Article

Multifractal feature descriptor for histopathology.

Department of Computational Intelligence and Systems Science, Tokyo Institute of Technology, Tokyo, Japan.
Analytical cellular pathology (Amsterdam) (impact factor: 0.92). 11/2011; 35(2):123-6. DOI:10.3233/ACP-2011-0045
Source: PubMed

ABSTRACT Histologic image analysis plays an important role in cancer diagnosis. It describes the structure of the body tissues and abnormal structure gives the suspicion of the cancer or some other diseases. Observing the structural changes of these chaotic textures from the human eye is challenging process. However, the challenge can be defeat by forming mathematical descriptor to represent the histologic texture and classify the structural changes via a sophisticated computational method.
In this paper, we propose a texture descriptor to observe the histologic texture into highly discriminative feature space.
Fractal dimension describes the self-similar structures in different and more accurate manner than topological dimension. Further, the fractal phenomenon has been extended to natural structures (images) as multifractal dimension. We exploited the multifractal analysis to represent the histologic texture, which derive more discriminative feature space for classification.
We utilized a set of histologic images (belongs to liver and prostate specimens) to assess the discriminative power of the multifractal features. The experiment was organized to classify the given histologic texture as cancer and non-cancer. The results show the discrimination capability of multifractal features by achieving approximately 95% of correct classification rate.
Multifractal features are more effective to describe the histologic texture. The proposed feature descriptor showed high classification rate for both liver and prostate data sample datasets.

0 0
 · 
0 Bookmarks
 · 
103 Views
  • Source
    Article: Introduction to multifractal detrended fluctuation analysis in matlab.
    Espen A F Ihlen
    [show abstract] [hide abstract]
    ABSTRACT: Fractal structures are found in biomedical time series from a wide range of physiological phenomena. The multifractal spectrum identifies the deviations in fractal structure within time periods with large and small fluctuations. The present tutorial is an introduction to multifractal detrended fluctuation analysis (MFDFA) that estimates the multifractal spectrum of biomedical time series. The tutorial presents MFDFA step-by-step in an interactive Matlab session. All Matlab tools needed are available in Introduction to MFDFA folder at the website www.ntnu.edu/inm/geri/software. MFDFA are introduced in Matlab code boxes where the reader can employ pieces of, or the entire MFDFA to example time series. After introducing MFDFA, the tutorial discusses the best practice of MFDFA in biomedical signal processing. The main aim of the tutorial is to give the reader a simple self-sustained guide to the implementation of MFDFA and interpretation of the resulting multifractal spectra.
    Frontiers in physiology. 01/2012; 3:141.
Data provided are for informational purposes only. Although carefully collected, accuracy cannot be guaranteed. The impact factor represents a rough estimation of the journal's impact factor and does not reflect the actual current impact factor. Publisher conditions are provided by RoMEO. Differing provisions from the publisher's actual policy or licence agreement may be applicable.

Keywords

accurate manner
 
body tissues
 
chaotic textures
 
classification rate
 
correct classification rate
 
discrimination capability
 
discriminative feature space
 
discriminative power
 
fractal phenomenon
 
given histologic texture
 
Histologic image analysis
 
histologic images
 
mathematical descriptor
 
multifractal analysis
 
multifractal dimension
 
Multifractal features
 
non-cancer
 
prostate data sample datasets
 
sophisticated computational method
 
structural changes