Transfer learning for predicting conversion from mild cognitive impairment to dementia of Alzheimer's type based on a three-dimensional convolutional neural network.

Dementia of Alzheimer's type (DAT) is associated with devastating and irreversible cognitive decline. Predicting which patients with mild cognitive impairment (MCI) will progress to DAT is an ongoing challenge in the field. We developed a deep learning model to predict conversion from MCI to DAT. Structural magnetic resonance imaging scans were used as input to a 3-dimensional convolutional neural network. The 3-dimensional convolutional neural network was trained using transfer learning; in the source task, normal control and DAT scans were used to pretrain the model. This pretrained model was then retrained on the target task of classifying which MCI patients converted to DAT. Our model resulted in 82.4% classification accuracy at the target task, outperforming current models in the field. Next, we visualized brain regions that significantly contribute to the prediction of MCI conversion using an occlusion map approach. Contributory regions included the pons, amygdala, and hippocampus. Finally, we showed that the model's prediction value is significantly correlated with rates of change in clinical assessment scores, indicating that the model is able to predict an individual patient's future cognitive decline. This information, in conjunction with the identified anatomical features, will aid in building a personalized therapeutic strategy for individuals with MCI.

Integrated cortical structural marker for Alzheimer's disease.

In this article, we propose an approach to integrate cortical morphology measures for improving the discrimination of individuals with and without very mild Alzheimer's disease (AD). FreeSurfer was applied to scans collected from 83 participants with very mild AD and 124 cognitively normal individuals. We generated cortex thickness, white matter convexity (aka "sulcal depth"), and white matter surface metric distortion measures on a normalized surface atlas in this first study to integrate high resolution gray matter thickness and white matter surface geometric measures in identifying very mild AD. Principal component analysis was applied to each individual structural measure to generate eigenvectors. Discrimination power based on individual and combined measures are compared, based on stepwise logistic regression and 10-fold cross-validation. Global AD likelihood index and surface-based likelihood maps were also generated. Our results show complementary patterns on the cortical surface between thickness, which reflects gray matter atrophy, convexity, which reflects white matter sulcal depth changes and metric distortion, which reflects white matter surface area changes. The classifier integrating all 3 types of surface measures significantly improved classification performance compared with classification based on single measures. The principal component analysis-based approach provides a framework for achieving high discrimination power by integrating high-dimensional data, and this method could be very powerful in future studies for early diagnosis of diseases that are known to be associated with abnormal gyral and sulcal patterns.

Midlife memory improvement predicts preservation of hippocampal volume in old age.

This study examines whether midlife change in episodic memory predicts hippocampal volume in old age. From the Seattle Longitudinal Study we retrospectively identified 84 healthy, cognitively normal individuals, age 52 to 87, whose episodic memory had reliably declined (n = 33), improved (n = 28) or remained stable (n = 23) over a 14-year period in midlife (age 43-63). Midlife memory improvement was associated with 13% larger hippocampal volume (p < 0.01) in old age (age 66-87), compared with old age individuals whose midlife episodic memory had either declined or remained stable during midlife. Midlife memory change did not predict total hippocampal volume for those currently in late middle age (age 52-65). The pattern of findings was not modified by gender, apolipoprotein ε4 status, education or current memory performance. Change in midlife memory scores over 14 years, but not any single assessment, predicted hippocampal volumes in old age, emphasizing the importance of longitudinal data in examining brain-cognition relationships. These findings suggest that improvement in memory in midlife is associated with sparing of hippocampal volume in later life.

Hippocampal surface mapping of genetic risk factors in AD via sparse learning models.

Genetic mapping of hippocampal shape, an under-explored area, has strong potential as a neurodegeneration biomarker for AD and MCI. This study investigates the genetic effects of top candidate single nucleotide polymorphisms (SNPs) on hippocampal shape features as quantitative traits (QTs) in a large cohort. FS+LDDMM was used to segment hippocampal surfaces from MRI scans and shape features were extracted after surface registration. Elastic net (EN) and sparse canonical correlation analysis (SCCA) were proposed to examine SNP-QT associations, and compared with multiple regression (MR). Although similar in power, EN yielded substantially fewer predictors than MR. Detailed surface mapping of global and localized genetic effects were identified by MR and EN to reveal multi-SNP-single-QT relationships, and by SCCA to discover multi-SNP-multi-QT associations. Shape analysis identified stronger SNP-QT correlations than volume analysis. Sparse multivariate models have greater power to reveal complex SNP-QT relationships. Genetic analysis of quantitative shape features has considerable potential for enhancing mechanistic understanding of complex disorders like AD.

Fully-automated, multi-stage hippocampus mapping in very mild Alzheimer disease.

Landmark-based high-dimensional diffeomorphic maps of the hippocampus (although accurate) is highly-dependent on rater's anatomic knowledge of the hippocampus in the magnetic resonance images. It is therefore vulnerable to rater drift and errors if substantial amount of effort is not spent on quality assurance, training, and re-training. A fully-automated, FreeSurfer-initialized large-deformation diffeomorphic metric mapping procedure of small brain substructures, including the hippocampus, has been previously developed and validated in small samples. In this report, we demonstrate that this fully-automated pipeline can be used in place of the landmark-based procedure in a large-sample clinical study to produce similar statistical outcomes. Some direct comparisons of the two procedures are also presented.

Increasing the power of functional maps of the medial temporal lobe by using large deformation diffeomorphic metric mapping.

The functional magnetic resonance imagery responses of declarative memory tasks in the medial temporal lobe (MTL) are examined by using large deformation diffeomorphic metric mapping (LDDMM) to remove anatomical variations across subjects. LDDMM is used to map the structures of the MTL in multiple subjects into extrinsic atlas coordinates; these same diffeomorphic mappings are used to transfer the corresponding functional data activation to the same extrinsic coordinates. The statistical power in the averaged LDDMM mapped signals is significantly increased over conventional Talairach-Tournoux averaging. Activation patterns are highly localized within the MTL. Whereas the present demonstration has been aimed at enhancing alignment within the MTL, this technique is general and can be applied throughout the brain.

Semi-automated basal ganglia segmentation using large deformation diffeomorphic metric mapping.

This paper investigates the techniques required to produce accurate and reliable segmentations via grayscale image matching. Finding a large deformation, dense, non-rigid transformation from a template image to a target image allows us to map a template segmentation to the target image space, and therefore compute the target image segmentation and labeling. We outline a semi-automated procedure involving landmark and image intensity-based matching via the large deformation diffeomorphic mapping metric (LDDMM) algorithm. Our method is applied specifically to the segmentation of the caudate nucleus in pre- and post-symptomatic Huntington's Disease (HD) patients. Our accuracy is compared against gold-standard manual segmentations and various automated segmentation tools through the use of several error metrics.