Enhancing Diagnostic Accuracy for Breast Cancer Using Classical-Quantum Hybrid and Transfer Learning Technique

Abstract

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 quantum-optimized 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.