Radiomics in Stroke Neuroimaging: Techniques, Applications, and Challenges

Abstract

Stroke is a leading cause of disability and mortality worldwide, resulting in substantial economic costs for post-stroke care each year. Neuroimaging, such as cranial computed tomography or magnetic resonance imaging, is the backbone of stroke management strategies, which can guide treatment decision-making (thrombolysis or hemostasis) at an early stage. With advances in computational technologies, particularly in machine learning, visual image information can now be converted into numerous quantitative features in an objective, repeatable, and high-throughput manner, in a process known as radiomics. Radiomics is mainly used in the field of oncology, which remains an area of active research. Over the past few years, investigators have attempted to apply radiomics to stroke in the hope of gaining benefits similar to those obtained in cancer management, i.e., in promoting the development of personalized precision medicine. Currently, radiomic analysis has shown promise for a variety of applications in stroke, including the diagnosis of stroke lesions, early prediction of outcomes, and evaluation for long-term prognosis. In this article, we elaborate the contributions of radiomics to stroke, as well as the subprocesses and techniques involved in radiomics studies. We also discuss the potential challenges facing its widespread implementation in routine practice and the directions for future research.

Keywords: decision-making; neuroimaging; radiomics; stroke; texture analysis.

Figure 1.

Flowchart shows the typical process of radiomics in stroke neuroimaging. (A) Example CT image of an intracerebral hemorrhage and (B) example MR image of a patient with ischemic stroke.

Figure 2.

Texture in radiomics. (A) A stylized gray-level image (5 x 5 pixels) with grey values ranging from 0 (black) to 5 (white) and its derived gray-level co-occurrence matrix (GLCM) in horizontal (B), vertical (C), and oblique (D) directions. Row and column numbers in the GLCM represent corresponding gray values, while cells in white contain the number of times corresponding gray values occurs adjacent to each other in three directions. For example, the frequency of gray values of 0, 2, and 3 (red arrows on the gray-level image) is then mapped onto corresponding cell of GLCM (red circles) each time they occur adjacent to each other in particular direction. In texture analysis, GLCM represents spatial interrelationship between pixels within a digital image.