scholarly journals Patch individual filter layers in CNNs to harness the spatial homogeneity of neuroimaging data

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Fabian Eitel ◽  
Jan Philipp Albrecht ◽  
Martin Weygandt ◽  
Friedemann Paul ◽  
Kerstin Ritter
Keyword(s):  
Multiple Sclerosis ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Area Under The Curve ◽  
Heterogeneous Data ◽  
Uniform Structure ◽  
Linear Transformations ◽  
Hospital Data ◽  
Spatial Homogeneity ◽  
Neuroimaging Data

AbstractConvolutional neural networks (CNNs)—as a type of deep learning—have been specifically designed for highly heterogeneous data, such as natural images. Neuroimaging data, however, is comparably homogeneous due to (1) the uniform structure of the brain and (2) additional efforts to spatially normalize the data to a standard template using linear and non-linear transformations. To harness spatial homogeneity of neuroimaging data, we suggest here a new CNN architecture that combines the idea of hierarchical abstraction in CNNs with a prior on the spatial homogeneity of neuroimaging data. Whereas early layers are trained globally using standard convolutional layers, we introduce patch individual filters (PIF) for higher, more abstract layers. By learning filters in individual latent space patches without sharing weights, PIF layers can learn abstract features faster and specific to regions. We thoroughly evaluated PIF layers for three different tasks and data sets, namely sex classification on UK Biobank data, Alzheimer’s disease detection on ADNI data and multiple sclerosis detection on private hospital data, and compared it with two baseline models, a standard CNN and a patch-based CNN. We obtained two main results: First, CNNs using PIF layers converge consistently faster, measured in run time in seconds and number of iterations than both baseline models. Second, both the standard CNN and the PIF model outperformed the patch-based CNN in terms of balanced accuracy and receiver operating characteristic area under the curve (ROC AUC) with a maximal balanced accuracy (ROC AUC) of 94.21% (99.10%) for the sex classification task (PIF model), and 81.24% and 80.48% (88.89% and 87.35%) respectively for the Alzheimer’s disease and multiple sclerosis detection tasks (standard CNN model). In conclusion, we demonstrated that CNNs using PIF layers result in faster convergence while obtaining the same predictive performance as a standard CNN. To the best of our knowledge, this is the first study that introduces a prior in form of an inductive bias to harness spatial homogeneity of neuroimaging data.

scholarly journals Graph neural network based heterogeneous propagation scheme for classifying alzheimer’s disease

2021 ◽  
Author(s):  
Jiyoung Byun ◽  
Yong Jeong
Keyword(s):  
Neural Network ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Deep Learning ◽  
Heterogeneous Data ◽  
Disease Classification ◽  
Imaging Features ◽  
Neuroimaging Data ◽  
Individual Features ◽  
The Individual

ABSTRACTDeep learning frameworks for disease classification using neuroimaging and non-imaging information require the capability of capturing individual features as well as associative information among subjects. Graphs represent the interactions among nodes, which contain the individual features, through the edges in order to incorporate the inter-relatedness among heterogeneous data. Previous graph-based approaches for disease classification have focused on the similarities among subjects by establishing customized functions or solely based on imaging features. The purpose of this paper is to propose a novel graph-based deep learning architecture for classifying Alzheimer’s disease (AD) by combining the resting-state functional magnetic resonance imaging and demographic measures without defining any study-specific function. We used the neuroimaging data from the ADNI and OASIS databases to test the robustness of our proposed model. We combined imaging-based and non-imaging information of individuals by categorizing them into distinctive nodes to construct a subject–demographic bipartite graph. The approximate personalized propagation of neural predictions, a recently developed graph neural network model, was used to classify the AD continuum from cognitively unimpaired individuals. The results showed that our model successfully captures the heterogeneous relations among subjects and improves the quality of classification when compared with other classical and deep learning models, thus outperforming the other models.

scholarly journals IC-P-144: BLAZER: A VERSATILE AND EFFICIENT WORKFLOW FOR ANALYZING PET/MR NEUROIMAGING DATA IN ALZHEIMER'S DISEASE

2019 ◽  
Vol 15 ◽  
pp. P117-P118
Author(s):  
Fabio Raman ◽  
Sameera Grandhi ◽  
Charles F. Murchison ◽  
Richard E. Kennedy ◽  
Susan M. Landau ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Neuroimaging Data

scholarly journals Plasma contact factors as novel biomarkers for diagnosing Alzheimer’s disease

2021 ◽  
Vol 9 (1) ◽  
Author(s):  
Jung Eun Park ◽  
Do Sung Lim ◽  
Yeong Hee Cho ◽  
Kyu Yeong Choi ◽  
Jang Jae Lee ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Early Stage ◽  
Clinical Stage ◽  
Area Under The Curve ◽  
Contact System ◽  
Plasma Diagnostic ◽  
Vascular Abnormalities ◽  
Prodromal Ad ◽  
Novel Biomarkers

Abstract Background Alzheimer’s disease (AD) is the most common cause of dementia and most of AD patients suffer from vascular abnormalities and neuroinflammation. There is an urgent need to develop novel blood biomarkers capable of diagnosing Alzheimer’s disease (AD) at very early stage. This study was performed to find out new accurate plasma diagnostic biomarkers for AD by investigating a direct relationship between plasma contact system and AD. Methods A total 101 of human CSF and plasma samples from normal and AD patients were analyzed. The contact factor activities in plasma were measured with the corresponding specific peptide substrates. Results The activities of contact factors (FXIIa, FXIa, plasma kallikrein) and FXa clearly increased and statistically correlated as AD progresses. We present here, for the first time, the FXIIa cut-off scores to as: > 26.3 U/ml for prodromal AD [area under the curve (AUC) = 0.783, p < 0.001] and > 27.2 U/ml for AD dementia (AUC = 0.906, p < 0.001). We also describe the cut-off scores from the ratios of CSF Aβ1–42 versus the contact factors. Of these, the representative ratio cut-off scores of Aβ1–42/FXIIa were to be: < 33.8 for prodromal AD (AUC = 0.965, p < 0.001) and < 27.44 for AD dementia (AUC = 1.0, p < 0.001). Conclusion The activation of plasma contact system is closely associated with clinical stage of AD, and FXIIa activity as well as the cut-off scores of CSF Aβ1–42/FXIIa can be used as novel accurate diagnostic AD biomarkers.

scholarly journals Deep Learning with Neuroimaging and Genomics in Alzheimer’s Disease

2021 ◽  
Vol 22 (15) ◽  
pp. 7911
Author(s):  
Eugene Lin ◽  
Chieh-Hsin Lin ◽  
Hsien-Yuan Lane
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Deep Learning ◽  
Future Research ◽  
Learning Approaches ◽  
Learning Models ◽  
Learning Techniques ◽  
Neuroimaging Data ◽  
Similarities And Differences ◽  
Normal Controls

A growing body of evidence currently proposes that deep learning approaches can serve as an essential cornerstone for the diagnosis and prediction of Alzheimer’s disease (AD). In light of the latest advancements in neuroimaging and genomics, numerous deep learning models are being exploited to distinguish AD from normal controls and/or to distinguish AD from mild cognitive impairment in recent research studies. In this review, we focus on the latest developments for AD prediction using deep learning techniques in cooperation with the principles of neuroimaging and genomics. First, we narrate various investigations that make use of deep learning algorithms to establish AD prediction using genomics or neuroimaging data. Particularly, we delineate relevant integrative neuroimaging genomics investigations that leverage deep learning methods to forecast AD on the basis of incorporating both neuroimaging and genomics data. Moreover, we outline the limitations as regards to the recent AD investigations of deep learning with neuroimaging and genomics. Finally, we depict a discussion of challenges and directions for future research. The main novelty of this work is that we summarize the major points of these investigations and scrutinize the similarities and differences among these investigations.

scholarly journals Classifying Non-Dementia and Alzheimer’s Disease/Vascular Dementia Patients Using Kinematic, Time-Based, and Visuospatial Parameters: The Digital Clock Drawing Test

2021 ◽  
Vol 82 (1) ◽  
pp. 47-57 ◽  
Author(s):  
Anis Davoudi ◽  
Catherine Dion ◽  
Shawna Amini ◽  
Patrick J. Tighe ◽  
Catherine C. Price ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Vascular Dementia ◽  
Area Under The Curve ◽  
Clock Drawing Test ◽  
Digital Clock ◽  
Clock Drawing ◽  
Drawing Test ◽  
Dementia Patients ◽  
Optimal Area

Background: Advantages of digital clock drawing metrics for dementia subtype classification needs examination. Objective: To assess how well kinematic, time-based, and visuospatial features extracted from the digital Clock Drawing Test (dCDT) can classify a combined group of Alzheimer’s disease/Vascular Dementia patients versus healthy controls (HC), and classify dementia patients with Alzheimer’s disease (AD) versus vascular dementia (VaD). Methods: Healthy, community-dwelling control participants (n = 175), patients diagnosed clinically with Alzheimer’s disease (n = 29), and vascular dementia (n = 27) completed the dCDT to command and copy clock drawing conditions. Thirty-seven dCDT command and 37 copy dCDT features were extracted and used with Random Forest classification models. Results: When HC participants were compared to participants with dementia, optimal area under the curve was achieved using models that combined both command and copy dCDT features (AUC = 91.52%). Similarly, when AD versus VaD participants were compared, optimal area under the curve was, achieved with models that combined both command and copy features (AUC = 76.94%). Subsequent follow-up analyses of a corpus of 10 variables of interest determined using a Gini Index found that groups could be dissociated based on kinematic, time-based, and visuospatial features. Conclusion: The dCDT is able to operationally define graphomotor output that cannot be measured using traditional paper and pencil test administration in older health controls and participants with dementia. These data suggest that kinematic, time-based, and visuospatial behavior obtained using the dCDT may provide additional neurocognitive biomarkers that may be able to identify and tract dementia syndromes.

Plasma cortisol and norepinephrine in Alzheimer’s disease: opposite relations with recall performance and stage of progression

2007 ◽  
Vol 19 (4) ◽  
pp. 231-237 ◽  
Author(s):  
Karel J. Bemelmans ◽  
Annemarie Noort ◽  
Roel de Rijk ◽  
Huub A. M. Middelkoop ◽  
Godfried M. J. van Kempen ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Hippocampal Neurons ◽  
Plasma Cortisol ◽  
Recall Performance ◽  
Area Under The Curve ◽  
Plasma Norepinephrine ◽  
Clinical Dementia Rating ◽  
Memory Decline ◽  
Word Lists

Objective:Alzheimer’s disease (AD) is characterized by effortful retrieval memory impairments, loss of hippocampal neurons and elevated plasma cortisol (CORT) concentrations. The latter could induce further memory decline. AD is also characterized by increased central and peripheral noradrenergic activity. Since noradrenergic function is involved in memory formation, this upregulated function could counteract memory decline. The aim of the present study was to test these hypotheses using plasma norepinephrine (NE) as a noradrenergic parameter, and recall of the prerecency part of neutral valence word lists as a measure of effortful retrieval.Methods:Area under the curve (AUC) of morning, midday and afternoon plasma CORT and plasma NE concentrations was related to two measures of recall performance, ie summated recall scores of the prerecency and recency parts of three word lists, and to the stage of the Clinical Dementia Rating (CDR).Results:Partial correlation between each hormone AUC value and prerecency recall performance, controlling for the effect of the other hormone, showed opposite relations between recall and either plasma CORT or NE. Similar stronger correlations were found with the CDR score.Conclusions:Plasma CORT and NE are oppositely related with effortful retrieval and the stage of progression in AD.

Coexistence of Multiple Sclerosis and Alzheimer's disease: A review

2019 ◽  
Vol 27 ◽  
pp. 232-238 ◽  
Author(s):  
Pauline Luczynski ◽  
Cornelia Laule ◽  
Ging-Yuek Robin Hsiung ◽  
G.R. Wayne Moore ◽  
Helen Tremlett
Keyword(s):  
Multiple Sclerosis ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease

scholarly journals 12-year prediction of mild cognitive impairment aided by Alzheimer’s brain signatures at mean age 56

2021 ◽  
Author(s):  
McKenna E Williams ◽  
Jeremy A Elman ◽  
Linda K McEvoy ◽  
Ole A Andreassen ◽  
Anders M Dale ◽  
...  
Keyword(s):  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Cognitive Impairment ◽  
Mild Cognitive Impairment ◽  
Mean Diffusivity ◽  
Area Under The Curve ◽  
Polygenic Risk Score ◽  
Age Difference ◽  
Cognitively Normal ◽  
Brain Age

Abstract Neuroimaging signatures based on composite scores of cortical thickness and hippocampal volume predict progression from mild cognitive impairment to Alzheimer’s disease. However, little is known about the ability of these signatures among cognitively normal adults to predict progression to mild cognitive impairment. Toward that end, a signature sensitive to microstructural changes that may predate macrostructural atrophy should be useful. We hypothesized that: 1) a validated MRI-derived Alzheimer’s disease signature based on cortical thickness and hippocampal volume in cognitively normal middle-aged adults would predict progression to mild cognitive impairment; and 2) a novel gray matter mean diffusivity signature would be a better predictor than the thickness/volume signature. This cohort study was part of the Vietnam Era Twin Study of Aging. Concurrent analyses compared cognitively normal and mild cognitive impairment groups at each of three study waves (ns = 246–367). Predictive analyses included 169 cognitively normal men at baseline (age = 56.1, range = 51–60). Our previously published thickness/volume signature derived from independent data, a novel mean diffusivity signature using the same regions and weights as the thickness/volume signature, age, and an Alzheimer’s disease polygenic risk score were used to predict incident mild cognitive impairment an average of 12 years after baseline (follow-up age = 67.2, range = 61–71). Additional analyses adjusted for predicted brain age difference scores (chronological age minus predicted brain age) to determine if signatures were Alzheimer-related and not simply aging-related. In concurrent analyses, individuals with mild cognitive impairment had higher (worse) mean diffusivity signature scores than cognitively normal participants, but thickness/volume signature scores did not differ between groups. In predictive analyses, age and polygenic risk score yielded an area under the curve of 0.74 (sensitivity = 80.00%; specificity = 65.10%). Prediction was significantly improved with addition of the mean diffusivity signature (area under the curve = 0.83; sensitivity = 85.00%; specificity = 77.85%; P=0.007), but not with addition of the thickness/volume signature. A model including both signatures did not improve prediction over a model with only the mean diffusivity signature. Results held up after adjusting for predicted brain age difference scores. The novel mean diffusivity signature was limited by being yoked to the thickness/volume signature weightings. An independently-derived mean diffusivity signature may thus provide even stronger prediction. The young age of the sample at baseline is particularly notable. Given that the brain signatures were examined when participants were only in their 50 s, our results suggest a promising step toward improving very early identification of Alzheimer’s disease risk and the potential value of mean diffusivity and/or multimodal brain signatures.

Sign in / Sign up

Export Citation Format

Share Document