TY - JOUR AU - He, Yuchen AU - Tio, Earvin AU - Wang, Linda AU - Dulhanty, Chris AU - Khalvati, Farzad AU - Haider, Masoom A. AU - Wong, Alexander PY - 2020/01/02 Y2 - 2024/03/28 TI - A Comparative Study Between Apparent Diffusion Imaging and Correlated Diffusion Imaging for Prostate Cancer JF - Journal of Computational Vision and Imaging Systems JA - J. Comp. Vis. Imag. Sys. VL - 5 IS - 1 SE - Articles DO - UR - https://openjournals.uwaterloo.ca/index.php/vsl/article/view/1659 SP - 1 AB - <p>Prostate cancer is the second most common cancer in men world-wide, with approximately 174,650 new cases diagnosed in 2019 in<br>the U.S. [1]. However, prognosis is relatively good given sufficiently<br>early detection during the non-metastatic stage, motivating the need<br>for fast and reliable cancer screening methods. Diffusion weighted<br>imaging is a magnetic resonance imaging technique that is gaining<br>traction as a noninvasive method for cancer screening. In 2013, a<br>new form of diffusion weighted imaging called correlated diffusion<br>imaging (CDI) was introduced as a potential candidate modality for<br>building computer-aided clinical decision support systems [2]. We<br>perform a large scale study, across 101 patient cases with full PI-<br>RADS score and histopathology, to compare the performance of<br>correlated diffusion imaging in prostate cancer detection and localization to apparent diffusion coefficient maps, the most commonly<br>used diffusion weighted imaging-derived imaging modality in can-<br>cer grading. Using threshold-based classification, experimental results showed that CDI achieves higher specificity at high sensitivity<br>values of 90% and 95%, suggesting that CDI is well suited for scenarios where high sensitivity is crucial, such as cancer screening.</p> ER -