A statistical region selection and randomized volumetric features selection framework for early detection of Alzheimer's disease

Mishra, Shiwangi; Beheshti, Iman; Khanna, Pritee

doi:10.1002/ima.22290

Cited by 13 publications

(4 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…

High-to-low dimensionality transformations have been carried out via a number of approaches in the past. In some instances, dimensionality reduction or machine learning algorithms were applied directly to the raw voxel data [13][14][15][16][17] . Other approaches first use tools (e.g.

…”

mentioning

confidence: 99%

Predicting cognitive decline in a low-dimensional representation of brain morphology

Lamontagne-Caron,

Desrosiers,

Potvin

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Identifying early signs of neurodegeneration due to Alzheimer’s disease (AD) is a necessary first step towards preventing cognitive decline. Individual cortical thickness measures, available after processing anatomical magnetic resonance imaging (MRI), are sensitive markers of neurodegeneration. However, normal aging cortical decline and high inter-individual variability complicate the comparison and statistical determination of the impact of AD-related neurodegeneration on trajectories. In this paper, we computed trajectories in a 2D representation of a 62-dimensional manifold of individual cortical thickness measures. To compute this representation, we used a novel, nonlinear dimension reduction algorithm called Uniform Manifold Approximation and Projection (UMAP). We trained two embeddings, one on cortical thickness measurements of 6237 cognitively healthy participants aged 18–100 years old and the other on 233 mild cognitively impaired (MCI) and AD participants from the longitudinal database, the Alzheimer’s Disease Neuroimaging Initiative database (ADNI). Each participant had multiple visits ($$n \ge 2$$ n ≥ 2 ), one year apart. The first embedding’s principal axis was shown to be positively associated ($$r = 0.65$$ r = 0.65 ) with participants’ age. Data from ADNI is projected into these 2D spaces. After clustering the data, average trajectories between clusters were shown to be significantly different between MCI and AD subjects. Moreover, some clusters and trajectories between clusters were more prone to host AD subjects. This study was able to differentiate AD and MCI subjects based on their trajectory in a 2D space with an AUC of 0.80 with 10-fold cross-validation.

show abstract

“…

…”

mentioning

confidence: 99%

Predicting cognitive decline in a low-dimensional representation of brain morphology

Lamontagne-Caron,

Desrosiers,

Potvin

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Note that only age-related effects across field strengths were tested in this study. However, whether similar effects can extend to other comparisons such as sexual dimorphism [ 10 , 26 ] or disease/control [ 27 , 28 ], further studies are a paramount direction for future work.…”

Section: Discussionmentioning

confidence: 99%

Assessing Age-Related Gray Matter Differences in Young Adults with Voxel-Based Morphometry: The Effect of Field Strengths

Chen

et al. 2021

Brain Sciences

View full text Add to dashboard Cite

Knowing the patterns of brain differences with age in the young population could lead to a better understanding of the causes of certain psychiatric disorders; however, relevant information is insufficient. Here, a pattern of regional gray matter (GM) that changed with age in a young cohort aged 20–30 years was provided. Extending from previous age studies, all participants were imaged at both 1.5 T and 3 T to address the question of how far the field strength influences results. Fifty-nine young participants aged 20–30 years were scanned at both 1.5 T and 3 T. Voxel-based morphometry (VBM) was used to estimate the GM volume. Some brain regions showed a significant field strength-dependent difference in GM volume. VBM uncovered a significantly age-related increase in the GM volume in the left visual-associated area at 3 T, which was not detected at 1.5 T. In addition, voxels at 1.5 T that revealed a significant age-related reduction in the GM volume were found in the right cerebellum. In conclusion, age-related differences in human brain morphology could even be detected in a young cohort aged 20–30 years; however, the results varied across field strengths. Thus, field strength should be considered an important factor when comparing age-specific brain differences across studies.

show abstract

“…23.22282135 doi: medRxiv preprint High-to-low dimensionality transformations have been carried out via a number of approaches in the past. In some instances, dimensionality reduction or machine learning algorithms were applied directly to the raw voxel data [13][14][15][16] . Other approaches first use tools (e.g.…”

Section: (Which Was Not Certified By Peer Review) Preprintmentioning

confidence: 99%

Predicting cognitive decline in a low-dimensional representation of brain morphology

Lamontagne-Caron

Desrosiers²,

Potvin³

et al. 2022

Preprint

View full text Add to dashboard Cite

Identifying early signs of neurodegeneration due to Alzheimer's disease (AD) is a necessary first step towards preventing cognitive decline. Individual cortical thickness measures, available after processing anatomical magnetic resonance imaging (MRI), are sensitive markers of neurodegeneration. However, normal aging cortical decline and high inter-individual variability complicate the comparison and statistical determination of the impact of AD-related neurodegeneration on trajectories. In this paper, we computed trajectories of thickness changes in a 2D representation of a 62-dimensional manifold of individual cortical thickness measures. To compute this representation, we used a novel, nonlinear dimension reduction algorithm called Uniform Manifold Approximation and Projection (UMAP). We first trained a UMAP embedding on cortical thickness measurements of 6,237 cognitively healthy participants (3,556 women) aged 18 to 100 years old. Once transformed and rotated, its principal axis was shown to be positively associated (r= 0.65) with participants' age. We then projected in this transformed UMAP space, data from longitudinal MRIs of 537 mild cognitively impaired (MCI) subjects and 340 AD subjects from the Alzheimer's Disease Neuroimaging Initiative database. Each participant had multiple visits (n≥ 2), one year apart. Once in the transformed UMAP space, the data was clustered using ak-means variant. Average trajectories between clusters were shown to be significantly different between MCI and AD subjects. Moreover, we showed that some clusters and trajectories between clusters were more prone to host AD subjects. This study was able to differentiate AD and MCI subjects based on their cluster trajectory in a 2D space with a AUC of 0.72 over 2,000 iterations.

show abstract

A statistical region selection and randomized volumetric features selection framework for early detection of Alzheimer's disease

Cited by 13 publications

References 68 publications

Predicting cognitive decline in a low-dimensional representation of brain morphology

Predicting cognitive decline in a low-dimensional representation of brain morphology

Assessing Age-Related Gray Matter Differences in Young Adults with Voxel-Based Morphometry: The Effect of Field Strengths

Predicting cognitive decline in a low-dimensional representation of brain morphology

Contact Info

Product

Resources

About