A Boosting Cascade for Automated Detection of Prostate Cancer from Digitized Histology

  • Scott Doyle
  • Anant Madabhushi
  • Michael Feldman
  • John Tomaszeweski
Part of the Lecture Notes in Computer Science book series (LNCS, volume 4191)


Current diagnosis of prostatic adenocarcinoma is done by manual analysis of biopsy tissue samples for tumor presence. However, the recent advent of whole slide digital scanners has made histopathological tissue specimens amenable to computer-aided diagnosis (CAD). In this paper, we present a CAD system to assist pathologists by automatically detecting prostate cancer from digitized images of prostate histological specimens. Automated diagnosis on very large high resolution images is done via a multi-resolution scheme similar to the manner in which a pathologist isolates regions of interest on a glass slide. Nearly 600 image texture features are extracted and used to perform pixel-wise Bayesian classification at each image scale to obtain corresponding likelihood scenes. Starting at the lowest scale, we apply the AdaBoost algorithm to combine the most discriminating features, and we analyze only pixels with a high combined probability of malignancy at subsequent higher scales. The system was evaluated on 22 studies by comparing the CAD result to a pathologist’s manual segmentation of cancer (which served as ground truth) and found to have an overall accuracy of 88%. Our results show that (1) CAD detection sensitivity remains consistently high across image scales while CAD specificity increases with higher scales, (2) the method is robust to choice of training samples, and (3) the multi-scale cascaded approach results in significant savings in computational time.


Receiver Operating Characteristic Curve Texture Feature High Scale Image Scale Prostatic Adenocarcinoma 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.


  1. 1.
    Matlaga, B., Eskew, L., McCullough, D.: Prostate Biopsy: Indications and Technique. The Journal of Urology 169(1), 12–19 (2003)CrossRefGoogle Scholar
  2. 2.
    Madabhushi, A., et al.: Automated detection of prostatic adenocarcinoma from high resolution ex-vivo MRI. IEEE Trans. on Med. Imaging 24(12), 1611–1625 (2005)CrossRefGoogle Scholar
  3. 3.
    Wetzel, A.W., et al.: Evaluation of prostate tumor grades by content based image retrieval. In: Proc. of SPIE Annual Meeting, vol. 3584, pp. 244–252 (1999)Google Scholar
  4. 4.
    Esgiar, A.N., et al.: Microscopic image analysis for quantitative measurement and feature identification of normal and cancerous colonic mucosa. IEEE Trans. on Information Tech. in Biomedicine 2(3), 197–203 (1998)CrossRefGoogle Scholar
  5. 5.
    Tabesh, A., et al.: Automated prostate cancer diagnosis and Gleason grading of tissue microarrays. In: Proc. of the SPIE, vol. 5747, pp. 58–70 (2005)Google Scholar
  6. 6.
    Viola, P., Jones, M.: Rapid object detection using a boosted cascade of simple features. In: IEEE Conf. Comp. Vision and Pattern Recog., vol. 1, pp. 511–518 (2001)Google Scholar
  7. 7.
    Freund, Y., Schapire, R.: Experiments with a new boosting algorithm. In: Proc. of the Natural Conf. on Machine Learning, pp. 148–156 (1996)Google Scholar
  8. 8.
    Adelson, E.H., Burt, P.J.: Image data compression with the Laplacian pyramid. In: Proc. of Pattern Recog. and Inf. Proc. Conf., pp. 218–223 (1981)Google Scholar
  9. 9.
    Duda, R.O., Hart, P.E.: Pattern Classification and Scene Analysis. Wiley, Chichester (1973)zbMATHGoogle Scholar
  10. 10.
    Haralick, R.M., Shanmugan, K., Dinstein, I.: Textural features for image classification. IEEE Trans. on Systems, Man, and Cybernetics SMC-3, 610–621 (1973)CrossRefGoogle Scholar
  11. 11.
    Manjunath, B.S., Ma, W.Y.: Texture features for browsing and retrieval of image data. IEEE Trans. Pattern Anal. Machine Intell. 2, 837–842 (1996)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Scott Doyle
    • 1
  • Anant Madabhushi
    • 1
  • Michael Feldman
    • 2
  • John Tomaszeweski
    • 2
  1. 1.Dept. of Biomedical EngineeringRutgers Univ.PiscatawayUSA
  2. 2.Dept. of Surgical PathologyUniv. of PennsylvaniaPhiladelphiaUSA

Personalised recommendations