Geodesic path differences in neural networks in the Alzheimer's disease connectome project

Abstract

AbstractBackgroundNeural networks derived from diffusion‐weighted MRI (DW‐MRI) may shed light on disease progression and pathology propagation in Alzheimer’s disease in vivo. In this work analysis of the path properties of such networks are presented. Geodesic or shortest paths are fundamental in understanding key network phenomenon such as the propagation rates of information, infection or pathology. For example, the ubiquitous small‐worldness property of natural occurring biological and social networks is based on having short paths between any pair of entities in the network.MethodConnectome protocol based DW‐MRI data acquired from n=68 participants (Table 1) were analyzed. Neural networks were extracted from the data using state‐of‐the‐art image processing and tractography algorithms available in MRtrix3 (overview panel in Figure‐1). The average geodesic path lengths between frontal, temporal, parietal, occipital, subcortical regions were computed using Dijkstra algorithm. The regions were identified based on the IIT‐Desikan gray matter atlas. The paths can be used to reason about the average efficiency of communication of electrical signals or propagation of pathology between brain lobes. Statistical analysis was performed to test the geodesic path length differences between the CU, MCI and the AD groups controlling for age and sex. The path lengths were normalized so that they were at unity for the AD group, and differences were considered significant at p<=0.05.ResultStatistical effects of consensus diagnosis on the relative geodesic path length (RGPL) differences between lobes are shown in Figure‐2. 80% of the connections showed statistically significant higher path lengths in AD compared to CU and 60% when compared to MCI. The distributions of the mean geodesic path lengths are shown in Figure‐3. For all the different pairs of lobes, the mean length was higher for the AD compared to the CU and MCI groups.ConclusionThe path lengths between all of the major lobes are higher for the AD group compared to both the CU and MCI groups. These findings suggest that network efficiency is reduced in AD and may explain cognitive dysfunction observed in the Alzheimer’s clinical syndrome. Future work entails incorporating better constraints on tractography using structural T1‐weighted images and separating disease groups by AD‐biomarker status.