RESUMO
Late-life depression (LLD) is a highly prevalent mood disorder occurring in older adults and is frequently accompanied by cognitive impairment (CI). Studies have shown that LLD may increase the risk of Alzheimer's disease (AD). However, the heterogeneity of presentation of geriatric depression suggests that multiple biological mechanisms may underlie it. Current biological research on LLD progression incorporates machine learning that combines neuroimaging data with clinical observations. There are few studies on incident cognitive diagnostic outcomes in LLD based on structural MRI (sMRI). In this paper, we describe the development of a hybrid representation learning (HRL) framework for predicting cognitive diagnosis over 5 years based on T1-weighted sMRI data. Specifically, we first extract prediction-oriented MRI features via a deep neural network, and then integrate them with handcrafted MRI features via a Transformer encoder for cognitive diagnosis prediction. Two tasks are investigated in this work, including (1) identifying cognitively normal subjects with LLD and never-depressed older healthy subjects, and (2) identifying LLD subjects who developed CI (or even AD) and those who stayed cognitively normal over five years. We validate the proposed HRL on 294 subjects with T1-weighted MRIs from two clinically harmonized studies. Experimental results suggest that the HRL outperforms several classical machine learning and state-of-the-art deep learning methods in LLD identification and prediction tasks.
Assuntos
Doença de Alzheimer , Disfunção Cognitiva , Humanos , Idoso , Depressão/diagnóstico por imagem , Disfunção Cognitiva/diagnóstico por imagem , Imageamento por Ressonância Magnética/métodos , Doença de Alzheimer/diagnóstico por imagem , CogniçãoRESUMO
Age-related macular degeneration (AMD) has recently been linked to cognitive impairment. We hypothesized that AMD modifies the brain aging trajectory, and we conducted a longitudinal diffusion MRI study on 40 participants (20 with AMD and 20 controls) to reveal the location, extent, and dynamics of AMD-related brain changes. Voxel-based analyses at the first visit identified reduced volume in AMD participants in the cuneate gyrus, associated with vision, and the temporal and bilateral cingulate gyrus, linked to higher cognition and memory. The second visit occurred 2 years after the first and revealed that AMD participants had reduced cingulate and superior frontal gyrus volumes, as well as lower fractional anisotropy (FA) for the bilateral occipital lobe, including the visual and the superior frontal cortex. We detected faster rates of volume and FA reduction in AMD participants in the left temporal cortex. We identified inter-lingual and lingual-cerebellar connections as important differentiators in AMD participants. Bundle analyses revealed that the lingual gyrus had a lower streamline length in the AMD participants at the first visit, indicating a connection between retinal and brain health. FA differences in select inter-lingual and lingual cerebellar bundles at the second visit showed downstream effects of vision loss. Our analyses revealed widespread changes in AMD participants, beyond brain networks directly involved in vision processing.
RESUMO
Brain structural MRI has been widely used for assessing future progression of cognitive impairment (CI) based on learning-based methods. Previous studies generally suffer from the limited number of labeled training data, while there exists a huge amount of MRIs in large-scale public databases. Even without task-specific label information, brain anatomical structures provided by these MRIs can be used to boost learning performance intuitively. Unfortunately, existing research seldom takes advantage of such brain anatomy prior. To this end, this paper proposes a brain anatomy-guided representation (BAR) learning framework for assessing the clinical progression of cognitive impairment with T1-weighted MRIs. The BAR consists of a pretext model and a downstream model, with a shared brain anatomy-guided encoder for MRI feature extraction. The pretext model also contains a decoder for brain tissue segmentation, while the downstream model relies on a predictor for classification. We first train the pretext model through a brain tissue segmentation task on 9,544 auxiliary T1-weighted MRIs, yielding a generalizable encoder. The downstream model with the learned encoder is further fine-tuned on target MRIs for prediction tasks. We validate the proposed BAR on two CI-related studies with a total of 391 subjects with T1-weighted MRIs. Experimental results suggest that the BAR outperforms several state-of-the-art (SOTA) methods. The source code and pre-trained models are available at https://github.com/goodaycoder/BAR.