Researchers: Ge Yan, Chao Li, Carola Schönlieb
Nasopharyngeal carcinoma (NPC) is a unique head and neck cancer, for which radiotherapy (RT) is the main treatment modality. Although induction chemotherapy (IC) plus concurrent chemoradiotherapy (CCRT) has significantly improved patient survival for locoreigonally advanced NPC (LA-NPC). TNM staging is the most commonly used standard for treatment planning and prognosis determination for NPC patients. However, TNM staging based on gross anatomy does not take into account tumour heterogeneity, which poses significant challenges to precise treatment planning.
Radiomics has recently emerged as a promising field in oncology, based on the premise that medical imaging can provide important information on tumor physiology. By translating medical imaging into mineable, high-dimension, and quantitative imaging features via high-throughput extraction of data-characterization algorithms, radiomics offer an easy, effective, and reliable method of stratifying patients into risk groups and aids clinical decision-making. Meanwhile, the novel deep learning techniques have shown the promising capabilities to extract correlative quantitative representation in many medical applications. Magnetic resonance imaging (MRI) and positron emission tomography with computed tomography (PET/CT) have unique advantages in the diagnosis and evaluation of cases with advanced NPC. Given this, we propose this project to evaluate the role of MRI and PET/CT-based radiomics in assessment between intratumoral heterogeneity and survival outcomes and guiding individual radiation plan and chemotherapy for patients with LA-NPC.