Performing real-time interactive fiber tracking

Abstract

Fiber tracking is a technique that, based on a diffusion tensor magnetic resonance imaging dataset, locates the fiber bundles in the human brain. Because it is a computationally expensive process, the interactivity of current fiber tracking tools is limited. We propose a new approach, which we termed real-time interactive fiber tracking, which aims at providing a rich and intuitive environment for the neuroradiologist. In this approach, fiber tracking is executed automatically every time the user acts upon the application. Particularly, when the volume of interest from which fiber trajectories are calculated is moved on the screen, fiber tracking is executed, even while it is being moved. We present our fiber tracking tool, which implements the real-time fiber tracking concept by using the video card's graphics processing units to execute the fiber tracking algorithm. Results show that real-time interactive fiber tracking is feasible on computers equipped with common, low-cost video cards.

Fig. 1

The real-time interactive fiber tracking tool. Results shown here were obtained from dataset 3. a VOI placed at the brain stem. b VOI placed in the corpus callosum.

Fig. 1

The real-time interactive fiber tracking tool. Results shown here were obtained from dataset 3. a VOI placed at the brain stem. b VOI placed in the corpus callosum.

Fig. 2

Combination of results from two VOIs, one at the corpus callosum and another at the brain stem. The active VOI has its edges highlighted.

Fig. 3

Mean number of trajectory points against number of seed points for all three datasets. The number of seed trajectory points grows linearly with the number of seed points. Here, filled diamond, dataset 1; inverted filled triangle, dataset 2; filled square, dataset 3.

Fig. 4

Scatterplots showing the number of trajectory points and the time taken to process them. Here, filled diamond, dataset 1; inverted filled triangle, dataset 2; filled square, dataset 3.

Fig. 5

FPS rate against number of seeds for both setups. Red lines indicate GPU and green lines CPU. a Setup 1. b Setup 2.

Fig. 6

Results obtained from dataset 3 with the highest seed density supported by the GPU (a) and the CPU (b) while still being able to sustain an interactive FPS rate. a seeds. b seeds.