3 March 2017 Prostate lesion detection and localization based on locality alignment discriminant analysis
Author Affiliations +
Abstract
Prostatic adenocarcinoma is one of the most commonly occurring cancers among men in the world, and it also the most curable cancer when it is detected early. Multiparametric MRI (mpMRI) combines anatomic and functional prostate imaging techniques, which have been shown to produce high sensitivity and specificity in cancer localization, which is important in planning biopsies and focal therapies. However, in previous investigations, lesion localization was achieved mainly by manual segmentation, which is time-consuming and prone to observer variability. Here, we developed an algorithm based on locality alignment discriminant analysis (LADA) technique, which can be considered as a version of linear discriminant analysis (LDA) localized to patches in the feature space. Sensitivity, specificity and accuracy generated by the proposed algorithm in five prostates by LADA were 52.2%, 89.1% and 85.1% respectively, compared to 31.3%, 85.3% and 80.9% generated by LDA. The delineation accuracy attainable by this tool has a potential in increasing the cancer detection rate in biopsies and in minimizing collateral damage of surrounding tissues in focal therapies.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Mingquan Lin, Mingquan Lin, Weifu Chen, Weifu Chen, Mingbo Zhao, Mingbo Zhao, Eli Gibson, Eli Gibson, Matthew Bastian-Jordan, Matthew Bastian-Jordan, Derek W. Cool, Derek W. Cool, Zahra Kassam, Zahra Kassam, Tommy W. S. Chow, Tommy W. S. Chow, Aaron Ward, Aaron Ward, Bernard Chiu, Bernard Chiu, } "Prostate lesion detection and localization based on locality alignment discriminant analysis", Proc. SPIE 10134, Medical Imaging 2017: Computer-Aided Diagnosis, 101344A (3 March 2017); doi: 10.1117/12.2255621; https://doi.org/10.1117/12.2255621
PROCEEDINGS
8 PAGES


SHARE
Back to Top