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
. 2020;61(1):149-155.
doi: 10.47162/RJME.61.1.17.

Automated Gleason grading of prostate cancer using transfer learning from general-purpose deep-learning networks

Mircea Sebastian Şerbănescu  1 , Nicolae Cătălin Manea, Liliana Streba, Smaranda Belciug, Iancu Emil Pleşea, Ionica Pirici, Raluca Maria Bungărdean, Răzvan Mihail Pleşea
Affiliations

Automated Gleason grading of prostate cancer using transfer learning from general-purpose deep-learning networks

Mircea Sebastian Şerbănescu et al. Rom J Morphol Embryol. 2020.

Abstract

Two deep-learning algorithms designed to classify images according to the Gleason grading system that used transfer learning from two well-known general-purpose image classification networks (AlexNet and GoogleNet) were trained on Hematoxylin-Eosin histopathology stained microscopy images with prostate cancer. The dataset consisted of 439 images asymmetrically distributed in four Gleason grading groups. Mean and standard deviation accuracy for AlexNet derivate network was of 61.17±7 and for GoogleNet derivate network was of 60.9±7.4. The similar results obtained by the two networks with very different architecture, together with the normal distribution of classification error for both algorithms show that we have reached a maximum classification rate on this dataset. Taking into consideration all the constraints, we conclude that the resulted networks could assist pathologists in this field, providing first or second opinions on Gleason grading, thus presenting an objective opinion in a grading system which has showed in time a great deal of interobserver variability.

PubMed Disclaimer

Conflict of interest statement

The authors declare that they have no conflict of interests.

Figures

Figure 1
Figure 1
Samples from the dataset (HE staining, ×200): (A) Gleason pattern 2; (B) Gleason pattern 3; (C) Gleason pattern 4; (D) Gleason pattern 5
Figure 2
Figure 2
Training process: (A) AlexNet; (B) GoogleNet
Figure 3
Figure 3
Confusion matrix heatmap: (A) AlexNet; (B) GoogleNet
Figure 4
Figure 4
Standalone prostate cancer image classifier application interface
See this image and copyright information in PMC

References

    1. Cancer stat facts: prostate cancer – 2020. Surveillance, Epidemiology, and End Results Program [online], National Cancer Institute (NIH) Available from: https://seer.cancer.gov/statfacts/html/prost.html[ Accesed 27.12.2019]
    1. Epstein JI, Allsbrook WC, Amin MB, Egevad LL, ISUP Grading Committee The 2005 International Society of Urological Pathology (ISUP) Consensus Conference on Gleason grading of prostatic carcinoma. Am J Surg Pathol. 2005;29(9):1228–1242. - PubMed
    1. Epstein JI, Egevad L, Amin MB, Delahunt B, Srigley JR, Humphrey PA, Grading Committee The 2014 International Society of Urological Pathology (ISUP) Consensus Conference on Gleason grading of prostatic carcinoma: definition of grading patterns and proposal for a new grading system. Am J Surg Pathol. 2016;40(2):244–252. - PubMed
    1. National Comprehensive Cancer Network (NCCN) Clinical Practice Guidelines in Oncology. Prostate cancer – 2020. NCCN Evidence-Based Cancer Guidelines, Oncology Drug Compendium, Oncology Continuing Medical Education [online] Available from: https://www.nccn.org/professionals/physician_gls/default.aspxf[ Accesed 27.12.2019]
    1. Persson J, Wilderäng U, Jiborn T, Wiklund PN, Damber JE, Hugosson J, Steineck G, Haglind E, Bjartell A. Interobserver variability in the pathological assessment of radical prostatectomy specimens: findings of the Laparoscopic Prostatectomy Robot Open (LAPPRO) Study. Scand J Urol. 2014;48(2):160–167. - PubMed