Two-dimensional sample entropy: assessing image texture through irregularity

Autor(es)

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

• Tipo de documento: Artigo Científico
• Fonte: BIOMEDICAL PHYSICS & ENGINEERING EXPRESS; v. 2, n. 4 AUG 2016.
• Citações Web of Science: 8

Resumo

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)

• Processo FAPESP: 13/15445-8 - Desenvolvimento de métodos para avaliação de displasia cortical em pacientes com epilepsia refratária através da análise de imagens de ressonância magnética
• Beneficiário: Luiz Otavio Murta Junior
• Modalidade de apoio: Bolsas no Exterior - Pesquisa
• Processo FAPESP: 13/01111-0 - Estudo da velocidade de condução nervosa, sensitiva e motora, em ratos espontaneamente hipertensos (SHR), segundo a evolução da hipertensão
• Beneficiário: Valéria Paula Sassoli Fazan
• Modalidade de apoio: Auxílio à Pesquisa - Regular