Addressing multi-site functional MRI heterogeneity through dual-expert collaborative learning for brain disease identification.

Several studies employ multi-site rs-fMRI data for major depressive disorder (MDD) identification, with a specific site as the to-be-analyzed target domain and other site(s) as the source domain. But they usually suffer from significant inter-site heterogeneity caused by the use of different scanners and/or scanning protocols and fail to build generalizable models that can well adapt to multiple target domains. In this article, we propose a dual-expert fMRI harmonization (DFH) framework for automated MDD diagnosis. Our DFH is designed to simultaneously exploit data from a single labeled source domain/site and two unlabeled target domains for mitigating data distribution differences across domains. Specifically, the DFH consists of a domain-generic student model and two domain-specific teacher/expert models that are jointly trained to perform knowledge distillation through a deep collaborative learning module. A student model with strong generalizability is finally derived, which can be well adapted to unseen target domains and analysis of other brain diseases. To the best of our knowledge, this is among the first attempts to investigate multi-target fMRI harmonization for MDD diagnosis. Comprehensive experiments on 836 subjects with rs-fMRI data from 3 different sites show the superiority of our method. The discriminative brain functional connectivities identified by our method could be regarded as potential biomarkers for fMRI-related MDD diagnosis.

The Interaction of Personality and Social Support on Prospective Suicidal Ideation in Men and Women With Late-Life Depression.

OBJECTIVE: Evidence suggests a cross-sectional association between personality traits and suicidal ideation in LLD. Yet, it is unclear how personality may influence suicidal ideation over time in LLD, or whether such an association would be moderated by psychosocial and biological individual differences. The present study had three aims: 1) to examine whether personality traits increase suicidal ideation in LLD over time, 2) to understand whether this relationship is influenced by subjective social support, and 3) to determine whether the potential relationship between social support, personality, and suicidal ideation is different for men and women. DESIGN: Participants were enrolled in the Duke University Neurocognitive Outcomes of Depression in the Elderly (NCODE), a longitudinal investigation of the predictors of poor illness course in LLD. Patients were initially enrolled in the NCODE study between December 1994 and June 2000 and were followed for an average of six years. SETTING: NCODE operates in a naturalistic treatment milieu. PARTICIPANTS: One hundred twelve participants aged 60 and older with a current diagnosis of major depressive disorder. MEASUREMENTS: Annual assessments of depression, suicidal ideation, and social support (measured with the Duke Social Support Index). Participants also completed the NEO Personality Inventory-Revised (NEO-PI-R) providing measures of the five major personality dimensions (neuroticism, extraversion, openness, conscientiousness, and agreeableness). RESULTS: Univariate logistic generalized linear mixed modeling (GLMM) analyses revealed that higher levels of depression at baseline, less subjective social support, higher neuroticism, and lower extraversion were significantly associated with an increased likelihood of suicidal ideation over time. While the relationship between these dimensions and suicidal ideation were no longer significant in multivariate analyses, there was a significant moderating effect of social support on the association between suicidal ideation and certain neuroticism and extraversion personality facets. Decreased subjective social support was associated with an increased likelihood of suicidal ideation in LLD patients with high (but not low) impulsiveness and low (but not high) gregariousness and positive emotions. Across all models, social support was beneficial to women, but not men, in decreasing the likelihood of future suicidal ideation. CONCLUSION: Changes in social support may contribute to suicidal ideation in older depressed adults with certain personality traits. Irrespective of personality traits, changes in social support had a significant effect on the suicidal ideation of women but not men. These relationships were apparent even when controlling for depression severity, age, and history of suicide attempt.

Cognitive performance in antidepressant-free recurrent major depressive disorder.

BACKGROUND: Cognitive complaints are common in depression, and cognition may be an important treatment target as cognitive problems often remain during remission and may contribute to recurrence risk. Previous studies of cognitive performance in depression have mainly examined late-life depression, with a focus on older adults, or assessed performance in specific cognitive tasks rather than cognitive domains. METHODS: This study examined cognitive performance across multiple cognitive domains in antidepressant-free depressed adults with early onset recurrent depression compared to never-depressed controls. Domain scores were calculated for episodic memory, executive function, processing speed, and working memory, and the effect of depression diagnosis, depression severity, and depression duration on each domain score was examined, including interactions with age, sex, and education. RESULTS: Currently depressed adults (n = 91) exhibited poorer performance in the processing speed domain compared with never-depressed adults (n = 105). Additionally, there was an interactive effect of depression duration and age on processing speed and executive function domain performance, such that performance was worse with older age and longer duration of depression. There were no effects of depression severity on performance across the cognitive domains. CONCLUSIONS: These findings support that processing speed deficits appear in young adults with early onset depression that may not be related to current mood. Additionally, the effects of cumulative depressive episodes may interact with aging such that cognitive performance deficits worsen with recurrence over the lifespan.

Predictors of recurrence in remitted late-life depression.

BACKGROUND: Late-life depression (LLD) is associated with a fragile antidepressant response and high recurrence risk. This study examined what measures predict recurrence in remitted LLD. METHODS: Individuals of age 60 years or older with a Diagnostic and Statistical Manual - IV (DSM-IV) diagnosis of major depressive disorder were enrolled in the neurocognitive outcomes of depression in the elderly study. Participants received manualized antidepressant treatment and were followed longitudinally for an average of 5 years. Study analyses included participants who remitted. Measures included demographic and clinical measures, medical comorbidity, disability, life stress, social support, and neuropsychological testing. A subset underwent structural magnetic resonance imaging (MRI). RESULTS: Of 241 remitted elders, approximately over 4 years, 137 (56.8%) experienced recurrence and 104 (43.2%) maintained remission. In the final model, greater recurrence risk was associated with female sex (hazard ratio [HR] = 1.536; confidence interval [CI] = 1.027-2.297), younger age of onset (HR = 0.990; CI = 0.981-0.999), higher perceived stress (HR = 1.121; CI = 1.022-1.229), disability (HR = 1.060; CI = 1.005-1.119), and less support with activities (HR = 0.885; CI = 0.812-0.963). Recurrence risk was also associated with higher Montgomery-Asberg Depression Rating Scale (MADRS) scores prior to censoring (HR = 1.081; CI = 1.033-1.131) and baseline symptoms of suicidal thoughts by MADRS (HR = 1.175; CI = 1.002-1.377) and sadness by Center for Epidemiologic Studies-Depression (HR = 1.302; CI, 1.080-1.569). Sex, age of onset, and suicidal thoughts were no longer associated with recurrence in a model incorporating report of multiple prior episodes (HR = 2.107; CI = 1.252-3.548). Neither neuropsychological test performance nor MRI measures of aging pathology were associated with recurrence. CONCLUSIONS: Over half of the depressed elders who remitted experienced recurrence, mostly within 2 years. Multiple clinical and environmental measures predict recurrence risk. Work is needed to develop instruments that stratify risk.

Putamen Volume Differences Among Older Adults: Depression Status, Melancholia, and Age.

BACKGROUND: Individuals with major depressive disorder (MDD) may exhibit smaller striatal volumes reflecting deficits in the reward circuit. Deficits may change with age and be more pronounced among the melancholic subtype. Limited research has investigated striatal volume differences in older adults and by depression subtypes. METHOD: We used baseline data from the Neurocognitive Outcomes of Depression in the Elderly study. We examined volumetric differences in the putamen and caudate nucleus among older adults (60 years and older), comparing healthy control participants (n = 134) to depressed participants (n = 226), and comparing nonmelancholic depressed participants (n = 93) to melancholic depressed participants (n = 133). Group-by-age interactions were examined. RESULTS: There were no significant group differences for the caudate nucleus. For the left putamen, investigation of the significant group-by-age interaction revealed that volume size was greater for the healthy controls compared to the depressed participants but only at younger ages (60-65 years); group differences diminished with increasing age. Examining volume by depression subtype revealed that the melancholic depressed participants had a smaller left putamen compared to the nonmelancholic depressed participants. Anhedonia symptoms were related to both smaller left and right putamen. CONCLUSION: Structural abnormalities in reward regions may underlie the anhedonic phenotype. Volume loss associated with MDD may attenuate in older age.

Decreased between-hemisphere connectivity strength and network efficiency in geriatric depression.

White matter (WM) lesions have been recognized as a key etiological factor in geriatric depression. However, little is known about the topological pattern changes of WM in geriatric depression in the remitted state (RGD) and its relationship to depressive episodes. To address these questions, we acquired diffusion tensor images in 24 RGD and 24 healthy participants. Among them, 10 patients and 19 healthy controls completed a 1-year follow up. Between-hemisphere connectivity and graph theoretical methods were used to analyze the data. We found significantly reduced WM connectivity between the left and right hemisphere in the RGD group compared with the control group. Those with multiple depression episodes had greater reduction in between-hemisphere connectivity strength than those with fewer episodes. In addition, the RGD group had a reduced global clustering coefficient, global efficiency, and network strength, and an increased shortest path length compared with the controls. A lower clustering coefficient was correlated with poorer memory function. The reduction of nodal clustering coefficient, global efficiency, and network strength in several regions were associated with slower information processing speed. At 1-year follow up, the network properties in the RGD subjects were significantly changed suggesting instability of WM network properties of depressed patients. Together, our study provides direct evidence of reduced between-hemisphere WM connectivity with greater depressive episodes, and of alterations of network properties with cognitive dysfunction in geriatric depression. Hum Brain Mapp 38:53-67, 2017. © 2016 Wiley Periodicals, Inc.

Frontoparietal activation during visual conjunction search: Effects of bottom-up guidance and adult age.

We conducted functional magnetic resonance imaging (fMRI) with a visual search paradigm to test the hypothesis that aging is associated with increased frontoparietal involvement in both target detection and bottom-up attentional guidance (featural salience). Participants were 68 healthy adults, distributed continuously across 19 to 78 years of age. Frontoparietal regions of interest (ROIs) were defined from resting-state scans obtained prior to task-related fMRI. The search target was defined by a conjunction of color and orientation. Each display contained one item that was larger than the others (i.e., a size singleton) but was not informative regarding target identity. Analyses of search reaction time (RT) indicated that bottom-up attentional guidance from the size singleton (when coincident with the target) was relatively constant as a function of age. Frontoparietal fMRI activation related to target detection was constant as a function of age, as was the reduction in activation associated with salient targets. However, for individuals 35 years of age and older, engagement of the left frontal eye field (FEF) in bottom-up guidance was more prominent than for younger individuals. Further, the age-related differences in left FEF activation were a consequence of decreasing resting-state functional connectivity in visual sensory regions. These findings indicate that age-related compensatory effects may be expressed in the relation between activation and behavior, rather than in the magnitude of activation, and that relevant changes in the activation-RT relation may begin at a relatively early point in adulthood. Hum Brain Mapp 38:2128-2149, 2017. © 2017 Wiley Periodicals, Inc.

Longitudinal Cognitive Outcomes of Clinical Phenotypes of Late-Life Depression.

OBJECTIVE: Late-life depression is associated with cognitive deficits and increased risk for cognitive decline. The purpose of the study was to determine whether clinical characteristics could serve as phenotypes informative of subsequent cognitive decline. Age at depression onset and antidepressant remission at 3 months (acute response) and 12 months (chronic response) were examined. METHODS: In a longitudinal study of late-life depression in an academic center, 273 depressed and 164 never-depressed community-dwelling elders aged 60 years or older were followed on average for over 5 years. Participants completed annual neuropsychological testing. Neuropsychological measures were converted to z-scores derived from the baseline performance of all participants. Cognitive domain scores at each time were then created by averaging z-scores across tests, grouped into domains of episodic memory, attention-working memory, verbal fluency, and executive function. RESULTS: Depressed participants exhibited poorer performance at baseline and greater subsequent decline in all domains. Early-onset depressed individuals exhibited a greater decline in all domains than late-onset or nondepressed groups. For remission, remitters and nonremitters at both 3 and 12 month exhibited greater decline in episodic memory and attention-working memory than nondepressed subjects. Three-month remitters also exhibited a greater decline in verbal fluency and executive function, whereas 12-month nonremitters exhibited greater decline in executive function than other groups. CONCLUSION: Consistent with past studies, depressed elders exhibit greater cognitive decline than nondepressed subjects, particularly individuals with early depression onset, supporting the theory that repeated depressive episodes may contribute to decline. Clinical remission is not associated with less cognitive decline.

Appetite and Weight Loss Symptoms in Late-Life Depression Predict Dementia Outcomes.

OBJECTIVE: Identify depression symptoms during active late-life depression (LLD) that predict conversion to dementia. METHODS: The authors followed a cohort of 290 participants from the Neurocognitive Outcomes of Depression in the Elderly study. All participants were actively depressed and cognitively normal at enrollment. Depression symptom factors were derived from prior factor analysis: anhedonia and sadness, suicidality and guilt, appetite and weight loss, sleep disturbance, and anxiety and tension. Cox regression analysis modeled time to Alzheimer disease (AD) and non-AD dementia onset on depression symptom factors, along with age, education, sex, and race. Significant dementia predictors were tested for interaction with age at depression onset. RESULTS: Higher scores on the appetite and weight loss symptom factor were associated with an increased hazard of both AD and non-AD dementia. This factor was moderated by age at first depression onset, such that higher scores were associated with higher risk of non-AD dementia when depression first occurred earlier in life. Other depression symptom factors and overall depression severity were not related to risk of AD or non-AD dementia. CONCLUSION: Results suggest greater appetite/weight loss symptoms in active episodes of LLD are associated with increased likelihood of AD and non-AD dementia, but possibly via different pathways moderated by age at first depression onset. Results may help clinicians identify individuals with LLD at higher risk of developing AD and non-AD dementia and design interventions that reduce this risk.

Physical frailty in late-life depression is associated with deficits in speed-dependent executive functions.

OBJECTIVE: The aim of this study was to examine the association between physical frailty and neurocognitive performance in late-life depression (LLD). METHODS: Cross-sectional design using baseline data from a treatment study of late-life depression was used in this study. Individuals aged 60 years and older were diagnosed with major depressive disorder at time of assessment (N = 173). All participants received clinical assessment of depression and completed neuropsychological testing during a depressive episode. Physical frailty was assessed using an adaptation of the FRAIL scale. Neuropsychological domains were derived from a factor analysis that yielded three factors: (i) speeded executive and fluency, (ii) episodic memory, and (iii) working memory. Associations were examined with bivariate tests and multivariate models. RESULTS: Depressed individuals with a FRAIL score >1 had worse performance than nonfrail depressed across all three factors; however, speeded executive and fluency was the only factor that remained significant after controlling for depression symptom severity and demographic characteristics. CONCLUSIONS: Although physical frailty is associated with broad neurocognitive deficits in LLD, it is most robustly associated with deficits in speeded executive functions and verbal fluency. Causal inferences are limited by the cross-sectional design, and future research would benefit from a comparison group of nondepressed older adults with similar levels of frailty. Research is needed to understand the mechanisms underlying associations among depression symptoms, physical frailty, and executive dysfunction and how they are related to the cognitive and symptomatic course of LLD.

Appetite loss and neurocognitive deficits in late-life depression.

OBJECTIVES: This study aimed to examine the association of appetite loss symptoms to neurocognitive performance in late-life depression (LLD). METHODS: This study used cross-sectional data from individuals aged 60+ years with major depressive disorder (N = 322). Participants received clinical assessment of depression and neuropsychological testing. Factor analysis was used to characterize depression symptom factors, and composite scales were developed for episodic memory, psychomotor-executive functions, verbal fluency, and working memory span. RESULTS: Factor analysis produced a five-factor solution: (1) anhedonia/sadness; (2) suicidality/guilt; (3) appetite/weight loss; (4) sleep disturbance; and (5) anxiety/tension. In separate multivariate models for each neurocognitive domain and including all five depression factors, higher appetite-loss-related symptoms were associated with lower performance in episodic memory, psychomotor-executive functions, and verbal fluency; results were significant with covariates of age, education, race, sex, age of depression onset, and illness burden. No other depression factors were associated with neurocognitive performance in these models. In an additional set of models, the appetite factor mediated the association between global depression severity and neurocognitive performance. DISCUSSION: A factor of appetite and weight loss symptoms in LLD was uniquely associated with neurocognitive performance, in contrast to lack of association among other depression symptom factors. CONCLUSION: Cognitive deficits are a major adverse outcome of LLD, and prominent appetite loss during acute depression may be a marker for these deficits, independent of overall depression severity. Research is needed to understand the mechanisms that may explain this association, and how it is related to the cognitive and symptomatic course of LLD.

Cognitive functioning throughout the treatment history of clinical late-life depression.

OBJECTIVE: Previous investigations into the relationship between late-life depressive symptoms and cognitive functioning have resulted in mixed findings concerning whether or not depressive symptoms and cognitive functioning are related. The mixed reports may be due in part to differences in clinical and nonclinical samples and to inadequate consideration of the dynamic nature (i.e., fluctuating course) of depressive symptoms and cognitive functioning in older adults. The current study examined the chronic, acute, and longitudinal relationships between depressive symptoms and cognitive functioning in older adults in an ongoing treatment study of major depressive disorder (MDD). METHODS: The neurocognitive outcomes of depression in the elderly study operates in a naturalistic treatment milieu using a pharmacological treatment algorithm and regular psychiatric assessment. Four hundred and fifty-three older adults [mean age 70 years, standard deviation (SD) = 7.2] meeting criteria for MDD at study enrollment received annual neuropsychological testing and depressive symptom monitoring for an average of 8.5 years (SD = 4.5). RESULTS: Hierarchical linear modeling revealed that higher age, lower education, and higher average/chronic levels of depressive symptoms were related to lower cognitive functioning. Additionally, results revealed that when an individual's depressive symptoms are higher than is typical for a specific individual, general cognitive function was worse than average. There was no evidence of lagged/longitudinal relationships between depressive symptoms and cognitive functioning in older adults in treatment for MDD. CONCLUSIONS: Cognitive functioning and depressive symptoms are concurrently associated in older adults with MDD, highlighting the potential importance for stabilizing mood symptoms as a means to manage cognitive deficits in late-life depression.

Differential item functioning due to cognitive status does not impact depressive symptom measures in four heterogeneous samples of older adults.

OBJECTIVE: The objective of this study is to determine whether differential item functioning (DIF) due to cognitive status impacted three depressive symptoms measures commonly used with older adults. METHODS: Differential item functioning in depressive symptoms was assessed among participants (N = 3558) taking part in four longitudinal studies of cognitive aging, using the Geriatric Depression Scale, the Montgomery-Åsberg Depression Rating Scale, and the Center for Epidemiologic Studies Depression Scale. Participants were grouped by cognitive status using a general cognitive performance score derived from each study's neuropsychological battery and linked to a national average using a population-based survey representative of the US population. The Clinical Dementia Rating score was used as an alternate grouping variable in three of the studies. RESULTS: Although statistically significant DIF based on cognitive status was found for some depressive symptom items (e.g., items related to memory complaints, appetite loss, lack of energy, and mood), the effect of item bias on the total score for each scale was negligible. CONCLUSIONS: The depressive symptoms scales in these four studies measured depression in the same way, regardless of cognitive status. This may reduce concerns about using these depression measures in cognitive aging research, as relationships between depression and cognitive decline are unlikely to have been due to item bias, at least in the ways that were measured in the datasets we considered.

Demographic characteristics do not decrease the utility of depressive symptoms assessments: examining the practical impact of item bias in four heterogeneous samples of older adults.

OBJECTIVE: Previous studies have identified differential item function (DIF) in depressive symptoms measures, but the impact of DIF has been rarely reported. Given the critical importance of depressive symptoms assessment among older adults, we examined whether DIF due to demographic characteristics resulted in salient score changes in commonly used measures. METHODS: Four longitudinal studies of cognitive aging provided a sample size of 3754 older adults and included individuals both with and without a clinical diagnosis of major depression. Each study administered at least one of the following measures: the Center for Epidemiologic Studies Depression scale (20-item ordinal response or 10-item dichotomous response versions), the Geriatric Depression Scale, and the Montgomery-Åsberg Depression Rating Scale. Hybrid logistic regression-item response theory methods were used to examine the presence and impact of DIF due to age, sex, race/ethnicity, and years of education on the depressive symptoms items. RESULTS: Although statistically significant DIF due to demographic factors was present on several items, its cumulative impact on depressive symptoms scores was practically negligible. CONCLUSIONS: The findings support substantive meaningfulness of previously reported demographic differences in depressive symptoms among older adults, showing that these individual differences were unlikely to have resulted from item bias attributable to demographic characteristics we examined.

Disability but not social support predicts cognitive deterioration in late-life depression.

BACKGROUND: Depression in late life is a risk factor for cognitive decline. Depression is also associated with increased disability and social support deficits; these may precede conversion to dementia and inform risk. In this study, we examined if baseline or one-year change in disability and social support predicted later cognitive deterioration. METHODS: 299 cognitively intact depressed older adults were followed for an average of approximately seven years. Participants received antidepressant treatment according to a standardized algorithm. Neuropsychological testing and assessment of disability and social support were assessed annually. Cognitive diagnosis was reviewed annually at a consensus conference to determine if participants remained cognitively normal, or if they progressed to either dementia or cognitively impaired, no dementia (CIND). RESULTS: During study participation, 167 individuals remained cognitively normal (56%), 83 progressed to CIND (28%), and 49 progressed to dementia (16%). Greater baseline instrumental activities of daily living (IADL) deficits predicted subsequent conversion to a cognitive diagnosis (CIND or dementia). However, neither baseline measures nor one-year change in basic ADLs (BADLs) and social support predicted cognitive conversion. In post hoc analyses, two IADL measures (managing finances, preparing meals) significantly increased the odds of cognitive conversion. CONCLUSIONS: Greater IADL deficits predicted increased risk of cognitive conversion. Assessment of IADL deficits may provide clues about risk of later cognitive decline.

Age mediation of frontoparietal activation during visual feature search.

Activation of frontal and parietal brain regions is associated with attentional control during visual search. We used fMRI to characterize age-related differences in frontoparietal activation in a highly efficient feature search task, detection of a shape singleton. On half of the trials, a salient distractor (a color singleton) was present in the display. The hypothesis was that frontoparietal activation mediated the relation between age and attentional capture by the salient distractor. Participants were healthy, community-dwelling individuals, 21 younger adults (19-29 years of age) and 21 older adults (60-87 years of age). Top-down attention, in the form of target predictability, was associated with an improvement in search performance that was comparable for younger and older adults. The increase in search reaction time (RT) associated with the salient distractor (attentional capture), standardized to correct for generalized age-related slowing, was greater for older adults than for younger adults. On trials with a color singleton distractor, search RT increased as a function of increasing activation in frontal regions, for both age groups combined, suggesting increased task difficulty. Mediational analyses disconfirmed the hypothesized model, in which frontal activation mediated the age-related increase in attentional capture, but supported an alternative model in which age was a mediator of the relation between frontal activation and capture.

Amnestic mild cognitive impairment and incident dementia and Alzheimer's disease in geriatric depression.

BACKGROUND: Memory impairment in geriatric depression is understudied, but may identify individuals at risk for development of dementia and Alzheimer's disease (AD). Using a neuropsychologically based definition of amnestic mild cognitive impairment (aMCI) in patients with geriatric depression, we hypothesized that patients with aMCI, compared with those without it, would have increased incidence of both dementia and AD. METHODS: Participants were aged 60 years and older and consisted of depressed participants and non-depressed volunteer controls. The depressed cohort met criteria for unipolar major depression. All participants were free of dementia and other neurological illness at baseline. At study entry, participants were administered a standardized clinical interview, a battery of neurocognitive tests, and provided a blood sample for determination of apolipoprotein E genotype. A cognitive diagnosis was assigned by a panel of experts who convened annually and reviewed available clinical, neuropsychological and laboratory data to achieve a consensus cognitive diagnosis to determine a consensus diagnosis. Survival analysis examined the association between aMCI and later dementia (all-cause) and AD. RESULTS: Among 295 depressed individuals, 63 (21.36%) met criteria for aMCI. Among 161 non-depressed controls, four (2.48%) met aMCI criteria. Participants were followed for 6.28 years on average. Forty-three individuals developed dementia, including 40 (13.6%) depressed and three (1.9%) control participants. Both aMCI and age were associated with incident dementia and AD. CONCLUSIONS: The presence of aMCI is a poor prognostic sign among patients with geriatric depression. Clinicians should carefully screen elderly depressed adults for memory impairment.

Hybrid representation learning for cognitive diagnosis in late-life depression over 5 years with structural MRI.

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.

Accelerated Brain Atrophy, Microstructural Decline and Connectopathy in Age-Related Macular Degeneration.

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.

Diffusion tensor imaging of cerebral white matter integrity in cognitive aging.

In this article we review recent research on diffusion tensor imaging (DTI) of white matter (WM) integrity and the implications for age-related differences in cognition. Neurobiological mechanisms defined from DTI analyses suggest that a primary dimension of age-related decline in WM is a decline in the structural integrity of myelin, particularly in brain regions that myelinate later developmentally. Research integrating behavioral measures with DTI indicates that WM integrity supports the communication among cortical networks, particularly those involving executive function, perceptual speed, and memory (i.e., fluid cognition). In the absence of significant disease, age shares a substantial portion of the variance associated with the relation between WM integrity and fluid cognition. Current data are consistent with one model in which age-related decline in WM integrity contributes to a decreased efficiency of communication among networks for fluid cognitive abilities. Neurocognitive disorders for which older adults are at risk, such as depression, further modulate the relation between WM and cognition, in ways that are not as yet entirely clear. Developments in DTI technology are providing a new insight into both the neurobiological mechanisms of aging WM and the potential contribution of DTI to understanding functional measures of brain activity. This article is part of a Special Issue entitled: Imaging Brain Aging and Neurodegenerative disease.