Automated clear cell renal carcinoma grade classification with prognostic significance

Autoři: Katherine Tian aff001;  Christopher A. Rubadue aff001;  Douglas I. Lin aff001;  Mitko Veta aff003;  Michael E. Pyle aff001;  Humayun Irshad aff001;  Yujing J. Heng aff001
Působiště autorů: Department of Pathology, Harvard Medical School, Beth Israel Deaconess Medical Center, Boston, MA, United States of America aff001;  The Harker School, San Jose, CA, United States of America aff002;  Medical Image Analysis Group, Eindhoven University of Technology, Eindhoven, The Netherlands aff003;  Cancer Research Institute, Beth Israel Deaconess Cancer Center, Boston, MA, United States of America aff004
Vyšlo v časopise: PLoS ONE 14(10)
Kategorie: Research Article


We developed an automated 2-tiered Fuhrman’s grading system for clear cell renal cell carcinoma (ccRCC). Whole slide images (WSI) and clinical data were retrieved for 395 The Cancer Genome Atlas (TCGA) ccRCC cases. Pathologist 1 reviewed and selected regions of interests (ROIs). Nuclear segmentation was performed. Quantitative morphological, intensity, and texture features (n = 72) were extracted. Features associated with grade were identified by constructing a Lasso model using data from cases with concordant 2-tiered Fuhrman’s grades between TCGA and Pathologist 1 (training set n = 235; held-out test set n = 42). Discordant cases (n = 118) were additionally reviewed by Pathologist 2. Cox proportional hazard model evaluated the prognostic efficacy of the predicted grades in an extended test set which was created by combining the test set and discordant cases (n = 160). The Lasso model consisted of 26 features and predicted grade with 84.6% sensitivity and 81.3% specificity in the test set. In the extended test set, predicted grade was significantly associated with overall survival after adjusting for age and gender (Hazard Ratio 2.05; 95% CI 1.21–3.47); manual grades were not prognostic. Future work can adapt our computational system to predict WHO/ISUP grades, and validating this system on other ccRCC cohorts.

Klíčová slova:

Cancer detection and diagnosis – Diagnostic medicine – Ellipses – Chromatin – Image processing – Machine learning – Renal cell carcinoma – Computational systems


1. Amin MB, Amin MB, Tamboli P, Javidan J, Stricker H, de-Peralta Venturina M, et al. Prognostic impact of histologic subtyping of adult renal epithelial neoplasms: an experience of 405 cases. Am J Surg Pathol. 2002;26: 281–291. doi: 10.1097/00000478-200203000-00001 11859199

2. Goyal R, Gersbach E, Yang XJ, Rohan SM. Differential diagnosis of renal tumors with clear cytoplasm: Clinical relevance of renal tumor subclassification in the era of targeted therapies and personalized medicine. Arch Pathol Lab Med. 2013;137: 467–480. doi: 10.5858/arpa.2012-0085-RA 23544936

3. de Peralta-Venturina M, Moch H, Amin M, Tamboli P, Hailemariam S, Mihatsch M, et al. Sarcomatoid differentiation in renal cell carcinoma: a study of 101 cases. Am J Surg Pathol. 2001;25: 275–284. doi: 10.1097/00000478-200103000-00001 11224597

4. Rini BI, Campbell SC, Escudier B. Renal cell carcinoma. Lancet. 2009;373: 1119–1132. doi: 10.1016/S0140-6736(09)60229-4 19269025

5. Foster K, Prowse a, van den Berg a, Fleming S, Hulsbeek MM, Crossey P a, et al. Somatic mutations of the von Hippel-Lindau disease tumour suppressor gene in non-familial clear cell renal carcinoma. Hum Mol Genet. 1994;3: 2169–73. doi: 10.1093/hmg/3.12.2169 7881415

6. Delahunt B. Advances and controversies in grading and staging of renal cell carcinoma. Mod Pathol. 2009;22: S24–S36. doi: 10.1038/modpathol.2008.183 19494851

7. Lang H, Lindner V, de Fromont M, Molinié V, Letourneux H, Meyer N, et al. Multicenter determination of optimal interobserver agreement using the Fuhrman grading system for renal cell carcinoma. Cancer. 2005;103: 625–629. doi: 10.1002/cncr.20812 15611969

8. Hong SK, Jeong CW, Park JH, Kim HS, Kwak C, Choe G, et al. Application of simplified Fuhrman grading system in clear-cell renal cell carcinoma. BJU Int. 2011;107: 409–415. doi: 10.1111/j.1464-410X.2010.09561.x 20804473

9. Rioux-Leclercq N, Karakiewicz PI, Trinh QD, Ficarra V, Cindolo L, De La Taille A, et al. Prognostic ability of simplified nuclear grading of renal cell carcinoma. Cancer. 2007;109: 868–874. doi: 10.1002/cncr.22463 17262800

10. Delahunt B, Cheville JC, Martignoni G, Humphrey PA, Magi-Galluzzi C, McKenney J, et al. The International Society of Urological Pathology (ISUP) grading system for renal cell carcinoma and other prognostic parameters. Am J Surg Pathol. 2013;37: 1490–1504. doi: 10.1097/PAS.0b013e318299f0fb 24025520

11. Louis DN, Feldman M, Carter AB, Dighe AS, Pfeifer JD, Bry L, et al. Computational pathology: A path ahead. Arch Pathol Lab Med. 2016;140: 41–50. doi: 10.5858/arpa.2015-0093-SA 26098131

12. Beck AH, Sangoi AR, Leung S, Marinelli RJ, Nielsen TO, van de Vijver MJ, et al. Systematic analysis of breast cancer morphology uncovers stromal features associated with survival. Sci Transl Med. 2011;3: 108ra113. doi: 10.1126/scitranslmed.3002564 22072638

13. Ehteshami Bejnordi B, Veta M, van Diest PJ, van Ginneken B, Karssemeijer N, Litjens G, et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA. 2017;318: 2199–2210. PMCID: PMC5820737. doi: 10.1001/jama.2017.14585 29234806

14. Dong F, Irshad H, Oh EY, Lerwill MF, Brachtel EF, Jones NC, et al. Computational pathology to discriminate benign from malignant intraductal proliferations of the breast. PLoS One. 2014;9: e114885. doi: 10.1371/journal.pone.0114885 25490766

15. Tabesh A, Teverovskiy M, Pang HY, Kumar VP, Verbel D, Kotsianti A, et al. Multifeature prostate cancer diagnosis and gleason grading of histological images. IEEE Trans Med Imaging. 2007;26: 1366–1378. doi: 10.1109/TMI.2007.898536 17948727

16. Yu K-H, Zhang C, Berry GJ, Altman RB, Ré C, Rubin DL, et al. Predicting non-small cell lung cancer prognosis by fully automated microscopic pathology image features. Nat Commun. 2016;7: 12474. doi: 10.1038/ncomms12474 27527408

17. Schüffler PJ, Fuchs TJ, Ong CS, Roth V, Buhmann JM. Computational TMA analysis and cell nucleus classification of renal cell carcinoma. In: Goesele M, Roth S, Kuijper A, Schiele B, Schindler K, editors. Pattern Recognition DAGM 2010 Lecture Notes in Computer Science, vol 6376. Berlin, Heidelberg: Springer; 2010. pp. 202–211. doi: 10.1007/978-3-642-15986-2_21

18. Cancer Genome Atlas Research Network. Comprehensive molecular characterization of clear cell renal cell carcinoma. Nature. 2013;499: 43–49. doi: 10.1038/nature12222 23792563

19. Gutman D, Cobb J, Somanna D. Cancer Digital Slide Archive: an informatics resource to support integrated in silico analysis of TCGA pathology data. J Am Med Inf Assoc. 2013;20: 1091–1098. doi: 10.1136/amiajnl-2012-001469 23893318

20. Schindelin J, Arganda-Carreras I, Frise E, Kaynig V, Longair M, Pietzsch T, et al. Fiji: An open source platform for biological image analysis. Nat Methods. 2012;9: 676–682. doi: 10.1038/nmeth.2019 22743772

21. Khan AM, Rajpoot N, Treanor D, Magee D. A nonlinear mapping approach to stain normalization in digital histopathology images using image-specific color deconvolution. IEEE Trans Biomed Eng. 2014;61: 1729–1738. doi: 10.1109/TBME.2014.2303294 24845283

22. Ruifrok AC, Katz RL, Johnston DA. Comparison of quantification of histochemical staining by hue-saturation-intensity (HSI) transformation and color-deconvolution. Appl Immunohistochem Mol Morphol. 2003;11: 85–91. doi: 10.1097/00129039-200303000-00014 12610362

23. Haralick RM, Shanmugam K, Dinstein I. Textural features for image classification. IEEE Trans Syst Man Cybern. 1973;SMC-3: 610–621. doi: 10.1109/TSMC.1973.4309314

24. Galloway MM. Texture analysis using gray level run lengths. Comput Graph Image Process. 1975;4: 172–179. doi: 10.1016/S0146-664X(75)80008-6

25. Irshad H, Veillard A, Roux L, Racoceanu D. Methods for nuclei detection, segmentation, and classification in digital histopathology: A review-current status and future potential. IEEE Rev Biomed Eng. 2014;7: 97–114. doi: 10.1109/RBME.2013.2295804 24802905

26. Friedman J, Hastie T, Tibshirani R. Regularization paths for generalized linear models via coordinate descent. J Stat Softw. 2010;33: 1–22. doi: 10.1359/JBMR.0301229 20808728

27. Kuhn M. Building predictive models in R using the caret package. J Stat Softw. 2008;28: 1–26. doi: 10.18637/jss.v028.i07

28. Tibshirani R. Regression shrinkage and selection via the lasso: A retrospective. J R Stat Soc Ser B Stat Methodol. 2011;73: 273–282. doi: 10.1111/j.1467-9868.2011.00771.x

29. Therneau T, Grambsch P. Modeling survival data: extending the Cox model. Technometrics. 2002;44: 85–86. doi: 10.1198/tech.2002.s656

30. Yeh FC, Parwani A, Pantanowitz L, Ho C. Automated grading of renal cell carcinoma using whole slide imaging. J Pathol Inform. 2014;5: 23. doi: 10.4103/2153-3539.137726 25191622

31. Kruk M, Kurek J, Osowski S, Koktysz R, Swiderski B, Markiewicz T. Ensemble of classifiers and wavelet transformation for improved recognition of Fuhrman grading in clear-cell renal carcinoma. Biocybern Biomed Eng. 2017;37: 357–364. doi: 10.1016/j.bbe.2017.04.005

32. Holdbrook DA, Singh M, Choudhury Y, Kalaw EM, Koh V, Tan HS, et al. Automated Renal Cancer Grading Using Nuclear Pleomorphic Patterns. JCO Clin Cancer Informatics. 2018; 1–12. doi: 10.1200/cci.17.00100 30652593

33. Heng YJ, Lester SC, Tse GMK, Factor RE, Allison KH, Collins LC, et al. The molecular basis of breast cancer pathological phenotypes. J Pathol. 2017;241: 375–391. doi: 10.1002/path.4847 27861902

34. Hatipoglu N, Bilgin G. Cell segmentation in histopathological images with deep learning algorithms by utilizing spatial relationships. Med Biol Eng Comput. 2017;55: 1829–1848. doi: 10.1007/s11517-017-1630-1 28247185

35. Kumar N, Verma R, Sharma S, Bhargava S, Vahadane A, Sethi A. A dataset and a technique for generalized nuclear segmentation for computational pathology. IEEE Trans Med Imaging. 2017;36: 1550–1560. doi: 10.1109/TMI.2017.2677499 28287963

Článek vyšel v časopise


2019 Číslo 10
Nejčtenější tento týden