Abstract The coronavirus has been affecting people's everyday life since 2019. To stop the further spread of the virus, early detection of carriers of the virus and isolation are needed. Due to the limitations of nuclear accounting amplification assay (NAAT), CT imaging, which has the high sensitivity to the new corona virus, is used as a diagnostic method. In this study, a classical-quantum hybrid model using a variational quantum circuit as a classifier was designed. A pre-trained VGG16 was used for feature extraction, and the extracted features were passed to a variational quantum classifier for classification. Experiments show that using variational quantum circuits to linearly vary the classical data can improve the accuracy of the model prediction. Hybrid Model achieves good results with values of 98.78%, 97.65%, 100.00%, and 98.81% for Accuracy, Precision, Recall, and F1-score metrics, respectively. The comparison between Hybrid Model and the classical model shows that the overall performance of Hybrid Model is better than that of the classical model. Hybrid Model provides a reliable, flexible and scalable classical-quantum deep learning approach for the prediction task of COVID-19.
Abstract The coronavirus has been affecting people's everyday life since 2019. To stop the further spread of the virus, early detection of carriers of the virus and isolation are needed. Due to the limitations of nuclear accounting amplification assay (NAAT), CT imaging, which has the high sensitivity to the new corona virus, is used as a diagnostic method. In this study, a classical-quantum hybrid model using a variational quantum circuit as a classifier was designed. A pre-trained VGG16 was used for feature extraction, and the extracted features were passed to a variational quantum classifier for classification. Experiments show that using variational quantum circuits to linearly vary the classical data can improve the accuracy of the model prediction. Hybrid Model achieves good results with values of 98.78%, 97.65%, 100.00%, and 98.81% for Accuracy, Precision, Recall, and F1-score metrics, respectively. The comparison between Hybrid Model and the classical model shows that the overall performance of Hybrid Model is better than that of the classical model. Hybrid Model provides a reliable, flexible and scalable classical-quantum deep learning approach for the prediction task of COVID-19.
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.
Abstract Classical deep learning models often struggle to fully capture complex visual patterns and to generalize effectively when trained on limited or imbalanced medical imaging data. To address this limitation, this paper presents a novel Hybrid Quantum Deep Learning (Hybrid QDL) framework that leverages the strengths of both deep neural networks and quantum circuits for advanced medical image interpretation. The proposed model integrates a pre-trained EfficientNet-B4 as the feature extractor and a variational quantum circuit as the classification head, enabling joint learning of hierarchical and quantum-enhanced representations. The Hybrid QDL model is evaluated on three clinically relevant datasets: COVIDx (for 3-class COVID-19 diagnosis using chest X-rays), PneumoniaMNIST (for pneumonia detection), and OrganAMNIST (for multi-organ abdominal classification). The model achieves state-of-the-art results, with 98.48% accuracy and 98.33% F1-score on COVIDx, outperforming both classical and prior quantum baselines. On PneumoniaMNIST and OrganAMNIST, it reaches 98.28% and 95.27% accuracy, respectively, along with high macro F1-scores. Ablation studies confirm that increasing quantum circuit depth and entanglement enhances discriminative power, particularly in complex multi-class scenarios. These results demonstrate that the Hybrid QDL framework is a robust, scalable solution for automated medical diagnosis and holds significant promise for real-world clinical decision support and COVID-19 detection.
Classifying malaria cell images relies on examining blood-smear microscopy slides to separate healthy red blood cells from those carrying the parasite to recognize the stage of infection. Manually examining the cells under a microscope is slow, as it depends heavily on expert skill, and can lead to inconsistent results, especially in resource-limited settings. Machine learning and deep learning help overcome these difficulties by automatically detecting subtle patterns that are hard for the human eye to distinguish, enabling faster, more accurate, and scalable diagnosis. This work compares the performance of classical deep learning models and hybrid quantum-classical systems for malaria cell classification problem, for a publicly available Kaggle dataset of 27,558 labelled images. The pipeline combines classical feature extraction from a subset of 5000 images with quantum feature mapping and variational quantum circuits (2, 3 and 4 qubits) through angle encoding and strongly entangling layers. All the models have been trained over 40 epochs with a 70-15-15 train-validation-test split, and accuracy, precision, recall, and F1-score have been evaluated. Classical CNN achieved 92.93% accuracy, while ResNet18 and MobileNetV2 achieved 87.87% and 60.67 % respectively.4-qubit Quantum CNN achieves the highest score of 93.47%, surpassing all the classical baselines. The hybrid MobileNetV2 achieved an accuracy of 87.07%, which is a significant improvement compared with its classical counterpart, indicating that quantum feature transformation can repurpose weak classical representations.
The need to have rapid technological solutions is becoming more evident as the information world digitizes and the amount of data around us grows.It is argued that the future of computational systems will be quantum computing, which will be faster and more capable of solving several issues that cannot be solved with current computers.The aim of the current research is to examine the contributions made by quantum transfer learning models in enhancing the detection of breast cancer.Although both classical and deep learning approaches have proved to be effective, they continue to face serious challenges in handling high-dimensional and complex medical data.Quantum computing can be a feasible solution to such complexity.This study presents a hybrid model, which combines a classical pre-trained deep learning model ( ResNet50) with a range of variational quantum circuits-simple, entangled, and more complex.The main goal is to find the best model set up with regard to predictive power and computation time.It has been found that a hybrid model with an entangled variational circuit has an accuracy of 98.46, a precision of 100, and an F1-score of 97.3, which means a better result compared to the standard transfer learning model, which had an accuracy of 94.6, a precision of 97, and an F1-score of 90.4.These results improve upon recent quantum transfer learning studies, such as Azevedo et al. (2022) with 84% accuracy, and align closely with state-of-the-art quantumoptimized models reporting up to 99.3% accuracy, highlighting the effectiveness of our entangled variational approach on ultrasound images.Meanwhile, the traditional transfer learning model was the best in computational resource utilization.
Classifying the severity of medical images using the quantum-classical model with respect to the desperately required COVID-19 virus screening area. It is a pandemic concern that is having an impact on millions of people’s lives. The most frequent result that involves expert evaluation in COVID-19 Computed Tomography(CT) images of the lungs is ground glass turbidity. Quantum Machine Learning (QML), is one of the fields that quantum computing has the ability to explore. These days, with so much data available, machine learning might gain from increased speed, computational complexity in which it needs a lot of weights for better performance. In this paper, exploring a machine learning issue using a quantum technique and quantum-classical hybrid model use for severity classification that perform on different input images 28*28, 32*32 and 64*64 that’s run on simulator. The research laid out in this paper shows that the hybrid model succeeds over CNN in terms of low resolution image size and fewer trainable parameters. Quantum-Classical model categorizes the patient’s Computed Tomography images into three severity classes: moderate, severe and critical. The best hybrid model in this study uses a 32*32 image size with accuracy of 96.82% and 3075 trainable parameters , whereas the VGG-19 model uses a 64*64 image size with 262659 trainable parameters provide accuracy of 85.97%.
Magnetic Resonance Imaging (MRI) images reveal unique abnormal patterns in brain tumors. These patterns play an important role in diagnosis and therapy planning. This study proposed a new model that combines Convolution Neural Network (CNN) and Parameterized Variational Quantum Circuit (VQC) to better diagnose and categorize brain tumors. The model extracted features from MRI images using pre-trained systems such as VGG16, VGG19, and ResNet-18. Among these models of CNN, the base model was selected as VGG16 for feature extraction which yield better performance. The features were subsequently reduced via an affine transformation and passed through a VQC for the hybrid model. The VQC used quantum superposition and entanglement as tools for categorization. The hybrid model performed better than base model due to the representation of feature in large space called Hilbert space. Using n qubit of quantum, 2n states were represented in the Hilbert space. Using VQC, the complex high dimensional relationship of features was learnt and also the performance of the hybrid model was optimized by integrating VQC to VGG16. The experiment was done integrating the pennylane simulator with pytorch.