Download presentation
Presentation is loading. Please wait.
Published byJeremy Glenn Modified over 8 years ago
1
Baseline and longitudinal patterns of brain atrophy in MCI patients, and their use in prediction of Short- term conversion to AD: Results from ADNI Xuejiao Chen 2012.12.7
2
Introduction Materials and methods Results Discussion and conclusion Outline
3
Author: Chandan Misra, Yong Fan, Christos Davatzikos Published in NeuroImage Introduction
4
Goal: Utilize high-dimensional pattern classification of baseline scans to determine predictors of short-term conversion from MCI to AD. Measure the spatial distribution of brain atrophy, as well as its longitudinal change, in MCI converters (MCI-C) and in MCI non-converters (MCI-NC) in the ADNI cohort, and to evaluate differences between these two groups. Introduction
5
Hypothesis Advanced pattern analysis and classification techniques applied to baseline and longitudinal images of the regional distribution of brain tissues would allow us to predict future conversion from MCI to AD. Introduction
6
Introduction Materials and methods Results Discussion and conclusion Outline
7
ADNI 800 adults, ages 55 to 90 200 CN older individuals followed for 3 years 400 MCI followed for 3 years 200 early AD followed for 2 years Materials and methods
9
Image analysis Pre-processing: Alignment to the AC-PC plane Skull-stripping Tissue segmentation into GM, WM, and CSF High-dimensional image warping to a standardized coordinate system, a brain atlas was aligned with the MNI coordinate space Formation of RAVENS maps using tissue-preserving image warping. Materials and methods
10
RAVENS maps quantify the regional distribution of GM, WM, and CSF, since one REVENS map is formed for each tissue type. RAVENS values in the template’s (stereotaxic) space are directly proportional to the volume of the respective structures in the original brain scan. Materials and methods
11
In order to minimize longitudinal “jitter noise” Aligned all scans of each individual to his/her baseline scan Materials and methods
12
Statistical analysis and pattern classification Group comparison performed via voxel-based statistical analysis of respective REVENS maps normalized by intracranial volume, smoothed using 8mm FWHM smoothing kernel. Group comparisons involved voxel-by-voxel t-test applied by SPM to the RAVENS maps and to voxel-wise regression maps obtained from longitudinal RAVENS measurements. Materials and methods
13
Statistical analysis and pattern classification Group comparisons of the rates of change in the RAVENS maps were calculated by first applying voxel- wise linear regression to all available RAVENS maps of each participant, and subsequently applying SPM’s t-test. Materials and methods
14
Statistical analysis and pattern classification Classifier: A classifier was constructed from the CN and AD groups, and then applied to the MCI subjects. A more specific classifier that optimally differentiates between MCI-C and MCI-NC was constructed and tested using leave-one-out cross-validation. Materials and methods
15
Introduction Materials and methods Results Discussion and conclusion Outline
16
Voxel-based analysis of baseline RAVENS maps GM: anterior hippocampus, amygdala, temporal lobe GM, insular contex, posterior cingulate, orbitofrontal cortex WM: periventricular frontal region, right hippocampus CSF: temporal horns of the lateral ventricles Results
19
Voxel-based analysis of regression maps of rate of RAVENS change No significant differences in the rages of change of GM A relatively faster increase of periventricular abnormal WM Higher rates of CSF increase in MCI-C Results
21
Pattern classification between MCI-C and MCI-NC (Classifier 2) Maximum classification rate: 81.5%, AUC=0.77 Results
23
Introduction Materials and methods Results Discussion and conclusion Outline
24
Significant differences at baseline were measured between MCI-C and MCI-NC. MCI-C had reduced GM volumes in a number of brain regions and parahippocampal WM. Larger size of the temporal horns of the ventricles. MCI-C had already reached levels of widespread and significant brain atrophy at baseline. Discussions and conclusion
25
Used individual patient classification using pattern recognition methods (Classifier 1). Scores of AD-like patterns of brain atrophy were determined for each individual. Almost all MCI-C effectively had AD-like brains at baseline. Discussions and conclusion
26
High-dimensional patterns classification (Classifier 2) indicated that a relatively reasonable classification accuracy can be obtained. A number of MCI-NC have AD-like structural profiles, which indicates that these individuals might become converters soon. Discussions and conclusion
27
Higher level of periventricular abnormal tissue, which appears gray in T1 images and is known to indicate small-vessel disease. Measuring vascular pathology is bound to be very important in predicting which individuals will convert to AD. Discussions and conclusion
28
Only significant group differences in the longitudinal rate of change were found in measures of periventricular abnormal WM and the temporal horn’s CSF volumes. Practically obtaining robust measurements of rate of change from a limited number of imaging measurements is problematic variations in scanner performance and tissue contrast noise in the image analysis measurements Discussions and conclusion
29
Though the ADNI data had been corrected for scanner distortions, the baseline measurements are far better markers of patterns of atrophy distinguishing converters from non-converters. Baseline atrophy is the cumulative effect of possibly many years of progression of AD pathology. Discussions and conclusion
30
The use of high-dimensional pattern classification methods also helped amplify the predictive value of baseline measurements. Rate of change is nonetheless a significant biomarker in clinical studies evaluating treatment effects. Discussions and conclusion
31
Investigated the use of a high-dimensional pattern classification approach as a means to obtain a sensitive and specific biomarker of AD-like spatial patterns of brain atrophy, and of conversion from MCI to AD. The results of this short-follow-up study are encouraging and indicate that subtle and spatially complex patterns of brain atrophy can be detected and quantified with relatively high accuracy. Discussions and conclusion
Similar presentations
© 2024 SlidePlayer.com Inc.
All rights reserved.