Comparison of multiple tractography methods for reconstruction of the retinogeniculate visual pathway using diffusion MRI

Abstract

The retinogeniculate visual pathway (RGVP) conveys visual information from the retina to the lateral geniculate nucleus. The RGVP has four subdivisions, including two decussating and two nondecussating pathways that cannot be identified on conventional structural magnetic resonance imaging (MRI). Diffusion MRI tractography has the potential to trace these subdivisions and is increasingly used to study the RGVP. However, it is not yet known which fiber tracking strategy is most suitable for RGVP reconstruction. In this study, four tractography methods are compared, including constrained spherical deconvolution (CSD) based probabilistic (iFOD1) and deterministic (SD-Stream) methods, and multi-fiber (UKF-2T) and single-fiber (UKF-1T) unscented Kalman filter (UKF) methods. Experiments use diffusion MRI data from 57 subjects in the Human Connectome Project. The RGVP is identified using regions of interest created by two clinical experts. Quantitative anatomical measurements and expert anatomical judgment are used to assess the advantages and limitations of the four tractography methods. Overall, we conclude that UKF-2T and iFOD1 produce the best RGVP reconstruction results. The iFOD1 method can better quantitatively estimate the percentage of decussating fibers, while the UKF-2T method produces reconstructed RGVPs that are judged to better correspond to the known anatomy and have the highest spatial overlap across subjects. Overall, we find that it is challenging for current tractography methods to both accurately track RGVP fibers that correspond to known anatomy and produce an approximately correct percentage of decussating fibers. We suggest that future algorithm development for RGVP tractography should take consideration of both of these two points.

Keywords: cranial nerve; diffusion magnetic resonance imaging; human Connectome project; retinogeniculate visual pathway; tractography.

FIGURE 1

A schematic anatomical overview of the RGVP. There are four major subdivisions, including two nondecussating fiber pathways (orange and red) connecting the optic nerve and the optic tract in the same hemisphere and two decussating fiber pathways (green and blue) connecting the optic nerve and the optic tract across the hemispheres

FIGURE 2

Illustration of two situations for excluded subjects. (a) shows an example of an incomplete RGVP in DWI data, where part of the optic nerve region is not present in the b0 image. (b) shows an example of abnormal signals, where the black holes on the mean diffusivity image show the voxels with negative diffusion tensor eigenvalues

FIGURE 3

Tractography seeding mask and ROIs for selecting the RGVP fibers. (a) The tractography mask provides full coverage of the potential RGVP. (b) Five ROIs were drawn on the DTI image for every subject. (c) A pair of ROIs near the eyeball was drawn from the coronal view. (d) The second ROI was drawn at the optic chiasm. (e) The third ROIs were located in the optic tract near the LGN

FIGURE 4

Illustration of the reconstructed subdivisions of the RGVP. (a) Axial view of an example RGVP overlaid on T1w image. Bundles of each color represent one subdivision. (b) A pair of decussating fiber bundles (green and blue), and (c) a pair of nondecussating fiber bundles (red and orange)

FIGURE 5

Visualization of RGVP segmentations. (a) shows the expert RGVP segmentation in MNI space; (b) shows a subject's RGVP segmentation, which was warped from the RGVP segmentation in MNI space. (c) shows a RGVP segmentation computed from tractography results

FIGURE 6

Reconstruction rate of RGVP subdivisions using different tractography methods. The overall RGVP reconstruction rates were statistically significantly different across the four compared tractography methods (ANOVA, p < .0001). Posthoc two‐group Cochran's Q tests (with FDR correction) with significant results are indicated by asterisks. *: p < .05; **: p < .01; ****: p < .0001

FIGURE 7

Boxplot indicates the percentage of decussating fibers of all subjects using each tractography method. On each box, the central line indicates the median, the plus symbol indicates the mean, and the bottom and top edges of the box indicate the 25th and 75th percentiles, respectively. The percentage of decussating fibers was statistically significantly different between the different tractography methods (ANOVA, p < .0001). The posthoc paired t‐tests (with FDR correction) with significant results are indicated by asterisks. **: p < .01; ****: p < .0001

FIGURE 8

Scatter plots of correlation between T1w‐based volume and tractography‐based volume. In each plot, the y‐axis shows the tractography‐based volume (mm³) and the x‐axis shows the T1w‐based volume (mm³). Each row represents the correlation results of one tractography method under different threshold values. The correlation coefficient r and the p‐value are reported for each plot. Plots showing significant correlations are outlined in bold. MAE (mean absolute error) between the tractography‐based and the T1w‐based volumes across all subjects is also reported

FIGURE 9

Visual comparison of the RGVP reconstructed using the four tractography methods. The RGVPs (yellow bundles) obtained from one HCP subject are displayed, overlaid on the T1w image. Each row shows the RGVP and its subdivisions using one of the tracking strategies. The first column shows the overall RGVP fiber pathway, and the following columns show the four subdivisions

FIGURE 10

Violin plot indicates interexpert validation results. The wDice score was statistically significantly different between the different tractography methods (ANOVA, p = .06)

FIGURE 11

Violin plot indicates the ranking score of all subjects using each tractography method. On each violin box, the central circle indicates the median, the plus symbol indicates the mean, and the bottom and top of the gray central vertical line indicate the 25th and 75th percentiles, respectively. The ranking score was statistically significantly different between the different tractography methods using the Friedman test (p < .0001). Posthoc paired Wilcoxon signed‐rank tests (with FDR correction) with significant results are indicated by asterisks. *: p < .05; **: p < .01; ****: p < .0001

FIGURE 12

Normalized overlap score (NOS) of conjunction images generated by different tractography methods. The y‐axis shows the log ratio (the ratio that is summed in Equation (2)), while the x‐axis shows different threshold values of conjunction images. The NOS is the area under the curve