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
. 2022 Jun 8:2:64.
doi: 10.1038/s43856-022-00126-3. eCollection 2022.

Predicting biochemical recurrence of prostate cancer with artificial intelligence

Hans Pinckaers  1 , Jolique van Ipenburg  1 , Jonathan Melamed  2 , Angelo De Marzo  3 , Elizabeth A Platz  4 , Bram van Ginneken  1 , Jeroen van der Laak  1   5 , Geert Litjens  1
Affiliations

Predicting biochemical recurrence of prostate cancer with artificial intelligence

Hans Pinckaers et al. Commun Med (Lond). .

Abstract

Background: The first sign of metastatic prostate cancer after radical prostatectomy is rising PSA levels in the blood, termed biochemical recurrence. The prediction of recurrence relies mainly on the morphological assessment of prostate cancer using the Gleason grading system. However, in this system, within-grade morphological patterns and subtle histopathological features are currently omitted, leaving a significant amount of prognostic potential unexplored.

Methods: To discover additional prognostic information using artificial intelligence, we trained a deep learning system to predict biochemical recurrence from tissue in H&E-stained microarray cores directly. We developed a morphological biomarker using convolutional neural networks leveraging a nested case-control study of 685 patients and validated on an independent cohort of 204 patients. We use concept-based explainability methods to interpret the learned tissue patterns.

Results: The biomarker provides a strong correlation with biochemical recurrence in two sets (n = 182 and n = 204) from separate institutions. Concept-based explanations provided tissue patterns interpretable by pathologists.

Conclusions: These results show that the model finds predictive power in the tissue beyond the morphological ISUP grading.

Keywords: Epidemiology; Prognostic markers; Prostate; Prostate cancer.

PubMed Disclaimer

Conflict of interest statement

Competing interestsB.v.G. receive funding and royalties from MeVis Medical Solutions AG, (Bremen, Germany), and reports grants and stock/royalties from Thirona, and grants and royalties from Delft Imaging Systems, all outside the submitted work. J.v.d.L. is a member of the advisory boards of Philips, the Netherlands, and ContextVision, Sweden; and received research funding from Philips, the Netherlands; ContextVision, Sweden; and Sectra, Sweden, all outside the submitted work. G.L. reports research grants from the Dutch Cancer Society, the Netherlands Organization for Scientific Research (NWO), and HealthHolland during the conduct of the study, and grants from Philips Digital Pathology Solutions, and consultancy fees from Novartis and Vital Imaging, outside the submitted work. J.M. is supported by Department of Defense Prostate Cancer Research Program, DOD Award No W81XWH-18-2-0016, PCRP Prostate Cancer Biorepository Network A.D.M. is a paid consultant to Cepheid LLC, and Merck & Co., A.D.M has also received research support from Myriad Genetics and Janssen R&D for other studies. All other authors have no competing interests.

Figures

Fig. 1
Fig. 1. Overview of the methods summarizing the biomarker development and the Automatic Concept Explanations (ACE) process.
Cores were extracted from TMA slides and used to train a neural network to predict the years to biochemical recurrence. On the nested case-control test set, a matched analysis was performed. For ACE, patches were generated from the cores, inferenced through the network and clustered based on their intermediate features.
Fig. 2
Fig. 2. Kaplan–Meier plot for New York Langone external validation cohort.
Groups were separated using the median DLS biomarker score in this cohort (a) and using four thresholds (b).
Fig. 3
Fig. 3. Examples of automatic concepts explanations.
Concepts were sorted by their average score for the cores in which the pattern occurs. Showing the two most benign concepts, two intermediate and two aggressive concepts. The boxes show the quartiles of the concept predictions while the whiskers extend to show the rest of the distribution except for outlier points that lie below the 25% or above 75% of the data, by 1.5 times the interquartile range. Green, yellow and red shaded areas indicate 33%, 66% percentiles. See the Supplementary Notes 2 for all concepts.
See this image and copyright information in PMC

References

    1. Sung, H. et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J. Clin.10.3322/caac.21660 (2021). - PubMed
    1. Grossman DC, et al. Screening for Prostate Cancer: US preventive services task force recommendation statement. JAMA. 2018;319:1901–1913. doi: 10.1001/jama.2018.0161. - DOI - PubMed
    1. Heijnsdijk EAM, et al. Summary statement on screening for prostate cancer in Europe. Int J Cancer. 2018;142:741–746. doi: 10.1002/ijc.31102. - DOI - PubMed
    1. Goonewardene SS, Phull JS, Bahl A, Persad RA. Interpretation of PSA levels after radical therapy for prostate cancer. Trends Urol. Men S Health. 2014;5:30–34. doi: 10.1002/tre.407. - DOI
    1. Amling CL, et al. Long-term hazard of progression after radical prostatectomy for clinically localized prostate cancer: continued risk of biochemical failure after 5 years. J Urol. 2000;164:101–105. doi: 10.1016/S0022-5347(05)67457-5. - DOI - PubMed