Spatial assessments in texture analysis: what the radiologist needs to know

Abstract

To date, studies investigating radiomics-based predictive models have tended to err on the side of data-driven or exploratory analysis of many thousands of extracted features. In particular, spatial assessments of texture have proven to be especially adept at assessing for features of intratumoral heterogeneity in oncologic imaging, which likewise may correspond with tumor biology and behavior. These spatial assessments can be generally classified as spatial filters, which detect areas of rapid change within the grayscale in order to enhance edges and/or textures within an image, or neighborhood-based methods, which quantify gray-level differences of neighboring pixels/voxels within a set distance. Given the high dimensionality of radiomics datasets, data dimensionality reduction methods have been proposed in an attempt to optimize model performance in machine learning studies; however, it should be noted that these approaches should only be applied to training data in order to avoid information leakage and model overfitting. While area under the curve of the receiver operating characteristic is perhaps the most commonly reported assessment of model performance, it is prone to overestimation when output classifications are unbalanced. In such cases, confusion matrices may be additionally reported, whereby diagnostic cut points for model predicted probability may hold more clinical significance to clinical colleagues with respect to related forms of diagnostic testing.

Keywords: artificial intelligence; machine learning; radiomics; spatial assessment; texture analysis.

Figure 1

Top row: (A) grayscale image with four different gray-levels. (B) Digitized version of the gray-level image with unique numerical values corresponding to the gray-level or a range of gray-levels (dependent on bin size of bin width) for each theoretical pixel/voxel. (C) GLCM map of the image obtained for distance 1 and direction 0 degrees. (D) This same process is then repeated in all other directions: i.e., 45, 90, and 135 deg, respectively. To obtain direction invariant results, all results are normalized and averaged. Middle row: (A) Grayscale image with four different gray-levels. (B) Digitized version of the gray-level image with unique numerical values corresponding to the gray-level or a range of gray-levels (dependent on bin size of bin width) for each theoretical pixel/voxel. (C) GLRLM map of the image obtained for direction zero degrees. This same process is then repeated in all other directions: i.e., 45, 90, and 135 deg, respectively. To obtain direction invariant results all results are normalized and averaged. Bottom row: (A) grayscale image with four different gray-levels. (B) Digitized version of the gray-level image with unique numerical values corresponding to the gray-level or a range of gray-levels (dependent on bin size of bin width) for each theoretical pixel/voxel. (C) GLSZM map of the image. GLCM, Gray-Level Co-Occurrence Matrix; GLRLM, Gray-Level Run-Length Matrix; GLSZM, Gray-Level Size-Zone Matrix.

Figure 2

Axial contrast-enhanced T1-weighted MR image with fat suppression of a 70-year-old male with leiomyosarcoma of the posterolateral calf (A), with corresponding texture parameter maps for Gray-Level Co-Occurrence Matrix (GLCM) homogeneity (B), GLCM contrast (C), GLCM energy (D) and GLCM correlation (E). The GLCM homogeneity map (B) reflects the closeness of the distribution of elements in the GLCM map relative to the GLCM diagonal. Highly homogenous regions (i.e., regions with less variation; close to the GLCM diagonal) receive a value of 1, while highly heterogenous regions receive a value of 0. The GLCM contrast map (C) measures the intensity contrast between an index pixel and its neighborhood pixels. Regions of high contrast show high heterogeneity in values up to a maximum value of 1. A constant image receives a value of 0. In some studies, contrast may also be referred to as variance and inertia. The GLCM energy map (D) measures the sum of the squared elements in the GLCM, whereby highly homogenous regions receive values of 1 and highly heterogenous regions receive values of 0. In some studies, energy may also be referred to as angular second moment, uniformity, or uniformity of energy. The GLCM correlation map (E) reflects how correlated a given pixel is to its neighboring pixels, with highly correlated regions receiving values of 1. In general, a neighborhood of 3 × 3 was adopted for the GLCM approach. Original image (A) courtesy of The Cancer Genome Atlas Sarcoma Collection (TCGA-SARC) based on data generated by the TCGA research network: http://cancergenome.nih.gov/ (38, 39).