الفهرس 
1 INTRODUCTIONOnly 14 pages are availabe for public view
 |  | from | 165 |  |  |
| | | from | 165 | | |
Abstract
Due to the superiority and progress of quantum computing in many areas (e.g., cryptography, machine learning, healthcare), a combination of classical machine learning and quantum information processing has established a new field called quantum machine learning. One of the most frequently used applications of quantum computing is machine learning. In this thesis, we want to achieve low-cost learning with increased accuracy to save time during the learning phase for datasets classification in the medical area that is compatible with available limited quantum hardware. In this thesis, two-hybrid quantum-classical models for medical data processing are presented.
The first model, despite the great efforts to find an effective way for COVID-19 prediction, the virus nature and mutation represent a critical challenge to diagnose the covered cases. However, developing a model to predict COVID-19 via Chest X-Ray (CXR) images with accurate performance is necessary to help in early diagnosis. In this thesis, a hybrid quantum-classical convolutional neural networks (HQ-CNN) model using random quantum circuits (RQC) as a base to detect COVID-19 patients with CXR images. A collection of 5,445 CXR images, including 1350 COVID-19, 1350 normal, 1345 viral pneumonia, and 1400 bacterial pneumonia images, were used as a dataset in this thesis. The proposed HQ-CNN model achieved higher performance with binary and multi-class classification. Moreover, the HQ-CNN model is assessed with the statistical analysis (i.e., Cohen’s Kappa and Matthew correlation coefficients).
The second model, cancer classification based on gene expression in- creases early diagnosis and recovery, but high-dimensional genes with a small number of samples are a major challenge. This thesis intro- duces a new hybrid quantum-kernel support vector machine (QKSVM) combined with a Binary Harris hawk optimization (BHHO)-based gene selection for cancer classification on a quantum simulator. This model aims to improve the microarray cancer prediction performance with the quantum kernel estimation based on the informative genes by BHHO. The principal component analysis (PCA) is applied to reduce the se- lected genes to match the qubit numbers. After which, the quantum computer is used to estimate the kernel with the training data of the reduced genes and generate the quantum kernel matrix. The proposed approach (QKSVM–PCA–BHHO) enhanced the overall performance with two datasets. Also, the QKSVM–PCA–BHHO approach is evalu- ated with different quantum feature maps (kernels) and classical kernel (RBF). The experimental results of the two-hybrid quantum-classical techniques prove its ability in improving classical deep/machine learning models for processing and classification of medical data.