quantum properties enable the QCNN to explore a broader feature space, offering richer representations of the retinal images than those achievable through classical methods alone. Evaluation of the model’s performance reveals that the QCNN surpasses a traditional CNN in both accuracy and diagnostic performance. This improvement suggests that hybrid QCNN models hold significant promise for enhancing diabetic retinopathy screening, paving the way for earlier diagnosis and better patient outcomes. Future research will focus on refining the hybrid QCNN model to improve its robustness and adaptability, aiming to ensure its effectiveness in real-world healthcare environments.
Traditional convolutional neural networks (CNNs) have shown potential for recognizing retinopathy caused by diabetes (DR). However, developing quantum computing has the possibility for improved feature representation. We propose a hybrid approach that combines classical CNNs with quantum circuits to capitalize on both classical and quantum information for DR classification. Using the Keras and Qiskit frameworks, our model encodes picture features into quantum states, allowing for richer representations. Through experiments on a collection of retinal pictures, our model displays competitive performance, with excellent reliability and precision in categorizing DR severity levels. This combination of classical and quantum paradigms offers a fresh approach to enhancing DR diagnosis and therapy.
Abstract This study demonstrates that a hybrid CNN–QNN architecture outperforms classical CNNs for multi-class retinal OCT classification by leveraging variational quantum circuits to enhance feature separability. Early detection of retinal diseases through optical coherence tomography (OCT) imaging is critical for timely intervention and vision preservation. While classical convolutional neural networks (CNNs) excel at pattern recognition in retinal OCT B-scans, their ability to capture complex, non-linear feature relationships in subtle disease manifestations remains limited. Hybrid quantum-classical architectures offer a promising approach by leveraging variational quantum circuits to enhance feature separability in challenging classification regimes. This study presents a hybrid CNN–QNN architecture for multi-class classification of retinal OCT images dataset (CNV, DME, DRUSEN, NORMAL). A classical CNN backbone extracts hierarchical spatial features from B-scans, which are then processed through parallel classical and quantum classification heads. The quantum head employs a 5-qubit variational quantum circuit with angle embedding and strongly entangling layers to generate quantum-enhanced feature representations. Outputs from both heads are concatenated and passed through a final softmax layer for four-class prediction. The findings establish hybrid quantum-classical neural networks as a viable enhancement to conventional deep learning for retinal OCT analysis, offering improved discriminative performance on established medical imaging benchmarks through quantum feature transformations.