K-confidence: Assessing uncertainty in tractography using K optimal paths

Tractography algorithms are susceptible to errors due to poor image quality. As a result, having some measure of confidence in the anatomical accuracy of a tractography result is a desirable goal. We propose that such a measure of confidence can be obtained from the spatial distribution of likely paths between two fixed endpoints. We present for the first time a k optimal paths tractography algorithm for determining the k most likely fiber tract trajectories between two fixed regions. We further examine the spatial spread of the k optimal fiber paths to obtain a measure of confidence that two regions are connected by an axonal fiber. We show on both synthetic and real data that the uniformity of the spread of the k optimal paths shows good correspondence with anatomically known connectivity.