Post-acquisition mathematical analysis of medical images can range from simple image processing to complex computer-aided diagnosis. The intent of such manipulation can range from the enhancement of aspects of the image for improved human visualization to artificial intelligence. The tools available for image analysis span the fields of mathematics, statistics, and computer science and incorporate biophysical aspects of the medical image acquisition system. This chapter explores the concepts and practical implementation of one specific form of mathematical manipulation of CT images: texture analysis. Texture refers to the magnitude, spatial orientation, and structure of gray-level fluctuations within an image. The quantification of image textures attempts to capture underlying relationships among the values and spatial distributions of pixels and provides a way to objectively extract quantitative information from CT scans. Texture analysis has proven to be a powerful tool over a broad array of CT applications and a wide range of radiologic tasks in CT. An important caveat for the eventual clinical use of CT texture analysis is its dependence on CT image acquisition parameters, transformations to which an image might be subjected post-acquisition, and algorithmic details of the specific texture software package employed.
KeywordsComputed tomography (CT) Image texture Texture analysis Radiomics Image variability Robustness
- 4.Laws KI: Textured image segmentation. USCIPI Technical Report No. 940, University of Southern California, 1980.Google Scholar
- 6.Creutzburg R, Ivanov E. Fast algorithm for computing fractal dimensions of image segments. In: Cantoni V, Creutzburg R, Levialdi S, Wolf G, editors. Recent issues in pattern analysis and recognition. Lecture notes in computer science, vol. 399. Berlin, Heidelberg: Springer; 1989. p. 42–51..CrossRefGoogle Scholar
- 22.Nougaret S, Tardieu M, Vargas HA, Reinhold C, Vande Perre S, Bonanno N, Sala E, Thomassin-Naggara I. Ovarian cancer: an update on imaging in the era of radiomics. Diagnostic Interventional Imaging, DII-1134 (9 pages). 2018.Google Scholar
- 26.Cunliffe AR, Armato SG III, Castillo R, Pham N, Guerrero T, Al-Hallaq HA. Lung texture in serial thoracic computed tomography scans: correlation of radiomics-based features with radiation therapy dose and radiation pneumonitis development. Int J Radiat Oncol Biol Phys. 2015;91:1048–56.CrossRefGoogle Scholar
- 27.Aerts HJ, Velazquez ER, Leijenaar RT, Parmar C, Grossmann P, Cavalho S, Bussink J, Monshouwer R, Haibe-Kains B, Rietveld D, Hoebers F, Rietbergen MM, Leemans CR, Dekker A, Quackenbush J, Gillies RJ, Lambin P. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun. 2014;5:1–8.Google Scholar