@article{Wang_Dulhanty_Chung_Khalvati_Haider_Wong_2020, title={Zone-DR: Discovery Radiomics via Zone-level Deep Radiomic Sequencer Discovery for Zone-based Prostate Cancer Grading using Diffusion Weighted Imaging}, volume={5}, url={https://openjournals.uwaterloo.ca/index.php/vsl/article/view/1648}, abstractNote={<p>Prostate cancer is the most commonly diagnosed cancer in men, however prognosis is relatively good given sufficiently early diagnosis. This motivates the need for fast and reliable prostate cancer grading. In this study, we investigate the efficacy of a discovery radiomics strategy for prostate zone-based cancer grading using a deep radiomic sequencer discovered from diffusion weighted imaging (DWI) data. More specifically, we propose Zone-DR, a discovery<br>radiomics approach based on zone-level deep radiomic sequencer discovery that discover radiomic feature directly from DWI data. Experimental results using 12, 466 pathology-verified zones obtained<br>from DWI data of 101 patients showed that the proposed Zone-DR approach achieved higher accuracy than a threshold-based approach for both ADC and CHB-DWI. Furthermore, the results also showed that the trade-off between sensitivity and specificity can be based approach and Zone-DR optimized based on the particular clinical scenario we wish to employ Zone-DR for, such as clinical screening versus surgical planning.</p>}, number={1}, journal={Journal of Computational Vision and Imaging Systems}, author={Wang, Linda and Dulhanty, Chris and Chung, Audrey and Khalvati, Farzad and Haider, Masoom A. and Wong, Alexander}, year={2020}, month={Jan.}, pages={1} }