MAPS: A Quantitative Radiomics Approach for Prostate Cancer Detection

被引:145
作者
Cameron, Andrew [1 ]
Khalvati, Farzad [2 ,3 ]
Haider, Masoom A. [2 ,3 ]
Wong, Alexander [1 ]
机构
[1] Univ Waterloo, Dept Syst Design Engn, Waterloo, ON N2L 3G1, Canada
[2] Univ Toronto, Dept Med Imaging, Toronto, ON M5T 1W7, Canada
[3] Sunnybrook Res Inst, Toronto, ON M4N 3M5, Canada
基金
加拿大自然科学与工程研究理事会;
关键词
Computer-aided detection; feature models; multiparametric MRI (mpMRI); prostate cancer detection; prostate MRI; radiomics; DIFFUSION; MRI; SEGMENTATION; MORTALITY;
D O I
10.1109/TBME.2015.2485779
中图分类号
R318 [生物医学工程];
学科分类号
0831 ;
摘要
This paper presents a quantitative radiomics feature model for performing prostate cancer detection using multiparametric MRI (mpMRI). It incorporates a novel tumor candidate identification algorithm to efficiently and thoroughly identify the regions of concern and constructs a comprehensive radiomics feature model to detect tumorous regions. In contrast to conventional automated classification schemes, this radiomics-based feature model aims to ground its decisions in a way that can be interpreted and understood by the diagnostician. This is done by grouping features into high-level feature categories which are already used by radiologists to diagnose prostate cancer: Morphology, Asymmetry, Physiology, and Size (MAPS), using biomarkers inspired by the PI-RADS guidelines for performing structured reporting on prostate MRI. Clinical mpMRI data were collected from 13 men with histology-confirmed prostate cancer and labeled by an experienced radiologist. These annotated data were used to train classifiers using the proposed radiomics-driven feature model in order to evaluate the classification performance. The preliminary experimental results indicated that the proposed model outperformed each of its constituent feature groups as well as a comparable conventional mpMRI feature model. A further validation of the proposed algorithm will be conducted using a larger dataset as future work.
引用
收藏
页码:1145 / 1156
页数:12
相关论文
共 38 条
[1]  
Amelard R, 2012, IEEE ENG MED BIO, P4458, DOI 10.1109/EMBC.2012.6346956
[2]   Mortality Results from a Randomized Prostate-Cancer Screening Trial [J].
Andriole, Gerald L. ;
Grubb, Robert L., III ;
Buys, Saundra S. ;
Chia, David ;
Church, Timothy R. ;
Fouad, Mona N. ;
Gelmann, Edward P. ;
Kvale, Paul A. ;
Reding, Douglas J. ;
Weissfeld, Joel L. ;
Yokochi, Lance A. ;
Crawford, E. David ;
O'Brien, Barbara ;
Clapp, Jonathan D. ;
Rathmell, Joshua M. ;
Riley, Thomas L. ;
Hayes, Richard B. ;
Kramer, Barnett S. ;
Izmirlian, Grant ;
Miller, Anthony B. ;
Pinsky, Paul F. ;
Prorok, Philip C. ;
Gohagan, John K. ;
Berg, Christine D. .
NEW ENGLAND JOURNAL OF MEDICINE, 2009, 360 (13) :1310-1319
[3]  
[Anonymous], CAN CANC STAT 2012
[4]  
[Anonymous], NATURE COMMUN
[5]   Multiparametric MR Imaging for Detection of Clinically Significant Prostate Cancer: A Validation Cohort Study with Transperineal Template Prostate Mapping as the Reference Standard [J].
Arumainayagam, Nimalan ;
Ahmed, Hashim U. ;
Moore, Caroline M. ;
Freeman, Alex ;
Allen, Clare ;
Sohaib, S. Aslam ;
Kirkham, Alex ;
van der Meulen, Jan ;
Emberton, Mark .
RADIOLOGY, 2013, 268 (03) :761-769
[6]   ESUR prostate MR guidelines 2012 [J].
Barentsz, Jelle O. ;
Richenberg, Jonathan ;
Clements, Richard ;
Choyke, Peter ;
Verma, Sadhna ;
Villeirs, Geert ;
Rouviere, Olivier ;
Logager, Vibeke ;
Futterer, Jurgen J. .
EUROPEAN RADIOLOGY, 2012, 22 (04) :746-757
[7]   Computed Diffusion-weighted MR Imaging May Improve Tumor Detection [J].
Blackledge, Matthew D. ;
Leach, Martin O. ;
Collins, David J. ;
Koh, Dow-Mu .
RADIOLOGY, 2011, 261 (02) :573-581
[8]  
Cameron A, 2014, IEEE ENG MED BIO, P3357, DOI 10.1109/EMBC.2014.6944342
[9]  
Canadian Cancer Society's Advisory Committee on Cancer Statistics, 2014, CAN CANC STAT 2014
[10]  
Carroll P. R., 2010, COMMUN ONCOL, V7, P25