Published Paper Details:

Lung cancer is still the top cause of cancer-related deaths. Getting a diagnosis early and having a precise prognosis are vital for boosting survival rates among patients. This paper puts forward an innovative Hybrid Quantum Classical (HQC) Framework aimed at improving lung cancer detection and outcome predictions. The framework takes advantage of multimodal imaging data specifically, it taps into integrated features (radiomics) from Computed Tomography (CT), Positron Emission Tomography (PET), and Magnetic Resonance Imaging (MRI) to provide a well-rounded view of tumor diversity. We also introduce a Quantum Machine Learning (QML) element, using a Variational Quantum Classifier (VQC), to enhance the way features are mapped to outcomes. The HQC method tackles the computational challenges and restrictions of traditional deep learning when handling large, high-dimensional radiomics data, showing better performance in terms of both diagnostic accuracy (classifying malignant nodules) and predicting prognosis (patient survival).