@article{Wong_Chung_Kumar_Shafiee_Khalvati_Haider_2015, title={Discovery Radiomics for Imaging-driven Quantitative Personalized Cancer Decision Support}, volume={1}, url={https://openjournals.uwaterloo.ca/index.php/vsl/article/view/VL101}, DOI={10.15353/vsnl.v1i1.46}, abstractNote={<p>In this paper, we describe the underlying methodology behind discovery<br />radiomics, where the ultimate goal is to discover customized,<br />abstract radiomic feature models directly from the wealth of medical<br />imaging data to better capture highly unique tumor traits beyond<br />what can be captured using hand-crafted radiomic feature<br />models. We further explore the current state-of-the-art in discovery<br />radiomics and their application to various forms of cancer such<br />as prostate cancer and lung cancer, and show that discovery radiomics<br />can yield significant potential clinical impact.</p>}, number={1}, journal={Journal of Computational Vision and Imaging Systems}, author={Wong, Alexander and Chung, Audrey G. and Kumar, Devinder and Shafiee, Mohammad Javad and Khalvati, Farzad and Haider, Masoom}, year={2015}, month={Oct.} }