Considerations for MRI study design and implementation in pediatric and clinical populations

Abstract

Human neuroimaging, specifically magnetic resonance imaging (MRI), is being used with increasing popularity to study brain structure and function in development and disease. When applying these methods to developmental and clinical populations, careful consideration must be taken with regard to study design and implementation. In this article, we discuss two major considerations particularly pertinent to brain research in special populations. First, we discuss considerations for subject selection and characterization, including issues related to comorbid conditions, medication status, and clinical assessment. Second, we discuss methods and considerations for acquisition of adequate, useable MRI data. Given that children and patients may experience anxiety with the scanner environment, preventing participation, and that they have a higher risk of motion artifact, resulting in data loss, successful subject compliance and data acquisition are not trivial tasks. We conclude that, as researchers, we must consider a number of issues when using neuroimaging tools to study children and patients, and we should thoughtfully justify our choices of methods and study design.

Keywords: Development; Inclusion/exclusion criteria; Mock scanner; Motion artifact; Neuroimaging; Neuropsychiatric disorders; Tourette syndrome.

Fig. 1

Pictorial display of resting state fMRI gray matter signals from 2 adult subjects. Top 2 panels show movement traces (top) and gray matter signal intensity (second from the top). The middle 3 gray panels show the effect of regressing increasing numbers of motions parameters. The bottom panel shows the effect of regressing the global signal. Yellow arrows point to examples of motion artifact that remain in the data until global signal regression is applied. FD_Power: framewise displacement as calculated in Power et al. (2012); WM: white matter signal; CSF: ventricle signal; GS: global signal (whole-brain average); R: realignment estimates (6 parameters representing translation and rotation). The 12 motion parameters are [R R′], the 24 are [R R²R_t−1R²_t−1], and the 36 are [R R²R_t−1R²_t−1R_t−2R²_t−2], where subscripts represent the estimates from 1 or 2 previous frames, the prime represents the difference from the previous frame, and the superscript 2 means squared. Figure modified from Power et al. (2015). (For interpretation of the references to color in this figure legend, the reader is referred to the web version of this article.)