Abstract
Purpose:
Prostate cancer is routinely graded according to the Gleason grading scheme. This scheme is predominantly based on the textural appearance of aberrant glandular structures. Gleason grade is difficult to standardize and often leads to discussion due to interrater and intrarater disagreement. Thus, we investigated whether digital image based automated quantitative histomorphometry could be used to achieve a more standardized, reproducible classification outcome.
Materials and Methods:
In a proof of principle study we developed a method to evaluate digitized histological images of single prostate cancer regions in hematoxylin and eosin stained sections. Preprocessed color images were subjected to color deconvolution, followed by the binarization of obtained hematoxylin related image channels. Highlighted neoplastic epithelial gland related objects were morphometrically assessed by a classifier based on 2 calculated quantitative and objective geometric measures, that is inverse solidity and inverse compactness. The procedure was then applied to the prostate cancer probes of 125 patients. Each probe was independently classified for Gleason grade 3, 4 or 5 by an experienced pathologist blinded to image analysis outcome.
Results:
Together inverse compactness and inverse solidity were adequate discriminatory features for a powerful classifier that distinguished Gleason grade 3 from grade 4/5 histology. The classifier was robust on sensitivity analysis.
Conclusions:
Results suggest that quantitative and interpretable measures can be obtained from image based analysis, permitting algorithmic differentiation of prostate Gleason grades. The method must be validated in a large independent series of specimens.
References
- 1 : Molecular biology underlying the clinical heterogeneity of prostate cancer: an update. Arch Pathol Lab Med2009; 133: 1033. Google Scholar
- 2 : Heterogeneity of Gleason grade in multifocal adenocarcinoma of the prostate. Cancer2004; 100: 2362. Google Scholar
- 3 : Watchful waiting versus active surveillance: appropriate patient selection. Curr Urol Rep2008; 9: 211. Google Scholar
- 4 : Meta-analysis of prostate-specific antigen and digital rectal examination as screening tests for prostate carcinoma. J Am Board Fam Pract2003; 16: 95. Google Scholar
- 5 : Fusion in the ETS gene family and prostate cancer. Br J Cancer2008; 99: 847. Google Scholar
- 6 : Molecular pathways in the progression of hormone-independent and metastatic prostate cancer. Curr Cancer Drug Targets2010; 10: 392. Google Scholar
- 7 : MicroRNAs and prostate cancer. Acta Biochim Biophys Sin (Shanghai)2010; 42: 363. Google Scholar
- 8 : Emerging role of microRNAs in prostate cancer: implications for personalized medicine. Discov Med2010; 9: 212. Google Scholar
- 9 :
Urologic and male genital cancers: prostate cancer . In: Clinical Oncology: A Multidisciplinary Approach for Physicians and Students. Edited by . Philadelphia: WB Saunders2001: 538. Google Scholar - 10 : Classification of prostatic carcinomas. Cancer Chemother Rep1966; 50: 125. Medline, Google Scholar
- 11 :
Histological Typing of Prostate Tumours . In: . Berlin: Springer Verlag2002: 15. Google Scholar - 12 : Classification, histologic and cytologic grading and regression grading of prostate cancer. Urologe A1985; 24: 156. Google Scholar
- 13 : Interobserver reproducibility of Gleason grading: evaluation using prostate cancer tissue microarrays. J Cancer Res Clin Oncol2008; 134: 1071. Google Scholar
- 14 : The 2005 International Society of Urological Pathology (ISUP) consensus conference on Gleason grading of prostatic carcinoma. Am J Surg Pathol2005; 29: 1228. Google Scholar
- 15 : Modified Gleason grading: An updated review. Histol Histopathol2009; 24: 661. Google Scholar
- 16 : A hybrid neural and statistical classifier system for histopathologic grading of prostatic lesions. Anal Quant Cytol Histol1995; 17: 204. Google Scholar
- 17 : Multiwavelet grading of pathological images of prostate. IEEE Trans Biomed Eng2003; 50: 697. Google Scholar
- 18 : The use of morphological characteristics and texture analysis in the identification of tissue composition in prostatic neoplasia. Hum Pathol2004; 35: 1121. Google Scholar
- 19 : Multifeature prostate cancer diagnosis and Gleason grading of histological images. IEEE Trans Med Imaging2007; 26: 1366. Google Scholar
- 20 :
Quantify prostate cancer by automated histomorphometry . In: Bildverarbeitung für die Medizin 2008—Algorithmen, Systeme, Anwendungen. Edited by . Berlin: Springer-Verlag2008: 358. Google Scholar - 21 : The digital TV filter and nonlinear denoising. IEEE Trans Image Process2001; 10: 231. Google Scholar
- 22 : Quantification of histochemical staining by color deconvolution. Anal Quant Cytol Histol2001; 23: 291. Google Scholar
- 23 : Prognostic and predictive factors and reporting of prostate carcinoma in prostate needle biopsy specimens. Scand J Urol Nephrol Suppl2005; : 20. Google Scholar
- 24 : A UK-based investigation of inter- and intra-observer reproducibility of Gleason grading of prostatic biopsies. Histopathology2006; 48: 644. Google Scholar
- 25 : Review of the morphology of prostatic carcinoma with special emphasis on subgrading and prognosis. J Urol Pathol1993; 1: 3. Google Scholar
- 26 : Using nuclear morphometry to predict the need for treatment among men with low grade, low stage prostate cancer enrolled in a program of expectant management with curative intent. Prostate2008; 68: 183. Google Scholar
- 27 : Automatic classification for pathological prostate images based on fractal analysis. IEEE Trans Med Imaging2009; 28: 1037. Google Scholar
- 28 : High-throughput prostate cancer gland detection, segmentation, and classification from digitized needle core biopsies. Prostate Cancer Imaging2010; LNCS 6367: 77. Google Scholar
