MRI based Prostate Cancer Localization with Random Forests and Auto-context Model

Prostate cancer is the most commonly diagnosed non-skin cancer and the second leading cause of cancer death among U.S. men [1]. Current clinical practice for the diagnosis of prostate cancer is often based on a transrectal ultrasound (TRUS) biopsy, after the patient shows an elevated serum prostate specific antigen (PSA) level. A large screening trial using PSA and TRUS has shown that it is possible to reduce prostate cancer mortality by 20-30% [2]. However, these studies have also shown that PSA testing in combination with TRUS biopsies has a relatively low specificity.

Source: Computerized Medical Imaging and Graphics - February 27, 2016 Category: Radiology Authors: Chunjun Qian, Li Wang, Yaozong Gao, Ambereen Yousuf, Xiaoping Yang, Aytekin Oto, Dinggang Shen Source Type: research