Application of Haralick Texture Analysis to Differentiate Suspicious Prostate Lesions from Normative Tissue on Low-field MRI

Abstract

Haralick texture features extract frequencies of local spatial variations in signal intensity, quantifying pixel relationships within regions of interest. In this study, Haralick texture features were used to differentiate biopsy-proven, cancerous lesions from non-suspicious regions in low-field MR images. The results demonstrate consistency in texture measures for cancerous regions compared to non-suspicious, where Energy and Homogeneity are elevated while Contrast and Correlation are reduced within cancerous regions compared to non-suspicious regions.