Two-dimensional sample entropy: assessing image texture through irregularity

Author(s)

Silva, L. E. V. ; Senra Filho, A. C. S. ; Fazan, V. P. S. ; Felipe, J. C. ; Murta Junior, L. O.

• Document type: Journal article
• Source: BIOMEDICAL PHYSICS & ENGINEERING EXPRESS; v. 2, n. 4 AUG 2016.
• Web of Science Citations: 8

Abstract

Image texture analysis is a key task in computer vision. Although various methods have been applied to extract texture information, none of them are based on the principles of sample entropy, which is a measurement of entropy rate. This paper proposes a two-dimensional sample entropy method, namely SampEn(2D), in order to measure irregularity in pixel patterns. Weevaluated the proposed method in three different situations: a set of simulated images generated by a deterministic function corrupted with different levels of a stochastic influence; the Brodatz public texture database; and a real biological image set of rat sural nerve. Evaluation with simulations showed SampEn(2D) as a robust irregularity measure, closely following sample entropy properties. Results with Brodatz dataset testified superiority of SampEn(2D) to separate different image categories compared to conventional Haralick and wavelet descriptors. SampEn(2D) was also capable of discriminating rat sural nerve images by age groups with high accuracy (AUROC = 0.844). No significant difference was found between SampEn2DAUROCand those obtained with the best performed Haralick descriptors, i.e. entropy (AUROC = 0.828), uniformity (AUROC = 0.833), homogeneity (AUROC = 0.938) and Wavelet descriptors, i.e. Haar energy/entropy (AUROC = 0.932) and Daubechies energy/entropy (AUROC = 0.859). In addition, it was shown that SampEn(2D) computation time increases with image size, being around 1400 s for a 600x600 pixels image. In conclusion, SampEn(2D) showed to be stable and robust enough to be applied as texture feature quantifier and irregularity properties, as measured by SampEn(2D), seem to be an important feature for image characterization in biomedical image analysis. (AU)

• FAPESP's process: 13/15445-8 - Development of methods for evaluating cortical dysplasia in patients with refractory epilepsy by analyzing magnetic resonance images
• Grantee: Luiz Otavio Murta Junior
• Support Opportunities: Scholarships abroad - Research
• FAPESP's process: 13/01111-0 - Sensory and motor conduction velocity in spontaneously hypertensive rats
• Grantee: Valéria Paula Sassoli Fazan
• Support Opportunities: Regular Research Grants