Surgical Planning Laboratory - Brigham & Women's Hospital - Boston, Massachusetts USA - a teaching affiliate of Harvard Medical School

Surgical Planning Laboratory

The Publication Database hosted by SPL

All Publications | Upload | Advanced Search | Gallery View | Download Statistics | Help | Import | Log in

Classification of Clinical Significance of MRI Prostate Findings Using 3D Convolutional Neural Networks

Institution:
1Department of Radiology, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, USA.
2Department of Electrical and Computer Engineering, University of British Columbia, Vancouver, BC, Canada.
3Medical Informatics Laboratory, Queen’s University, Kingston, ON, Canada.
4Diagnostic Image Analysis Group, Radboud University Medical Center, Nijmegen, the Netherlands.
Publication Date:
Feb-2017
Volume Number:
10134
Pages:
101342A
Citation:
Proc SPIE Int Soc Opt Eng. 2017 Feb 11; 10134: 101342A.
PubMed ID:
28615793
PMCID:
PMC5467889
Appears in Collections:
NCIGT, Prostate Group, SPL
Sponsors:
P41 EB015898/EB/NIBIB NIH HHS/United States
Generated Citation:
Mehrtash A., Sedghi A., Ghafoorian M., Taghipour M., Tempany C.M., Wells III W.M., Kapur T., Mousavi P., Abolmaesumi P., Fedorov A. Classification of Clinical Significance of MRI Prostate Findings Using 3D Convolutional Neural Networks. Proc SPIE Int Soc Opt Eng. 2017 Feb 11; 10134: 101342A. PMID: 28615793. PMCID: PMC5467889.
Downloaded: 71 times. [view map]
Paper: Download, View online
Export citation:
Google Scholar: link

Prostate cancer (PCa) remains a leading cause of cancer mortality among American men. Multi-parametric magnetic resonance imaging (mpMRI) is widely used to assist with detection of PCa and characterization of its aggressiveness. Computer-aided diagnosis (CADx) of PCa in MRI can be used as clinical decision support system to aid radiologists in interpretation and reporting of mpMRI. We report on the development of a convolution neural network (CNN) model to support CADx in PCa based on the appearance of prostate tissue in mpMRI, conducted as part of the SPIE-AAPM-NCI PROSTATEx challenge. The performance of different combinations of mpMRI inputs to CNN was assessed and the best result was achieved using DWI and DCE-MRI modalities together with the zonal information of the finding. On the test set, the model achieved an area under the receiver operating characteristic curve of 0.80.

Additional Material
1 File (26.823kB)
Mehrtash-SPIEIntSocOptEng2017A-fig4.jpg (26.823kB)