Leveraging Quantum Convolutional Network for Medical Dataset Classification

EasyChair Preprint no. 13108

Abstract

In the realm of medical image classification, the integration of advanced computational methodologies holds the promise of revolutionizing diagnostic capabilities. This abstract explores the innovative fusion of Quantum Convolutional Network (QCNN) with the ResNet (50) architecture for the classification of medical datasets. By harnessing the unique properties of quantum computing, such as superposition and entanglement, alongside the robustness of ResNet (50), this hybrid approach aims to achieve unprecedented levels of accuracy and efficiency in identifying anomalies within medical images. Through meticulous experimentation and evaluation on diverse medical datasets, including the MNIST medical dataset, this study demonstrates the efficacy of the QCNN-ResNet (50) fusion in surpassing the benchmarks set by conventional convolutional neural networks (CNNs). The results showcase remarkable performance across various metrics, highlighting the potential of quantum-enhanced methodologies in reshaping the landscape of medical image classification. As the field continues to evolve, this innovative approach paves the way for transformative advancements in diagnostic imaging and personalized healthcare.

Keyphrases: deep learning, medical, MNIST, quantum

@Booklet{EasyChair:13108,
  author = {Rana Ali and Asmaa Mohammed and Yara Yasser and Mostafa Hesham},
  title = {Leveraging Quantum Convolutional Network for Medical Dataset Classification},
  howpublished = {EasyChair Preprint no. 13108},

  year = {EasyChair, 2024}}