Gleason grade-based automatic classification of prostate cancer pathological images
Ali Almuntashri, Sos С. Agaian, Ian Murchie Thompson, Danny Munther Rabah, Osman Zin Al-Abdin, Marlo M. Nicolas · 2011
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.