The diffusion tensor imaging toolbox

Abstract

During the past few years, The Journal of Neuroscience has published more than 30 articles that describe investigations that used Diffusion Tensor Imaging (DTI) and related techniques as a primary observation method. This illustrates a growing interest in DTI within the basic and clinical neuroscience communities. This article summarizes DTI methodology in terms that can be immediately understood by the neuroscientist who has little previous exposure to DTI. It describes the fundamentals of water molecular diffusion coefficient measurement in brain tissue and illustrates how these fundamentals can be used to form vivid and useful depictions of white matter macroscopic and microscopic anatomy. It also describes current research applications and the technique's attributes and limitations. It is hoped that this article will help the readers of this Journal to more effectively evaluate neuroscience studies that use DTI.

Figure 1.

Key elements of the spin echo pulse sequence used for DTI. The timing of off/on (0/1) events for the three most important MRI scanner subsystems (radiofrequency transmitter, diffusion-sensitizing gradient, and signal detection) is presented.

Figure 2.

Quantitative image of diffusion coefficient from a normal human subject. The gray scale to the right of the image indicates that image intensity represents the quantitative value of the diffusion coefficient (also referred to as diffusivity) of the brain tissue. Specifically, this is an image of Mean Diffusivity defined by Equation 12 (see text).

Figure 3.

DTI concept diagram. The middle panel illustrates water molecule diffusion trajectories in CSF, white matter, and gray matter. The top and bottom panels illustrate the effect of gradient-sensitizing direction on MRI signal intensity from these tissue regions. See text for further details.

Figure 4.

Diffusion-weighted images from a normal human subject obtained with two different diffusion-sensitizing gradient directions. These are 4-mm-thick sections acquired with diffusion-weighted spin echo echo planar imaging using a b-vector magnitude of 1000 s mm⁻² with the b-vector directed along the left/right axis (left) and the anterior/posterior axis (right). Ovals identify differing signal characteristics in three major white matter pathways [left–right-oriented corpus callosum spenium (solid oval), anterior–posterior-oriented temporofrontal pathway (dotted oval), and rising/descending pyramidal tracts (dashed oval)].

Figure 5.

DTI results images (FA, CM, AD, RD, MD) from a normal human subject. A T1-weighted image (T1wMRI) that depicts the traditional MRI view of brain anatomy has been aligned and resliced to match the DTI images. These images illustrate that DTI provides directional information about white matter fiber array orientation that is not present in traditional T1-weighted MRI and that DTI provides quantitative images of water diffusivity parallel to and perpendicular to the fiber array orientation. The color system used for the CM is displayed to the lower right of the CM. The CM allows the reader to immediately visualize the directional orientation of the primary eigenvector in the left–right, anterior–posterior, superior–inferior coordinate system.

Figure 6.

Three-dimensional volume renderings of DTI CM. Left lateral, frontal, and cranial views are provided. These images are presented to illustrate that DTI results are 3-dimensional image volumes. The color system is the same as that used in Figure 5.

Figure 7.

Fiber tractography of major white matter systems in a normal human subject: a left lateral view showing white matter structures passing through the corpus callosum (red), rising/descending pyramidal pathways (blue), and fronto-temporo-occipital pathways (green) are presented. Tractography was performed with DTIStudio/MRIStudio (www.mristudio.org).

Figure 8.

The left panel is a depiction of the diffusion ellipsoid derived from the diffusion tensors measured in each image voxel in a single 2 mm axial slice. Each ellipsoid is represented as a color-coded 3-dimensional object. Color coding reflects the direction of the principal eigenvalue using the color system defined in Figure 5. The right panel shows a magnified view of the region around the genu of the corpus callosum.