TY - JOUR
T1 - A 3d-2d hybrid u-net convolutional neural network approach to prostate organ segmentation of multiparametric MRI
AU - Ushinsky, Alexander
AU - Bardis, Michelle
AU - Glavis-Bloom, Justin
AU - Uchio, Edward
AU - Chantaduly, Chanon
AU - Nguyentat, Michael
AU - Chow, Daniel
AU - Chang, Peter D.
AU - Houshyar, Roozbeh
N1 - Funding Information:
Supported by a grant from Cannon, Inc., to D. Chow.
Publisher Copyright:
© 2021 American Roentgen Ray Society.
PY - 2021/1
Y1 - 2021/1
N2 - OBJECTIVE. Prostate cancer is the most commonly diagnosed cancer in men in the United States with more than 200,000 new cases in 2018. Multiparametric MRI (mpMRI) is increasingly used for prostate cancer evaluation. Prostate organ segmentation is an essential step of surgical planning for prostate fusion biopsies. Deep learning convolutional neural networks (CNNs) are the predominant method of machine learning for medical image recognition. In this study, we describe a deep learning approach, a subset of artificial intelligence, for automatic localization and segmentation of prostates from mpMRI. MATERIALS AND METHODS. This retrospective study included patients who underwent prostate MRI and ultrasound-MRI fusion transrectal biopsy between September 2014 and December 2016. Axial T2-weighted images were manually segmented by two abdominal radiologists, which served as ground truth. These manually segmented images were used for training on a customized hybrid 3D-2D U-Net CNN architecture in a fivefold cross-validation paradigm for neural network training and validation. The Dice score, a measure of overlap between manually segmented and automatically derived segmentations, and Pearson linear correlation coefficient of prostate volume were used for statistical evaluation. RESULTS. The CNN was trained on 299 MRI examinations (total number of MR images = 7774) of 287 patients. The customized hybrid 3D-2D U-Net had a mean Dice score of 0.898 (range, 0.890-0.908) and a Pearson correlation coefficient for prostate volume of 0.974. CONCLUSION. A deep learning CNN can automatically segment the prostate organ from clinical MR images. Further studies should examine developing pattern recognition for lesion localization and quantification.
AB - OBJECTIVE. Prostate cancer is the most commonly diagnosed cancer in men in the United States with more than 200,000 new cases in 2018. Multiparametric MRI (mpMRI) is increasingly used for prostate cancer evaluation. Prostate organ segmentation is an essential step of surgical planning for prostate fusion biopsies. Deep learning convolutional neural networks (CNNs) are the predominant method of machine learning for medical image recognition. In this study, we describe a deep learning approach, a subset of artificial intelligence, for automatic localization and segmentation of prostates from mpMRI. MATERIALS AND METHODS. This retrospective study included patients who underwent prostate MRI and ultrasound-MRI fusion transrectal biopsy between September 2014 and December 2016. Axial T2-weighted images were manually segmented by two abdominal radiologists, which served as ground truth. These manually segmented images were used for training on a customized hybrid 3D-2D U-Net CNN architecture in a fivefold cross-validation paradigm for neural network training and validation. The Dice score, a measure of overlap between manually segmented and automatically derived segmentations, and Pearson linear correlation coefficient of prostate volume were used for statistical evaluation. RESULTS. The CNN was trained on 299 MRI examinations (total number of MR images = 7774) of 287 patients. The customized hybrid 3D-2D U-Net had a mean Dice score of 0.898 (range, 0.890-0.908) and a Pearson correlation coefficient for prostate volume of 0.974. CONCLUSION. A deep learning CNN can automatically segment the prostate organ from clinical MR images. Further studies should examine developing pattern recognition for lesion localization and quantification.
KW - Artificial intelligence
KW - Deep learning
KW - Machine learning
KW - Multiparametric MRI (mpMRI)
KW - Prostate
UR - http://www.scopus.com/inward/record.url?scp=85098685240&partnerID=8YFLogxK
U2 - 10.2214/AJR.19.22168
DO - 10.2214/AJR.19.22168
M3 - Article
C2 - 32812797
AN - SCOPUS:85098685240
SN - 0361-803X
VL - 216
SP - 111
EP - 116
JO - American Journal of Roentgenology
JF - American Journal of Roentgenology
IS - 1
ER -