A Hybrid QNN-Based Framework for Accurate Early Detection of HCV Liver Abnormalities from CT Scans Using Custom Transfer Learning and AI Edge Device

The discovery of the Hepatitis C Virus (HCV) by Drs. Harvey J. Alter, Michael Houghton, and Charles M. Rice was recognized with the 2020 Nobel Prize in Medicine, and their groundbreaking work has paved the way for effective treatments for HCV [1]. Despite this, early detection and diagnosis remain critical for successful management of the disease. Computed Tomography (CT) is a widely used imaging technique that can detect liver lesions and other abnormalities associated with HCV infection. However, interpretation of CT scans can be challenging, time-consuming, and subject to interobserver variability, making it difficult for radiologists to accurately diagnose HCV. In recent years, the development of Artificial Intelligence (AI) and Computer Vision (CV) techniques has opened up new possibilities for medical image analysis, allowing for the development of AI-based diagnostic products that can assist radiologists in the interpretation of CT scans and improve the accuracy and speed of HCV diagnosis. In this paper, a novel end-to-end framework for the diagnosis of Hepatitis C Virus (HCV) is presented that leverages Transfer Learning and Hybrid Quantum Neural Networks (QNNs). By utilizing pre-trained models and transferring knowledge to new tasks, Transfer Learning significantly reduces the time required for training Deep Learning models for image analysis tasks, leading to improved accuracy and precision of the resulting models. The integration of hybrid QNNs in the training process further accelerates the training process and improves the accuracy of the models. The integration of hardware and software accelerators onto AI edge devices onboard CT scanners is proposed, enabling faster inferencing and offering a promising approach for developing an efficient early HCV diagnostic product assisting radiologists. This approach enables rapid analysis and classification of HCV-related liver lesions, potentially reducing the burden of HCV-related liver disease. By revolutionizing the field of medical imaging, this technology has the power to significantly improve the speed and accuracy of HCV detection and diagnosis, transforming the landscape of liver disease diagnosis and treatment.