Title: Multi-feature prostate cancer diagnosis of histological images using advanced image segmentation

Authors: S. Subha Rani, A. Kannammal, M.S. Nirmal, K. Vignesh Prabhu, R. Vinoth Kumar

Addresses: Department of ECE, PSG College of Technology, Peelamedu, Coimbatore-641 004, India. ' Department of ECE, PSG College of Technology, Peelamedu, Coimbatore-641 004, India. ' Department of ECE, PSG College of Technology, Peelamedu, Coimbatore-641 004, India. ' Department of ECE, PSG College of Technology, Peelamedu, Coimbatore-641 004, India. ' Department of ECE, PSG College of Technology, Peelamedu, Coimbatore-641 004, India

Abstract: We present a study of image features for cancer diagnosis of the histological images of prostate. In diagnosis, the tissue image is classified into the tumour and non-tumour classes. In Gleason grading, which characterises tumor aggressiveness, the image is classified as containing a low- or high-grade tumour. The primary contribution of this paper is to aggregate colour and texture properties at histological object levels for classification. Features representing different visual cues were combined in a supervised learning framework. We also compare the performance of Gaussian, k-nearest neighbour, and Bayesian classifier.

Keywords: computer-aided diagnosis; Gleason grading; statistical pattern recognition; prostate cancer diagnosis; histological images; image segmentation; image processing; image features; tumor aggressiveness; texture properties; colour properties; classification; supervised learning.

DOI: 10.1504/IJMEI.2010.036312

International Journal of Medical Engineering and Informatics, 2010 Vol.2 No.4, pp.408 - 416

Published online: 01 Nov 2010 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article