Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2017 Feb 11:10134:101342A.
doi: 10.1117/12.2277123. Epub 2017 Mar 3.

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

Alireza Mehrtash  1   2 , Alireza Sedghi  3 , Mohsen Ghafoorian  1   4 , Mehdi Taghipour  1 , Clare M Tempany  1 , William M Wells 3rd  1 , Tina Kapur  1 , Parvin Mousavi  3 , Purang Abolmaesumi  2 , Andriy Fedorov  1
Affiliations

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

Alireza Mehrtash et al. Proc SPIE Int Soc Opt Eng. .

Abstract

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.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Distribution of training and test datasets of the PROSTATEx challenge. (a) Training samples: the distribution of lesion findings shows that the training dataset is not balanced in terms of both zonal distribution and the clinical significance of the finding. (b) Test samples are not balanced in terms of zones.
Figure 2
Figure 2
Architecture of the proposed 3D CNN. The network uses combination of ADC map, maximum B-Value (BVAL) from DWI and Ktrans from DCE-MRI with zone information.
Figure 3
Figure 3
Comparison of classifiers trained with architecture in Figure 2 on different folds of cross-validation.
Figure 4
Figure 4
An example of a PZ true positive in validation set. Only (d–f) modalities with zone information (zone=PZ) were used by the network to predict the clinical significance of the finding.
See this image and copyright information in PMC

References

    1. Siegel RL, Miller KD, Jemal A. Cancer statistics. CA Cancer J Clin. 2017;67(1):7–30. - PubMed
    1. Hegde JV, Mulkern RV, Panych LP, Fennessy FM, Fedorov A, Maier SE, Tempany CMC. Multiparametric MRI of prostate cancer: An update on state-of-the-art techniques and their performance in detecting and localizing prostate cancer. Journal of Magnetic Resonance Imaging. 2013;37(5):1035–1054. - PMC - PubMed
    1. Litjens G, Kooi T, Ehteshami Bejnordi B, Setio AAA, Ciompi F, Ghafoorian M, van der Laak JAWM, van Ginneken B, Sánchez CI. A survey on deep learning in medical image analysis. arXiv preprint arXiv:1702.05747. 2017 - PubMed
    1. Samala RK, Chan HP, Hadjiiski LM, Cha K, Helvie MA. SPIE Medical Imaging. International Society for Optics and Photonics; 2016. Deep-learning convolution neural network for computer-aided detection of microcalcifications in digital breast tomosynthesis; pp. 97850Y–97850Y.
    1. Qiu Y, Yan S, Tan M, Cheng S, Liu H, Zheng B. SPIE Medical Imaging. International Society for Optics and Photonics; 2016. Computer-aided classification of mammographic masses using the deep learning technology: a preliminary study; pp. 978520–978520.

LinkOut - more resources