Gleason grade-based automatic classification of prostate cancer pathological images

Author

Almuntashri, Ali ; Agaian, Sos ; Thompson, Ian ; Rabah, Danny ; Al-Abdin, Osman Zin ; Nicolas, Marlo

Author_Institution

Coll. of Eng., Univ. of Texas at San Antonio, San Antonio, TX, USA

fYear

2011

fDate

9-12 Oct. 2011

Firstpage

2696

Lastpage

2701

Abstract

In this Paper, we introduce a new method for automatic recognition and classification of prostate cancer biopsy images based on Gleason grading system. The introduced algorithm combines features from wavelet transform and fractal analysis domains. Biopsy images are pre-processed prior to features extraction using effective image processing algorithms to analyze textural complexity in terms of RGB color channels, edge and segmentation information. Experimental results achieved an average classification accuracy of 95% in a set of 45 images with diversities in resolution, magnification levels, and stain colors.

Keywords

cancer; feature extraction; fractals; image classification; image colour analysis; image segmentation; image texture; medical image processing; wavelet transforms; Gleason grading system; RGB color channel; automatic image recognition; features extraction; fractal analysis domain; image classification; image processing; prostate cancer biopsy image; prostate cancer pathological image; segmentation information; textural complexity; wavelet transform; Biopsy; Classification algorithms; Feature extraction; Fractals; Image edge detection; Support vector machine classification; Wavelet transforms; Gleason grading; Prostate cancer; fractal dimension; statistical classification; wavelet features;

fLanguage

English

Publisher

ieee

Conference_Titel

Systems, Man, and Cybernetics (SMC), 2011 IEEE International Conference on

Conference_Location

Anchorage, AK

ISSN

1062-922X

Print_ISBN

978-1-4577-0652-3

Type

conf

DOI

10.1109/ICSMC.2011.6084080

Filename

6084080