Classification of Prostate Histopathology Images Based on Multifractal Analysis

Chamidu ATUPELAGE  Hiroshi NAGAHASHI  Masahiro YAMAGUCHI  Tokiya ABE  Akinori HASHIGUCHI  Michiie SAKAMOTO  

Publication
IEICE TRANSACTIONS on Information and Systems   Vol.E95-D   No.12   pp.3037-3045
Publication Date: 2012/12/01
Online ISSN: 1745-1361
DOI: 10.1587/transinf.E95.D.3037
Print ISSN: 0916-8532
Type of Manuscript: PAPER
Category: Pattern Recognition
Keyword: 
histopathology,  prostate cancer,  fractal geomatry,  multifractal,  feature descriptors,  classification,  

Full Text: PDF(762.6KB)>>
Buy this Article




Summary: 
Histopathology is a microscopic anatomical study of body tissues and widely used as a cancer diagnosing method. Generally, pathologists examine the structural deviation of cellular and sub-cellular components to diagnose the malignancy of body tissues. These judgments may often subjective to pathologists' skills and personal experiences. However, computational diagnosis tools may circumvent these limitations and improve the reliability of the diagnosis decisions. This paper proposes a prostate image classification method by extracting textural behavior using multifractal analysis. Fractal geometry is used to describe the complexity of self-similar structures as a non-integer exponent called fractal dimension. Natural complex structures (or images) are not self-similar, thus a single exponent (the fractal dimension) may not be adequate to describe the complexity of such structures. Multifractal analysis technique has been introduced to describe the complexity as a spectrum of fractal dimensions. Based on multifractal computation of digital imaging, we obtain two textural feature descriptors; i) local irregularity: α and ii) global regularity: f(α). We exploit these multifractal feature descriptors with a texton dictionary based classification model to discriminate cancer/non-cancer tissues of histopathology images of H&E stained prostate biopsy specimens. Moreover, we examine other three feature descriptors; Gabor filter bank, LM filter bank and Haralick features to benchmark the performance of the proposed method. Experiment results indicated that the performance of the proposed multifractal feature descriptor outperforms the other feature descriptors by achieving over 94% of correct classification accuracy.