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
. 2021 Aug;54(2):452-459.
doi: 10.1002/jmri.27585. Epub 2021 Feb 26.

Deep Learning Whole-Gland and Zonal Prostate Segmentation on a Public MRI Dataset

Renato Cuocolo  1   2 , Albert Comelli  3 , Alessandro Stefano  4 , Viviana Benfante  4 , Navdeep Dahiya  5 , Arnaldo Stanzione  6 , Anna Castaldo  6 , Davide Raffaele De Lucia  6 , Anthony Yezzi  5 , Massimo Imbriaco  6
Affiliations

Deep Learning Whole-Gland and Zonal Prostate Segmentation on a Public MRI Dataset

Renato Cuocolo et al. J Magn Reson Imaging. 2021 Aug.

Abstract

Background: Prostate volume, as determined by magnetic resonance imaging (MRI), is a useful biomarker both for distinguishing between benign and malignant pathology and can be used either alone or combined with other parameters such as prostate-specific antigen.

Purpose: This study compared different deep learning methods for whole-gland and zonal prostate segmentation.

Study type: Retrospective.

Population: A total of 204 patients (train/test = 99/105) from the PROSTATEx public dataset.

Field strength/sequence: A 3 T, TSE T2 -weighted.

Assessment: Four operators performed manual segmentation of the whole-gland, central zone + anterior stroma + transition zone (TZ), and peripheral zone (PZ). U-net, efficient neural network (ENet), and efficient residual factorized ConvNet (ERFNet) were trained and tuned on the training data through 5-fold cross-validation to segment the whole gland and TZ separately, while PZ automated masks were obtained by the subtraction of the first two.

Statistical tests: Networks were evaluated on the test set using various accuracy metrics, including the Dice similarity coefficient (DSC). Model DSC was compared in both the training and test sets using the analysis of variance test (ANOVA) and post hoc tests. Parameter number, disk size, training, and inference times determined network computational complexity and were also used to assess the model performance differences. A P < 0.05 was selected to indicate the statistical significance.

Results: The best DSC (P < 0.05) in the test set was achieved by ENet: 91% ± 4% for the whole gland, 87% ± 5% for the TZ, and 71% ± 8% for the PZ. U-net and ERFNet obtained, respectively, 88% ± 6% and 87% ± 6% for the whole gland, 86% ± 7% and 84% ± 7% for the TZ, and 70% ± 8% and 65 ± 8% for the PZ. Training and inference time were lowest for ENet.

Data conclusion: Deep learning networks can accurately segment the prostate using T2 -weighted images.

Evidence level: 4 TECHNICAL EFFICACY: Stage 2.

Keywords: deep learning; machine learning; magnetic resonance imaging; prostate; prostatic neoplasms.

PubMed Disclaimer

Comment in

References

    1. Heidler S, Drerup M, Lusuardi L, et al. The correlation of prostate volume and prostate-specific antigen levels with positive bacterial prostate tissue cultures. Urology 2018;115:151-156.
    1. Murphy AB, Nyame YA, Batai K, et al. Does prostate volume correlate with vitamin D deficiency among men undergoing prostate biopsy? Prostate Cancer Prostatic Dis 2017;20:55-60.
    1. Kim YM, Park S, Kim J, et al. Role of prostate volume in the early detection of prostate cancer in a cohort with slowly increasing prostate specific antigen. Yonsei Med J 2013;54:1202-1206.
    1. Nordström T, Akre O, Aly M, Grönberg H, Eklund M. Prostate-specific antigen (PSA) density in the diagnostic algorithm of prostate cancer. Prostate Cancer Prostatic Dis 2018;21:57-63.
    1. Porcaro AB, Tafuri A, Sebben M, et al. Prostate volume index is able to differentiate between prostatic chronic inflammation and prostate cancer in patients with Normal digital rectal examination and prostate-specific antigen values <10 ng/mL: Results of 564 biopsy Naïve cases. Urol Int 2019;103:415-422.

LinkOut - more resources