Radiomics applications in gastrointestinal oncology: the colorectal cancer model

Colorectal cancer (CRC) represents the third most common diagnosis of cancer in the worldwide, accounting for around 10% of all new cancer cases globally. Prognosis of patients affected by CRC is strongly dependent on the stage at diagnosis. Besides epidemiologic data, CRC is a complex and heterogeneous disease with different molecular, genetic and epi-genetic sub-types that led to different scenario in the disease course. As a consequence of heterogeneity, tissue sampling biopsy at diagnosis cannot be considered fully representative of tumor behavior and molecular profile. In this context a complete risk stratification to set the best personalized treatment is very important to reduce the risk of recurrence and improve survival. Medical imaging plays a pivotal role in all aspects of personalized medicine: prediction, diagnosis and especially treatment planning, in the choice of the best treatment for the specific patient at the right time. Among the most promising imaging techniques with the potential to improve cancer treatment and outcome, one cannot but include Radiomics. Radiomics is a methodology of advanced quantitative image analysis which uses mathematical algorithms to extract characteristic features from clinical imaging data. Prior studies have evaluated the use of radiomics analysis in CT imaging for adding information about cancer aggressiveness as well as for predicting treatment response. In the colon cancer staging, CT represent the main clinical imaging method to stage the tumor and manage the therapy choices. The major goal of CT is to determine by visual assessment if there is direct invasion of adjacent organs, presence of pathologic lymph nodes and, evidence of distant metastases. Radiomics in colon cancer is proposed to potentially improve characterization and prognosis, mostly using Computed Tomography (CT). The aim of the present thesis is to assess the role of CT imaging-based Radiomics in the colon cancer evaluation at staging to improve disease risk stratification in terms of tumor aggressiveness and lymph node metastasis to manage the best therapeutic approach tailored for the patient at clinical staging.