Search for: All records

High‐dimensional multinomial regression models are very useful in practice but have received less research attention than logistic regression models, especially from the perspective of statistical inference. In this work, we analyze the estimation and prediction error of the contrast‐based ‐penalized multinomial regression model and extend the debiasing method to the multinomial case, providing a valid confidence interval for each coefficient and value of the individual hypothesis test. We also examine cases of model misspecification and non‐identically distributed data to demonstrate the robustness of our method when some assumptions are violated. We apply the debiasing method to identify important predictors in the progression into dementia of different subtypes. Results from extensive simulations show the superiority of the debiasing method compared to other inference methods. 

Abstract Aging-related periventricular white matter hyperintensities (pvWMHs) are a common observation in medical images of the aging brain. The underlying tissue damage is part of the complex pathophysiology associated with age-related microstructural changes and cognitive decline. PvWMH formation is linked to blood–brain barrier dysfunction from cerebral small vessel disease as well as the accumulation of cerebrospinal fluid in periventricular tissue due to progressive denudation of the ventricular wall. In need of a unifying theory for pvWMH etiology, image-based finite-element modeling is used to demonstrate that ventricular expansion from age-related cerebral atrophy and hemodynamic loading leads to maximum mechanical loading of the ventricular wall in the same locations that show pvWMHs. Ventricular inflation, induced via pressurization of the ventricular wall, creates significant ventricular wall stretch and stress on the ependymal cells lining the wall, that are linked to cerebrospinal fluid leaking from the lateral ventricles into periventricular white matter tissue. Eight anatomically accurate 3D brain models of cognitively healthy subjects with a wide range of ventricular shapes are created. For all models, our simulations show that mechanomarkers of mechanical wall loading are consistently highest in pvWMHs locations ( p < 0.05). Maximum principal strain, the ependymal cell thinning ratio, and wall curvature are on average 14%, 8%, and 24% higher in pvWMH regions compared to the remaining ventricular wall, respectively. Computational modeling provides a powerful framework to systematically study pvWMH formation and growth with the goal to develop pharmacological interventions in the future. 

Abstract Early diagnosis of Alzheimer’s disease plays a pivotal role in patient care and clinical trials. In this study, we have developed a new approach based on 3D deep convolutional neural networks to accurately differentiate mild Alzheimer’s disease dementia from mild cognitive impairment and cognitively normal individuals using structural MRIs. For comparison, we have built a reference model based on the volumes and thickness of previously reported brain regions that are known to be implicated in disease progression. We validate both models on an internal held-out cohort from The Alzheimer's Disease Neuroimaging Initiative (ADNI) and on an external independent cohort from The National Alzheimer's Coordinating Center (NACC). The deep-learning model is accurate, achieved an area-under-the-curve (AUC) of 85.12 when distinguishing between cognitive normal subjects and subjects with either MCI or mild Alzheimer’s dementia. In the more challenging task of detecting MCI, it achieves an AUC of 62.45. It is also significantly faster than the volume/thickness model in which the volumes and thickness need to be extracted beforehand. The model can also be used to forecast progression: subjects with mild cognitive impairment misclassified as having mild Alzheimer’s disease dementia by the model were faster to progress to dementia over time. An analysis of the features learned by the proposed model shows that it relies on a wide range of regions associated with Alzheimer's disease. These findings suggest that deep neural networks can automatically learn to identify imaging biomarkers that are predictive of Alzheimer's disease, and leverage them to achieve accurate early detection of the disease.