Texture Analysis for Identifying Heterogeneity in Medical Images

Abstract

Abstract. Heterogeneity is a well-recognized feature of malignancy associated with increased tumor aggression and treatment resistance. Texture analysis (TA) of images of various modalities, including, among others, CT, MRI or PET, can be applied to quantify the tumor heterogeneity and to extract useful information from images acquired in routine clinical practice without additional radiation or expense of further procedures. In this paper, we elaborate on the filtration-based approach to TA applied for extracting features from large sets of simulated images reflecting various clinical circumstances. The areas under receiver operating characteristic curves were used to assess the diagnostic performance of the derived biomarkers. We present and discuss their discriminative abilities in identifying heterogeneity and classifying images with simulated lesions of various characteristics and localized density variations.

Virtual Biopsy in Soft Tissue Sarcoma. How Close Are We?

“…This study concluded that using a maximum of three features from first order statistics could achieve a model distinguishing grade with relatively good accuracy (78). Texture analysis tools can be applied to routine MR images to interrogate the inter-pixel relationships and grey level pattern of a ROI to provide a measure of heterogeneity (106,107). This was utilised in a retrospective study of 29 patients by Meyer et al to match Ki-67 index to discriminate between low and highly proliferating sarcomas (108 There remains occasions, particularly for STS located within the retroperitoneum, when MRI is not conducted and therefore CT radiomics remains a useful avenue to explore.…”