Quantum machine learning by superposition and entanglement, for disease categorization utilizing OCT images will be discussed in this paper. To the best of our knowledge, this is the first application of the quantum computing element in a neural network model for classifying ophthalmological disease. The model was built and tested with PennyLane (PennyLane.ai), an open-source software tool based on the concept of quantum differentiable programming. The model training circuit functioning was tested on an IBM 5 qubits system “ibmq_belem” and a 32 qubits simulator “ibmq. qasm_simulator”. A hybrid quantum and classical model with a 2 qubit QNode converted layer with operations such as Angle Embedding, BasicEntanglerLayers and measurements were the internal operations of the qlayer. Drusen, Choroidal neovascularization (CNV), and Diabetic macular edema (DME) OCT images formed the abnormal/disease class. The model was trained using 414 normal and 504 abnormal labelled OCT scans and the validation used 97 and 205 OCT scans. The resulting model had an accuracy of 0.95 in this preliminary 2-class classifier. This study aims to develop a 4-class classifier with 4 qubits and explore the potential of quantum computing for disease categorization. A preliminary performance analysis of quantum Machine Learning, the steps involved, and operational details will be discussed.
Quantum machine learning by superposition and entanglement, for disease categorization utilizing OCT images will be discussed in this paper. To the best of our knowledge, this is the first application of the quantum computing element in a neural network model for classifying ophthalmological disease. The model was built and tested with PennyLane (PennyLane.ai), an open-source software tool based on the concept of quantum differentiable programming. The model training circuit functioning was tested on an IBM 5 qubits system “ibmq_belem” and a 32 qubits simulator “ibmq. qasm_simulator”. A hybrid quantum and classical model with a 2 qubit QNode converted layer with operations such as Angle Embedding, BasicEntanglerLayers and measurements were the internal operations of the qlayer. Drusen, Choroidal neovascularization (CNV), and Diabetic macular edema (DME) OCT images formed the abnormal/disease class. The model was trained using 414 normal and 504 abnormal labelled OCT scans and the validation used 97 and 205 OCT scans. The resulting model had an accuracy of 0.95 in this preliminary 2-class classifier. This study aims to develop a 4-class classifier with 4 qubits and explore the potential of quantum computing for disease categorization. A preliminary performance analysis of quantum Machine Learning, the steps involved, and operational details will be discussed.
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.
Skin diseases affect millions of people worldwide, leading to significant healthcare burdens and challenges in diagnosis and treatment. In the past few years, machine learning techniques have demonstrated potential in assisting dermatologists with diagnosing various skin conditions. As in, conventional machine learning algorithms might encounter challenges in handling the complexity and distinction of skin disease classification tasks, primarily because of the intricate nature of medical image data with its high dimensional properties. In this work, the main analysis is done based on exploring quantum machine learning models for skin disease classification. This approach blends with the aspects of quantum computing with the conventional machine learning techniques to push the boundaries of skin disease classification. This work harnesses the HAM10000 dataset, an extensive compilation of categorized images portraying common skin lesions, to train and assess the efficacy of the proposed methodologies. Quantum computing libraries such as PennyLane and Qiskit is used in this study. Using different combination of qubit rotation encoding and decoding using three types of Pauli gates such as Pauli X, Y and Z gates are implemented and compared using proposed Quanvolutional neural network. Features extracted using MobileNet pre-trained network is used to build Quantum support vector classifier. These quantum machine learning models are compared with some well-known pre-trained models such as Resnet50, Inception-Resnet, Densenet121, DenseNet201 and MobileNet. The combination of RY qubit rotation and PauliZ gate in quantum convolution layer in Quanvolutional neural network produced the optimal classification accuracy of 82.86% more than any other models included in this study. In contrast, Quantum Support Vector Classifier produced similar classification accuracy of 72.5% with respect to pre-trained models.
Glaucoma is a progressive optic neuropathy that leads to irreversible vision loss if not detected early. Automated analysis of retinal images plays an important role in detecting glaucoma-related structural abnormalities; however, conventional image processing and classical machine learning methods often struggle to model complex nonlinear relationships among clinical biomarkers. This study presents a quantum enhanced diagnostic framework for glaucoma detection that encodes retinal structural features into quantum states and analyzes them using quantum machine learning techniques. Optical Coherence Tomography (OCT) provides high-resolution cross-sectional visualization of retinal layers and facilitates quantitative assessment of key biomarkers, including Retinal Nerve Fiber Layer (RNFL) thickness, Ganglion Cell-Inner Plexiform Layer (GCIPL) thickness, and Bruch's Membrane Opening-Minimum Rim Width (BMO-MRW). After normalization, the features are transformed into quantum states via angle encoding and subsequently processed within an entangled quantum circuit. Classification is performed using a Quantum Support Vector Machine (QSVM) with a fidelity-based quantum kernel. Experimental evaluation shows that the proposed model achieves a classification accuracy of 73% on the dataset that shows promising results over classical baseline SVM model. Although classical deep learning models often report higher accuracies, this work demonstrates the feasibility of representing clinically interpretable OCT biomarkers within quantum feature spaces. The study highlights the potential of quantum kernel methods for structured ophthalmic data and provides an initial step toward scalable quantum-assisted glaucoma diagnostic systems as quantum computing technology continues to evolve.
Timely and dependable recognition of eye-related. Addressing diseases is essential for averting irreversible vision impairment. Profound Advancements in medical imaging through learning have been substantial, but numerous existing models continue to struggle with detailed, multi-class assignments, particularly when the categories appear alike or the datasets exhibit imbalance. To fill this gap, we present QEyeNet, a combined quantum-classical system that integrates traditional feature extractors combined with quantum neural networks to categorize 15 eye disorders utilizing fundus imaging and OCT pictures. The quantum layer, designed using variational circuits, enables the model to grasp more complex feature interactions with considerable less parameters than similar traditional systems. In our assessments on meticulously selected datasets, Q-EyeNet demonstrated enhanced diagnostic precision, consistent performance amidst interference, and effective utilization of resources. We likewise noted quantifiable advantages of entanglement-driven feature blending and circuit optimization that takes hardware into account executed on PennyLane. As far as we know, this is the initial confirmed illustration of quantum transfer learning utilized for a intricate eye imaging challenge, providing a hopeful guidance for upcoming computational methods in eye-care diagnostic evaluations
Over the past decade, exceptional progress has been made in deep learning and its applications to medical imaging including image analysis, disease classification, medical image segmentation, and a variety of other tasks. Alzheimer’s disease is a progressive cognitive disorder and the most common cause of dementia in the world. In this research, we present a lightweight hybrid classical-quantum framework leveraging quantum machine learning (QML) using the pennylane library. Consisting of classical convolutional neural network (CNN) and quantum circuits as quantum nodes wrapped in a torch layer of pytorch, the framework has a total of eight layers including the quantum layer, for the classification of Alzheimer’s disease stages from brain MRI images. Using this framework, the 4 -class Alzheimer’s MRI dataset is assessed. This dataset contains 6400 MRI images across four classes of disease stages, available in the Kaggle. The dataset has gone through the Pre-processing stage of augmentation to scale and balance the classes. The proposed hybrid framework achieves an accuracy of 96.26 % in classifying 4 stages of Alzheimer’s Disease, outperforming the classical deep learning models while utilizing substantially fewer parameters. The superior performance of the hybrid framework is compared with the performance of four other classical models: 1. VGG 2. Densenet 3. Enet and 4. Resnet. Grad-CAM (Explainable AI) is employed to assess the proposed framework’s focus on relevant brain regions and to validate its accuracy through consultation with a medical professional. By ensuring alignment between the framework’s attention and clinical expertise, this research enhances the potential for assisting medical professionals in accurately interpreting neurodegenerative disease states and thereby advancing the development of clinically applicable diagnostic tools. It also demonstrates the feasibility of adopting quantum machine learning in medical image analysis and medical AI.
With millions of medical data being produced daily, it is important to leverage current technology to improve the healthcare system. As traditional deep learning models are unable to effectively handle high-dimensional data, a hybrid classical-quantum approach is used to enhance traditional deep learning algorithms. The hybrid classical-quantum models are built upon the classical deep learning framework with quantum techniques. The classical layers are utilized for feature extraction while the quantum layer is used for computational tasks. This addresses computational limitations and data imbalance challenges in medical image analysis. Transfer learning models, such as ResNet18 and InceptionV3, are used in conjunction with a quantum variational circuit to perform the task. The model is trained on a chest X-ray dataset, which consists of two sets of data: binary and multiclass. The binary dataset consists of Normal and COVID-19 images, while the multiclass dataset has COVID-19, Normal, and Tuberculosis images for classification. PennyLane, as a simulator, has been used to perform quantum computing. The dataset has also been used to train the traditional transfer learning models, pre-trained ResNet18, and their results have been compared. Out of all the models tested, the hybrid classical-quantum model, namely Hybrid ResNet18, performed the best. It achieved an accuracy of 93.22% for the binary classification task and 93.91% for the multiclass classification. The results show that there is a statistically significant improvement in classification accuracy and F1-score of the hybrid approach over the classical transfer learning baselines under a simulation-based environment. This sets the stage for further research on real-world physical quantum hardware. Class imbalance and overlapping predictions have been addressed using methods such as data augmentation and confusion matrix analysis. Thus, quantum machine learning could be used as a vital tool to analyze medical data for better diagnostic results.