TY - JOUR
T1 - Segmentation of the prostate transition zone and peripheral zone on mr images with deep learning
AU - Bardis, Michelle
AU - Houshyar, Roozbeh
AU - Chantaduly, Chanon
AU - Tran-Harding, Karen
AU - Ushinsky, Alexander
AU - Chahine, Chantal
AU - Rupasinghe, Mark
AU - Chow, Daniel
AU - Chang, Peter
N1 - Funding Information:
Disclosures of Conflicts of Interest: M.B. Activities related to the present article: disclosed no relevant relationships. Activities not related to the present article: author is a recipient of Radiological Society of North America Medical Student Research Grant (RMS1902) and recipient of Alpha Omega Alpha Carolyn L. Kuckein Student Research Fellowship. Other relationships: disclosed no relevant relationships. R.H. disclosed no relevant relationships. C. Chantaduly disclosed no relevant relationships. K.T.H. disclosed no relevant relationships. A.U. disclosed no relevant relationships. C. Chahine disclosed no relevant relationships. M.R. disclosed no relevant relationships. D.C. Activities related to the present article: disclosed no relevant relationships. Activities not related to the present article: author received consultancy fees from Canon Medical; author is employed by University of California, Irvine; author received money from Cullins and Grandy for expert testimony; author has stock/stock options in Avicenna.ai. Other relationships: disclosed no relevant relationships. P.C. Activities related to the present article: disclosed no relevant relationships. Activities not related to the present article: author received payment for lectures including service on speakers bureaus from Canon Medical; author is a cofounder of and has stock/stock options in Avicenna.ai. Other relationships: disclosed no relevant relationships.
Publisher Copyright:
© RSNA, 2021.
PY - 2021/5
Y1 - 2021/5
N2 - Purpose: images. To develop a deep learning model to delineate the transition zone (TZ) and peripheral zone (PZ) of the prostate on MR Materials and Methods: This retrospective study was composed of patients who underwent a multiparametric prostate MRI and an MRI/ transrectal US fusion biopsy between January 2013 and May 2016. A board-certified abdominal radiologist manually segmented the prostate, TZ, and PZ on the entire data set. Included accessions were split into 60% training, 20% validation, and 20% test data sets for model development. Three convolutional neural networks with a U-Net architecture were trained for automatic recognition of the prostate organ, TZ, and PZ. Model performance for segmentation was assessed using Dice scores and Pearson correlation coefficients. Results: A total of 242 patients were included (242 MR images; 6292 total images). Models for prostate organ segmentation, TZ segmentation, and PZ segmentation were trained and validated. Using the test data set, for prostate organ segmentation, the mean Dice score was 0.940 (interquartile range, 0.930–0.961), and the Pearson correlation coefficient for volume was 0.981 (95% CI: 0.966, 0.989). For TZ segmentation, the mean Dice score was 0.910 (interquartile range, 0.894–0.938), and the Pearson correlation coefficient for volume was 0.992 (95% CI: 0.985, 0.995). For PZ segmentation, the mean Dice score was 0.774 (interquartile range, 0.727–0.832), and the Pearson correlation coefficient for volume was 0.927 (95% CI: 0.870, 0.957). Conclusion: Deep learning with an architecture composed of three U-Nets can accurately segment the prostate, TZ, and PZ.
AB - Purpose: images. To develop a deep learning model to delineate the transition zone (TZ) and peripheral zone (PZ) of the prostate on MR Materials and Methods: This retrospective study was composed of patients who underwent a multiparametric prostate MRI and an MRI/ transrectal US fusion biopsy between January 2013 and May 2016. A board-certified abdominal radiologist manually segmented the prostate, TZ, and PZ on the entire data set. Included accessions were split into 60% training, 20% validation, and 20% test data sets for model development. Three convolutional neural networks with a U-Net architecture were trained for automatic recognition of the prostate organ, TZ, and PZ. Model performance for segmentation was assessed using Dice scores and Pearson correlation coefficients. Results: A total of 242 patients were included (242 MR images; 6292 total images). Models for prostate organ segmentation, TZ segmentation, and PZ segmentation were trained and validated. Using the test data set, for prostate organ segmentation, the mean Dice score was 0.940 (interquartile range, 0.930–0.961), and the Pearson correlation coefficient for volume was 0.981 (95% CI: 0.966, 0.989). For TZ segmentation, the mean Dice score was 0.910 (interquartile range, 0.894–0.938), and the Pearson correlation coefficient for volume was 0.992 (95% CI: 0.985, 0.995). For PZ segmentation, the mean Dice score was 0.774 (interquartile range, 0.727–0.832), and the Pearson correlation coefficient for volume was 0.927 (95% CI: 0.870, 0.957). Conclusion: Deep learning with an architecture composed of three U-Nets can accurately segment the prostate, TZ, and PZ.
UR - http://www.scopus.com/inward/record.url?scp=85112036341&partnerID=8YFLogxK
U2 - 10.1148/rycan.2021200024
DO - 10.1148/rycan.2021200024
M3 - Article
C2 - 33929265
AN - SCOPUS:85112036341
VL - 3
JO - Radiology: Imaging Cancer
JF - Radiology: Imaging Cancer
SN - 2638-616X
IS - 3
M1 - e200024
ER -