A Bayesian Nonparametric Model for Textural Pattern Heterogeneity
针对CT图像纹理分析中灰度共生矩阵的冗余统计量问题，提出贝叶斯多元概率框架，直接对矩阵对象进行聚类，并用于肾上腺病变图像的分型与病理诊断对照。
Abstract Cancer radiomics is an emerging discipline promising to elucidate lesion phenotypes and tumour heterogeneity through patterns of enhancement, texture, morphology and shape. The prevailing technique for image texture analysis relies on the construction and synthesis of grey-level co-occurrence matrices (GLCM). Practice currently reduces the structured count data of a GLCM to reductive and redundant summary statistics for which analysis requires variable selection and multiple comparisons for each application, thus limiting reproducibility. In this article, we develop a Bayesian multivariate probabilistic framework for the analysis and unsupervised clustering of a sample of GLCM objects. By appropriately accounting for skewness and zero inflation of the observed counts and simultaneously adjusting for existing spatial autocorrelation at nearby cells, the methodology facilitates estimation of texture pattern distributions within the GLCM lattice itself. The techniques are applied to cluster images of adrenal lesions obtained from CT scans with and without administration of contrast. We further assess whether the resultant subtypes are clinically oriented by investigating their correspondence with pathological diagnoses. Additionally, we compare performance to a class of machine learning approaches currently used in cancer radiomics with simulation studies.