Radiomics In Brain Tumors

Brain tumours are highly heterogeneous and carry poor prognosis and rank among the top 10 causes of cancer deaths. MRI is a routinely performed for patients who are suspected of brain tumours and is the main stay in its diagnosis and treatment response assessment. A number of advanced MRI techniques like diffusion-based imaging, perfusion imaging and MR spectroscopy are now routinely used in the evaluation of brain tumours. The application of radiomics has been initiated in clinical oncology due to its ability to analyse the combination of numerous quantitative features provides the possibility to unravel the underlying pathophysiology that is hard to be perceived by radiologists’ eyes and avoid subjective misreading. The general workflow of radiomics involves several discrete steps: imaging, segmentation, feature extraction, feature selection, machine learning, and validation. In this presentation, we intend to demonstrate the possible role of radiomics in brain tumor and how it may support in clinical decision making in overall management of the disease in future. The current challenges associated with radiomics will also be discussed.