Classifying Esophageal Cancer Using a Hybrid Quantum-Classical Neural Network

Early diagnosis of esophageal cancer is critical for increasing the chances of successful treatment and reducing mortality rates. Traditional machine learning models for diagnosing esophageal lesions use previously collected data on specific local features, but these methods can be slow and computationally intensive. As a result, researchers are exploring alternative training platforms for deep learning models, including quantum computers. These computers can take advantage of the properties of quantum entanglement and superposition to solve complex problems.In this study, we propose a Hybrid Quantum-Classical Neural Network using deep learning and supervised learning techniques in a quantum framework. Our focus is on classifying esophageal cancer to demonstrate the network’s capabilities. We trained a network of two qubits to learn the label of a given dataset and optimize circuit parameters to minimize error. The proposed Hybrid Quantum-Classical Neural Network showed high accuracy in classifying esophageal cancer.