Dataset Information

Convolutional neural network optimizes the application of diffusion kurtosis imaging in Parkinson's disease.

ABSTRACT:

Objectives

The literature regarding the use of diffusion-tensor imaging-derived metrics in the evaluation of Parkinson's disease (PD) is controversial. This study attempted to assess the feasibility of a deep-learning-based method for detecting alterations in diffusion kurtosis measurements associated with PD.

Methods

A total of 68 patients with PD and 77 healthy controls were scanned using scanner-A (3 T Skyra) (DATASET-1). Meanwhile, an additional five healthy volunteers were scanned with both scanner-A and an additional scanner-B (3 T Prisma) (DATASET-2). Diffusion kurtosis imaging (DKI) of DATASET-2 had an extra b shell compared to DATASET-1. In addition, a 3D-convolutional neural network (CNN) was trained from DATASET-2 to harmonize the quality of scalar measures of scanner-A to a similar level as scanner-B. Whole-brain unpaired t test and Tract-Based Spatial Statistics (TBSS) were performed to validate the differences between the PD and control groups using the model-fitting method and CNN-based method, respectively. We further clarified the correlation between clinical assessments and DKI results.

Results

An increase in mean diffusivity (MD) was found in the left substantia nigra (SN) in the PD group. In the right SN, fractional anisotropy (FA) and mean kurtosis (MK) values were negatively correlated with Hoehn and Yahr (H&Y) scales. In the putamen (Put), FA values were positively correlated with the H&Y scales. It is worth noting that these findings were only observed with the deep learning method. There was neither a group difference nor a correlation with clinical assessments in the SN or striatum exceeding the significance level using the conventional model-fitting method.

Conclusions

The CNN-based method improves the robustness of DKI and can help to explore PD-associated imaging features.

SUBMITTER: Sun J

PROVIDER: S-EPMC8479023 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ObjectiveTo investigate the utility of quantitative susceptibility mapping (QSM) and diffusion kurtosis imaging (DKI) as complementary tools in characterizing pathological changes in the deep grey nuclei in early Parkinson's disease (PD) and their clinical correlates to aid in diagnosis of PD.MethodPatients with a diagnosis of PD made within a year and age-matched healthy controls were recruited. All participants underwent clinical evaluation using the Unified Parkinson's Disease Rating Scale (MDS-UPDRS III) and Hoehn & Yahr stage (H&Y), and brain 3 T MRI including QSM and DKI. Regions-of-interest (ROIs) in the caudate nucleus, putamen, globus pallidus, and medial and lateral substantia nigra (SN) were manually drawn to compare the mean susceptibility (representing iron deposition) and DKI indices (representing restricted water diffusion) between PD patients and healthy controls and in correlation with MDS-UPDRS III and H&Y, focusing on susceptibility value, mean diffusivity (MD) and mean kurtosis (MK).ResultsThere were forty-seven PD patients (aged 68.7 years, 51% male, disease duration 0.78 years) and 16 healthy controls (aged 67.4 years, 63% male). Susceptibility value was increased in PD in all ROIs except the caudate, and was significantly different after multiple comparison correction in the putamen (PD: 64.75 ppb, HC: 44.61 ppb, p = 0.004). MD was significantly higher in PD in the lateral SN, putamen and caudate, the regions with the lowest susceptibility value. In PD patients, we found significant association between the MDS-UPDRS III score and susceptibility value in the putamen after correcting for age and sex (β = 0.21, p = 0.003). A composite DKI-QSM diagnostic marker based on these findings successfully differentiated the groups (p < 0.0001) and had "good" classification performance (AUC = 0.88).ConclusionsQSM and DKI are complementary tools allowing a better understanding of the complex contribution of iron deposition and microstructural changes in the pathophysiology of PD.

Project description:Prior postmortem studies have shown gray matter (GM) microstructural abnormalities in schizophrenia. However, few studies to date have examined GM microstructural integrity in schizophrenia in vivo. Here, we employed diffusion kurtosis imaging (DKI) to test for differences in GM microstructure in eighteen schizophrenia (SZ) patients versus nineteen healthy controls (HC). GM microstructure was characterized in each participant using DKI-derived metrics of mean kurtosis (MK) and mean diffusivity (MD). Individual T1-weighted images were used to create subject-specific cortically-labelled regions of interest (ROIs) of the four cortical lobes and sixty-eight cortical GM regions delineated by the Desikan-Killiany atlas, and to derive the associated cortical thickness and area measures. The derived ROIs were also registered to the diffusion space of each subject and used to generate region-specific mean MK and MD values. We additionally administered the Wisconsin Card Sorting Test (WCST), Stroop test, and Trail Making Test part B (Trails-B) to test the relationship between GM metrics and executive function in SZ. We found significantly increased MK and MD in SZ compared to HC participants in the temporal lobe, sub-lobar temporal cortical regions (fusiform, inferior temporal, middle temporal and temporal pole), and posterior cingulate cortex after correcting for multiple comparisons. Correlational analyses revealed significant associations of MK and MD with executive function scores derived from the WCST, Stroop, and Trails-B tests, along with an inverse relationship between MK and MD and cortical thickness and area. A hierarchical multiple linear regression analysis showed that up to 85% of the inter-subject variability in cognitive function in schizophrenia measured by the WCST could be explained by MK in combination with either GM thickness or area. MK and MD appear to be sensitive to GM microstructural pathology in schizophrenia and may provide useful biomarkers of abnormal cortical microstructure in this disorder.