Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Review Article
  • Published:

Technology Insight: will systems pathology replace the pathologist?

Nature Clinical Practice Urology volume 4, pages 39–45 (2007)Cite this article

Abstract

By using systems pathology, it might be possible to provide a predictive, personalized therapeutic recommendation for patients with prostate cancer. Systems pathology integrates quantitative data and information from many sources to generate a reliable prediction of the expected natural course of the disease and response to different therapeutic options. In other words, through the integration of relatively large data sets and the use of knowledge engineering, systems pathology aims at predicting the future behavior of tumors and their interaction with the host. In this Review, we introduce the methods used in systems pathology and summarize a recent study providing the first evidence of a concept for this strategy. The results show that systems pathology can provide a personalized prediction of the risk of recurrence after prostatectomy for cancer.

Key Points

  • Systems pathology integrates quantitative data from diverse sources to render a personalized predictive and prognostic report

  • Systems pathology combines conventional clinicopathologic information with quantitative morphology and molecular data

  • Systems pathology uses modern machine learning techniques to mine and interpret the data sets that produce a predictive personalized report

  • Prostate cancer has been chosen to provide the first proof that systems pathology can be used in patient care

  • Initial results show that it is possible to use systems pathology to provide a personalized prediction of the risk of recurrence after prostatectomy in men with prostate cancer

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Figure 1: The different steps involved in object-oriented image analysis.
Figure 2: Risk groups for PSA recurrence using the SVRc model score, illustrated as a Kaplan–Meier curve.
Figure 3: Risk of PSA recurrence for a specific patient.

Similar content being viewed by others

References

  1. Albertsen PC et al. (1998) Competing risk analysis of men aged 55 to74 years at diagnosis managed conservatively for clinically localized prostate cancer. JAMA 280: 975–980

    Article  CAS  PubMed  Google Scholar 

  2. Bianco FJ Jr et al. (2003) Ten-year survival after radical prostatectomy: specimen Gleason score is the predictor in organ-confined prostate cancer. Clin Prostate Cancer 1: 242–247

    Article  PubMed  Google Scholar 

  3. Allan RW et al. (2003) Correlation of minute (0.5 mm or less) focus of prostate adenocarcinoma on needle biopsy with radical prostatectomy specimen: role of prostate specific antigen density. J Urol 170: 370–372

    Article  PubMed  Google Scholar 

  4. Quinn DI et al. (2005) Molecular markers of prostate cancer outcome. European J Cancer 41: 858–887

    Article  CAS  Google Scholar 

  5. Diamond J et al. (2004) The use of morphological characteristics and texture analysis in the identification of tissue composition in prostatic neoplasia. Hum Pathol 35: 1121–1131

    Article  PubMed  Google Scholar 

  6. Roula MA et al. (2002) A multispectral computer vision system for automatic grading of prostatic neoplasia. In Proceedings of the IEEE International Symposium on Biomedical Imaging, July 7–10 2002, Washington, DC, 193–196

    Chapter  Google Scholar 

  7. Stotzka R et al. (1995) A hybrid neural and statistical classifier system for histopathologic grading of prostate lesions. Anal Quant Cytol Histol 17: 204–218

    CAS  PubMed  Google Scholar 

  8. Smith Y et al. (1999) Similarity measurement method for the classification of architecturally differentiated images. Comp Biomed Res 32: 1–12

    Article  CAS  Google Scholar 

  9. Wetzel AW et al. (1999) Evaluation of prostate tumor grades by content-based image retrieval. In 27th AIPR Workshop: Advances in Computer-Assisted Recognition, 14 October 1998, Washington, DC, 3584: 244–252 (Ed. Merickso RJ)

    Chapter  Google Scholar 

  10. Jafari-Khouzani K and Soltanian-Zadeh H (2003) Multiwavelet grading of pathological images of prostate. IEEE Trans Biomed Eng 50: 697–704

    Article  PubMed  Google Scholar 

  11. Vapnik VN (1995) The Nature of Statistical Learning Theory. New York: Springer–Verlag

    Book  Google Scholar 

  12. Su AI et al. (2001) Molecular classification of human carcinomas by use of gene expression signatures. Cancer Res 61: 7388–7393

    CAS  PubMed  Google Scholar 

  13. Yeang CH et al. (2001) Molecular classification of multiple tumor types. Bioinformatics 17 (Suppl 1): S316–S322

    Article  PubMed  Google Scholar 

  14. Cristianini N and Shawe-Taylor J. (2000) An Introduction to Support Vector Machines and Other Kernel-Based Learning Methods. Cambridge, UK: Cambridge University Press

    Book  Google Scholar 

  15. Ye QH et al. (2003) Predicting hepatitis B virus-positive metastatic hepatocellular carcinomas using gene expression profiling and supervised machine learning. Nat Med 9: 416–423

    Article  CAS  PubMed  Google Scholar 

  16. Brown MPS et al. (2000) Knowledgebased analysis of microarray gene expression data using support vector machines. Proc Natl Acad Sci USA 97: 262–267

    Article  CAS  PubMed  Google Scholar 

  17. Biganzoli E et al. (1998) Feed forward neural networks for the analysis of censored survival data: a partial logistic regression approach. Stat Med 17: 1169–1186

    Article  CAS  PubMed  Google Scholar 

  18. Ohno-Machado L and Musen MA. (1997) Modular neural networks for medical prognosis: quantifying the benefits of combining neural networks for survival prediction. Connect Sci 9: 71–86

    Article  Google Scholar 

  19. Kattan MW et al. (1998) Experiments to determine whether recursive partitioning or an artifi-cial neural network overcomes theoretical limitation of cox proportional hazards regression. Comput Biomed Res 31: 363–373

    Article  CAS  PubMed  Google Scholar 

  20. Brown SF et al. (1997) On the use of artificial neural networks for the analysis of survival data. IEEE Trans Neural Netw 8: 1071–1077

    Article  CAS  PubMed  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. O Saidi is a consultant at Aureon Laboratories, Yonkers, NY,

    Olivier Saidi

  2. C Cordon-Cardo is Director of the Division of Molecular Pathology at Memorial Sloan–Kettering Cancer Center, New York,

    Carlos Cordon-Cardo

  3. Department of Pathology, J Costa is Professor of Pathology and Medicine, Director of Anatomical Pathology, and Vice Chairman, Yale Cancer Center, Yale University School of Medicine, New Haven, CT, USA.,

    Jose Costa

Authors
  1. Olivier Saidi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Carlos Cordon-Cardo
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Jose Costa
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jose Costa.

Ethics declarations

Competing interests

Oliver Saidi is a consultant at Aureon Laboratories Inc. and is listed as inventor of IP created at Aureon.

Carols Cordon-Cardo is on the Board of Directors of Aureon Laboratories Inc.

Jose Costa is on the Board of Directors of Aureon Laboratories Inc.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Saidi, O., Cordon-Cardo, C. & Costa, J. Technology Insight: will systems pathology replace the pathologist?. Nat Rev Urol 4, 39–45 (2007). https://doi.org/10.1038/ncpuro0669

Download citation

  • Received:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1038/ncpuro0669

This article is cited by

Search

Advanced search

Quick links

Nature Briefing

Sign up for the Nature Briefing newsletter — what matters in science, free to your inbox daily.

Get the most important science stories of the day, free in your inbox. Sign up for Nature Briefing