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
. 2019 Jul;475(1):77-83.
doi: 10.1007/s00428-019-02577-x. Epub 2019 May 16.

Deep learning for automatic Gleason pattern classification for grade group determination of prostate biopsies

Marit Lucas  1 , Ilaria Jansen  2   3 , C Dilara Savci-Heijink  4 , Sybren L Meijer  4 , Onno J de Boer  4 , Ton G van Leeuwen  2 , Daniel M de Bruin  2   3 , Henk A Marquering  2   5
Affiliations

Deep learning for automatic Gleason pattern classification for grade group determination of prostate biopsies

Marit Lucas et al. Virchows Arch. 2019 Jul.

Abstract

Histopathologic grading of prostate cancer using Gleason patterns (GPs) is subject to a large inter-observer variability, which may result in suboptimal treatment of patients. With the introduction of digitization and whole-slide images of prostate biopsies, computer-aided grading becomes feasible. Computer-aided grading has the potential to improve histopathological grading and treatment selection for prostate cancer. Automated detection of GPs and determination of the grade groups (GG) using a convolutional neural network. In total, 96 prostate biopsies from 38 patients are annotated on pixel-level. Automated detection of GP 3 and GP ≥ 4 in digitized prostate biopsies is performed by re-training the Inception-v3 convolutional neural network (CNN). The outcome of the CNN is subsequently converted into probability maps of GP ≥ 3 and GP ≥ 4, and the GG of the whole biopsy is obtained according to these probability maps. Differentiation between non-atypical and malignant (GP ≥ 3) areas resulted in an accuracy of 92% with a sensitivity and specificity of 90 and 93%, respectively. The differentiation between GP ≥ 4 and GP ≤ 3 was accurate for 90%, with a sensitivity and specificity of 77 and 94%, respectively. Concordance of our automated GG determination method with a genitourinary pathologist was obtained in 65% (κ = 0.70), indicating substantial agreement. A CNN allows for accurate differentiation between non-atypical and malignant areas as defined by GPs, leading to a substantial agreement with the pathologist in defining the GG.

Keywords: Convolutional neural network; Gleason patterns; Grade groups; Prostate.

PubMed Disclaimer

Conflict of interest statement

DMdB is founder and shareholder of Offroad Medical, HAM is founder and shareholder of Nicolab.

Figures

Fig. 1
Fig. 1
a H&E image b with the annotations of the four classes
Fig. 2
Fig. 2
a H&E biopsy fragment, b ground truth manual annotations of GP 3, c probability map for malignancy. Color scale on the right of the image indicates the probability
Fig. 3
Fig. 3
a H&E biopsy fragment, b ground truth manual annotations of GP 4, c probability map for GP ≥ 4. Color scale on the right of the image indicates the probability
See this image and copyright information in PMC

References

    1. Siegel R, Miller K, Jemal A. Cancer statistics , 2015. CA Cancer J Clin. 2015;65:29–29. - PubMed
    1. Zhou CK, Check DP, Lortet-Tieulent J, Laversanne M, Jemal A, Ferlay J, Bray F, Cook MB, Devesa SS. Prostate cancer incidence in 43 populations worldwide: an analysis of time trends overall and by age group. Int J Cancer. 2016;138:1388–1400. doi: 10.1002/ijc.29894. - DOI - PMC - PubMed
    1. Heidenreich A, Bastian PJ, Bellmunt J, Bolla M, Joniau S, van der Kwast T, Mason M, Matveev V, Wiegel T, Zattoni F, Mottet N. EAU guidelines on prostate cancer. Part 1: screening, diagnosis, and local treatment with curative intent - update 2013. Eur Urol. 2014;65:124–137. doi: 10.1016/j.eururo.2013.09.046. - DOI - PubMed
    1. Epstein JI, Allsbrook WCJ, Amin MB, Egevad LL. The 2005 International Society of Urological Pathology (ISUP) consensus conference on Gleason grading of prostatic carcinoma. Am J Surg Pathol. 2005;29:1228–1242. doi: 10.1097/01.pas.0000173646.99337.b1. - DOI - PubMed
    1. Epstein JI, Zelefsky MJ, Sjoberg DD, Nelson JB, Egevad L, Magi-Galluzzi C, Vickers AJ, Parwani AV, Reuter VE, Fine SW, Eastham JA, Wiklund P, Han M, Reddy CA, Ciezki JP, Nyberg T, Klein EA. A contemporary prostate Cancer grading system: a validated alternative to the Gleason score. Eur Urol. 2016;69:428–435. doi: 10.1016/j.eururo.2015.06.046. - DOI - PMC - PubMed

Grants and funding