Diffusion weighted magnetic resonance imaging (dMRI) is a powerful magnetic resonance modality that provides a wealth of information regarding tissue microstructure, from which structural connectivity and pathological changes within the brain can be inferred [1,2]. As different microstructures predictably retard diffusion, the apparent diffusion of molecules combined with the angle of an applied diffusion gradient provides an indirect measure of neuroanatomy [3]. The most commonly used dMRI technique is diffusion tensor imaging (DTI). For DTI, a series of pulsed-gradient, spin–echoes are used to produce a 3x3 symmetric matrix modelling Gaussian diffusion (3). Most commonly, DTI characterizes the overall water diffusion within a given voxel by measuring mean diffusivity (MD) and the degree of directionality of the principle component of this diffusion, through fractional anisotropy (FA). This technique has been utilized for many years and has provided valuable insights into the effects of disease, as well as neurological and physiological processes [4–8].

However, subtle tissue diffusion characteristics may be missed in DTI because the method lacks the specificity to identify unique microstructural environments. For example, DTI cannot distinguish between distinct processes such as the loss of structural integrity and neural remodelling, and as a result provides an inherently vague and limited model of neuroanatomy [9,10]. Several more sophisticated dMRI models have been developed to overcome the limitations of DTI such as Q-Ball imaging [11], CHARMED [12], diffusion kurtosis imaging [13], oscillating gradient diffusion MRI [14], and more recently neurite orientation dispersion and density imaging (NODDI) [15]. NODDI examines neurite morphology by specifically probing the unique diffusion patterns within three separate microstructural environments: intra-neurite, extra-neurite, and CSF compartments [15].

Diffusion patterns within the brain may be separated into three distinct microstructural environments: highly restricted within neurites (intra neurite compartment), hindered diffusion near neurites (extra-neurite compartment) and free diffusion within the CSF compartment [16]. A carefully designed diffusion weighting scheme in an MRI pulse sequence combined with NODDI modelling is used to produce scalar maps indicating the volume fraction contribution of each compartment to the full diffusion signal. The intra-neurite space is modelled as cylinders of zero radius (modelling highly restricted diffusion perpendicular to neurites and free diffusion parallel to neural tracts) dispersed according to the Watson distribution (ranging from heavily dispersed to entirely parallel) while the extra-neurite space is modelled as Gaussian anisotropic diffusion [17]. Lastly the CSF compartment is modelled with Gaussian isotropic diffusion [15].

The NODDI acquisition incorporates a multi-shell protocol that leads to a multi-compartmental diffusion MR signal. Previous work has shown that the use of 2 shells (each shell corresponding to a subset of diffusion weightings known as b-values) combined with several b = 0 images, is sufficient to obtain NODDI scalar maps in-vivo [15]. These images are reconstructed based on the Stejskal-Tanner equations for a pulsed gradient spin-echo (PGSE) experiment, and the total signal determined to be the sum of the individual contributions from three non-exchanging tissue compartments (intra-cellular, extra-cellular, and CSF compartments) [15]. From this signal, quantitative scalar image maps may be reconstructed yielding the following NODDI metrics: Orientation Dispersion Index (ODI), Neurite Density Index (NDI), and Isotropic volume fraction (IsoVF). Additionally, by ensuring one shell conforms to DTI acquisition standards (e.g. a single shell with > six directions of b = 1000 s/mm² and one b = 0 volume) [1], it is possible within a single scan to obtain standard diffusion tensor metrics such as fractional anisotropy (FA) and mean diffusivity (MD). It is commonly recommended that DTI and NODDI be acquired simultaneously and analyzed together [10]. While MD and FA are routine measures obtained in diffusion imaging, the addition of the ODI, NDI, and IsoVF scalar maps can provide a more specific analysis of complex neuroanatomy [9,10]. ODI characterizes the angular variation and spatial configuration of neurite structures. NDI represents the fraction of tissue that comprises axons or dendrites (also referred to as intra-neurite volume fraction). Extra-neurite fraction may be reconstructed as 1- NDI, and as such provides does not provide unique information above NDI. IsoVF represents the CSF water fraction [15].

Previous use of NODDI has focused largely on the feasibility, reproducibility, and application to human imaging at field strengths up to 3 Tesla [18–24]. Specifically, it was shown that NODDI metrics were significantly dependent on field strength [25]. Many pre-clinical studies use rodent models to study neuro-pathological processes requiring extremely small voxel sizes relative to that used in human MRI. Image signal to noise ratio (SNR) is directly proportional to voxel size and to main magnetic field strength. Therefore, the use of ultra-high field strengths combined with strong imaging gradients helps to achieve adequate SNR for diffusion modelling at the image resolution required in rodent models [26]. While the feasibility of NODDI at 9.4 Tesla has been shown [27], we are aware of no studies that have explored reproducibility in rodent models at 9.4 Tesla. As ultra-high field MRI, and specifically pre-clinical rodent MRI, faces many unique challenges such as increased magnetic field inhomogeneities and physiological noise [28], it is important to carefully define reproducibility in the context of ultra-high field rodent imaging. Thus, our specific objective was to determine the reproducibility of the three most commonly derived NODDI metrics (ODI, NDI and IsoVF) at 9.4 Tesla in the rat brain. This information is crucial for the planning of future studies involving rat models of neurodegenerative disease or neurological injury.

The minimum accepted average whole-brain SNR was 25 at b = 0 for each of the included data sets. Two data sets were removed from the analysis due to low SNR causing significant reconstruction bias. Therefore, data were successfully acquired and analyzed from eight subjects (age 102 ± 13 days at time of initial scan, weight 323 ± 37 g) at two separate time points. For each subject the re-scan time point was between six and eight days after the original scan. The time of day was not standardized for the scans. Fig 1 shows representative cross sections of raw diffusion data (b = 0) from a single subject, as well as scalar maps of ODI, NDI, and IsoVF.

This study examined the reproducibility of the three most commonly derived NODDI metrics (ODI, NDI, and IsoVF) in the rodent brain at 9.4 Tesla. ODI and NDI were reproducible, showing low coefficients of variation in both the between and within subject conditions. CVs were lower within subjects compared to between subjects, indicating less variability on a within subject scan-rescan basis, as expected. These trends were observed in the mean ROI, whole brain voxel-wise, and targeted voxel-wise analyses.

Using the whole brain coefficients of variation on a voxel-by-voxel basis it was possible to detect changes on the order of 10% and 5% respectively in ODI and NDI metrics with feasible study samples sizes. For ODI, over 90% of voxels showed the ability to detect a 10% or greater change with sample sizes of five or more, while NDI showed the ability to detect a change of 5% or greater with sample sizes of five or more. NDI was the most sensitive in all cases, followed by ODI. Furthermore, it was shown that using a scan-rescan protocol and standard sample sizes (6, 8, and 10) it was possible to detect very small changes for both ODI and NDI. For example, sample sizes of eight per group (common to many preclinical studies) allowed biological effects as small as 5% to be detected on a voxel by voxel basis for both metrics.

While ODI and NDI were shown to be reproducible metrics, IsoVF was not. This was shown previously in similar studies of the human brain [25]. The IsoVF metric suffers from not only low values intrinsically in the given context but is also highly susceptible to noise [25]. This combination led to high average CVs (> 20%) in all measures explored in this study. Consequently, with the scan parameters used in this study, the reproducibility of IsoVF is limited. Improvements in SNR could increase the reproducibility of IsoVF but would come at the cost of increased scan time, decreased image resolution, or decreased angular resolution. It should be noted that inaccurate estimates of IsoVF could slightly bias the absolute values of NDI at low SNR, however this bias is expected to be consistent across all subjects and scans, allowing meaningful comparisons to be made under consistent scan parameters. As of now the optimal angular and image resolution in a rodent model of NODDI has yet to be explored, and it must be assumed that higher resolution in both improves the quality of the resulting scalar metric maps. Thus, an increase in scan time would be necessary. As the scan time in the present study was already high (83 minutes) it may be that the necessary scan time to improve the quality of IsoVF scalar maps is not feasible or cost effective.

These findings are consistent with previous research using human subjects. In humans, NODDI has been shown to produce accurate and reproducible metrics of ODI and NDI both between and within subjects [25]. The magnitude of NDI, ODI, and IsoVF have been shown to vary at different field strengths [25], and thus it is important to characterize these metrics not only in new animal models, but also at each field strength used. At the time of writing we are not aware of any other studies that specifically look at the reproducibility of NODDI in an in-vivo rodent model. This study shows NODDI to be reproducible in a rodent model at 9.4 Tesla and that this technique has the potential to detect very subtle tissue microstructure changes in a rodent model.

There are several limitations that should be considered in this study. Registration was performed using FLIRT [35] and FNIRT [37] in FSL. The quality of these registrations was not specifically quantified in terms of similarity overlap. As the quality of registration is important to both ROI and voxel-wise analyses, future studies may benefit from improvements and optimization of the registration process. Specifically, when using a targeted voxel-wise approach within a given ROI, registration can be optimized within that region, thereby increasing the precision of the analysis. Currently, the optimal angular resolution, image resolution and b-value combination in our NODDI pulse sequence has not been fully explored in a rodent model at 9.4 Tesla. It is possible that at high angular resolution more subtle changes in orientation are detected, and at higher image resolution more subtle changes in neurite microstructure may be shown. Furthermore, these parameters may vary greatly in coherently ordered white matter compared to less ordered structures within regions of grey matter and may be altered in disease states. These considerations must be balanced against scan time for any in-vivo study. Further exploration of optimal angular resolution sampling schemes and image resolution would lend strength to this technique and lead to a more robust acquisition and analysis pipeline. Additionally, the optimal b-value has not been expressly explored in rodents at 9.4 Tesla. In humans, the optimal b-values were explored through simulation and in-vivo study, and it was found that as long as two shells with moderate b-value were used, the precise choice of b-value made minimal difference [15]. Finally, it should be noted that for the within-subject calculation of CV, the standard deviation was determined from only two data points. As a result this this standard deviation may not accurately represent the spread of data within the population, leading to an unknown bias in the resulting CV.

The current study was designed to evaluate reproducibility of the NODDI metrics over a one-week interval, as this interval is relevant for many time course studies. While subtle changes in brain plasticity were of some concern, the results show that over this interval the ODI and NDI metrics were reproducible. Finally, we know of no studies which have expressly attempted to produce a template of absolute values of NODDI metrics within various brain regions of rodents at 9.4 Tesla. While intrinsic variability will always be present in these values due to scan parameters, it would be useful to attempt this characterization for all brain regions.

Preclinical imaging techniques, and specifically diffusion imaging techniques, are designed to detect very subtle changes in disease models, which may not be seen with anatomical based imaging techniques. The potential to improve the ability to detect these very small changes through novel neuroimaging techniques, such as NODDI, could illuminate early events in disease processes such as neurodegeneration. Early detection of key pathways and mechanisms involved in the progression of these devastating diseases may lead to a more thorough understanding of the downstream biological effects. By showing NODDI metrics to be reproducible in a rodent model at ultra-high field strengths, we may now apply this technique to appropriate pre-clinical models, in an effort to further our understanding of complex diseases processes affecting neuroanatomy.