Subregional Biomarkers in FDG PET for Alzheimer’s Diagnosis and Staging: An Interpretable and Explainable model DOI Creative Commons
Ramin Rasi, Albert Güveniş

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 27, 2024

Abstract Objective To investigate the radiomics features of hippocampus and amygdala subregions in FDG-PET images that can best differentiate Mild Cognitive Impairment (MCI), Alzheimer’s Disease (AD), healthy patients. Methods Baseline data from 555 participants ADNI dataset were analyzed, comprising 189 cognitively normal (CN) individuals, 201 with MCI, 165 AD. The segmented based on DKT-Atlas, additional subdivisions guided by probabilistic atlases Freesurfer. Then radiomic (n=120) extracted 38 hippocampal 18 nuclei using PyRadiomics. Various feature selection techniques, including ANOVA, PCA, Chi-square, LASSO, applied alongside nine machine learning classifiers. Results Multi-Layer Perceptron (MLP) model combined LASSO demonstrated excellent classification performance: ROC AUC 0.957 for CN vs. AD, 0.867 MCI 0.782 MCI. Key regions, accessory basal nucleus, presubiculum head, CA4 identified as critical biomarkers. Features GLRLM (Long Run Emphasis) Small Dependence Emphasis (GLDM) showed strong diagnostic potential, reflecting subtle metabolic microstructural changes often preceding anatomical alterations. Conclusion Specific their four found to have a significant role early diagnosis its staging, severity assessment capturing shifts patterns. Furthermore, these offer potential insights into disease’s underlying mechanisms interpretability.

Language: Английский

Estimating individual trajectories of structural and cognitive decline in mild cognitive impairment for early prediction of progression to dementia of the Alzheimer’s type DOI Creative Commons
Shreya K. Rajagopal, Adriene M. Beltz, Benjamin M. Hampstead

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: June 5, 2024

Abstract Only a third of individuals with mild cognitive impairment (MCI) progress to dementia the Alzheimer’s type (DAT). Identifying biomarkers that distinguish MCI who will DAT (MCI-Converters) from those not (MCI-Non-Converters) remains key challenge in field. In our study, we evaluate whether individual rates loss volumes Hippocampus and entorhinal cortex (EC) age stage can predict progression DAT. Using data 758 patients Disease Neuroimaging Database, employ Linear Mixed Effects (LME) models estimate trajectories regional brain volume over 12 years on average. Our approach involves three analyses: (1) mapping age-related MCI-Converters Non-Converters, (2) using logistic regression based hippocampal EC loss, (3) examining relationship between estimates these volumetric changes decline across different functions—episodic memory, visuospatial processing, executive function. We find Hippocampal is significantly more rapid than but no such difference volumes. also rate significant predictor conversion DAT, while other additional regions not. Finally, both EC, regions, correlate strongly decline. Across all analyses, variation initial MCI. This study highlights importance personalized approaches predicting AD progression, offering insights for future research intervention strategies.

Language: Английский

Citations

4
Amygdala Nuclei Atrophy in Cognitive Impairment and Dementia: Insights from High-Resolution Magnetic Resonance Imaging DOI Creative Commons

Evija Peiseniece,

Nauris Zdanovskis, Kristı̄ne Šneidere

et al.

Medicina, Journal Year: 2025, Volume and Issue: 61(1), P. 130 - 130

Published: Jan. 15, 2025

Background and Objectives: Cognitive impairment affects memory, reasoning, problem-solving, with early detection being critical for effective management. The amygdala, a key structure in emotional processing may play pivotal role detecting cognitive decline. This study examines differences amygdala nuclei volumes patients varying levels of performance to evaluate its potential as biomarker. Material methods: cross-sectional 35 participants was conducted classified into three groups: the normal (≥26), moderate (15–25), low (≤14) groups based on Montreal Assessment (MoCA) scores. High-resolution magnetic resonance imaging at 3.0 T scanner used assess volumes. Results: Significant atrophy observed multiple across groups, more pronounced changes low-performance group. right hemisphere nuclei, including lateral basal showed significant differences, indicating their sensitivity Conclusions: highlights biomarker impairment. Additional research larger sample sizes longitudinal designs is needed confirm these findings determine diagnostic value.

Language: Английский

Citations

0
Changes in the Parietal Lobe Subregion Volume at Various Stages of Alzheimer’s Disease and the Role in Cognitively Normal and Mild Cognitive Impairment Conversion DOI Creative Commons
Fang Lu,

Qing Ma,

Cailing Shi

et al.

Journal of Integrative Neuroscience, Journal Year: 2025, Volume and Issue: 24(1)

Published: Jan. 21, 2025

Background: Volume alterations in the parietal subregion have received less attention Alzheimer’s disease (AD), and their role predicting conversion of mild cognitive impairment (MCI) to AD cognitively normal (CN) MCI remains unclear. In this study, we aimed assess volumetric variation at different stages determine subregions CN conversion. Methods: We included 662 participants from Disease Neuroimaging Initiative (ADNI) database, including 228 CN, 221 early (EMCI), 112 late (LMCI), 101 participants. measured volume based on Human Brainnetome Atlas (BNA-246) using voxel-based morphometry among individuals various progressive stable MCI. then calculated area under curve (AUC) receiver operating characteristic (ROC) test ability discriminate between groups. The Cox proportional hazard model was constructed which specific subregions, alone or combination, could be used predict progression Finally, examined relationship scores diagnostic Results: left inferior lobule (IPL)_6_5 (rostroventral 39) showed best patients with those (AUC = 0.688). consisting IPL_6_4 (caudal 40) bilateral IPL_6_5 combination for IPL_6_1 predictive power AD. Certain correlated scales. Conclusion: Subregions angular gyrus are essential onset subsequent development AD, detection these regions may useful identifying tendency develop its treatment.

Language: Английский

Citations

0
Leveraging CapsNet for enhanced classification of 3D MRI images for Alzheimer’s diagnosis DOI
Jahangir Rasheed,

Moiz Uddin Shaikh,

Mohsin Raza Jafri

et al.

Biomedical Signal Processing and Control, Journal Year: 2025, Volume and Issue: 103, P. 107384 - 107384

Published: Jan. 5, 2025

Language: Английский

Citations

0
Plasma tryptophan levels are linked to hippocampal integrity and cognitive function in individuals with mild cognitive impairment DOI
Ali Azargoonjahromi

Brain Imaging and Behavior, Journal Year: 2025, Volume and Issue: unknown

Published: March 4, 2025

Language: Английский

Citations

0
Hippocampal-subfield macro- and microstructural changes in cerebral small vessel disease with mild cognitive impairment DOI
Binglan Li,

Bang Zeng,

Peng Zeng

et al.

Journal of Affective Disorders, Journal Year: 2025, Volume and Issue: unknown

Published: May 1, 2025

Language: Английский

Citations

0
Progression of hippocampal subfield atrophy and asymmetry in Alzheimer's disease DOI
Jingjing Xu,

Sijia Tan,

Jiaqi Wen

et al.

European Journal of Neuroscience, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 22, 2024

Alzheimer's disease (AD) affects the hippocampus during its progression, but specific observable changes of hippocampal subfields progression remain poorly understood. In this study, we employed an event-based model (EBM) to determine sequence occurrence subfield atrophy in mild cognitive impairment (MCI) and AD cohorts. Subjects (207) were included: 86 MCI, 53 AD, 68 healthy controls from Disease Neuroimaging Initiative (ADNI). Participants underwent structural magnetic resonance imaging (MRI) scans analyse subfields. We assigned each patient a EBM stage, based on number their abnormal A combination 2-year follow-up MRI applied demonstrate longitudinal consistency utility model's staging system. The estimated that earliest occurs fissure, then spreading other subregions both MCI AD. identified marked divergence between sequences left right atrophy, so inter-hemispheric asymmetry pattern was further analysed. index (AI) increases beginning molecular granule cell layers dentate gyrus (GC-ML-DG), cornus ammonis (CA) 4, layer (ML). Longitudinal analysis confirms efficacy model. addition, stages significantly correlated with patients' memory scores (p < .05). Collectively, used data-driven method provide new insight into progression. present could aid understanding stages, as well tracking decline.

Language: Английский

Citations

2
Medial Amygdalar Tau Is Associated With Mood Symptoms in Preclinical Alzheimer’s Disease DOI Creative Commons

Joyce S Li,

Samantha M Tun,

Bronte Ficek

et al.

Biological Psychiatry Cognitive Neuroscience and Neuroimaging, Journal Year: 2024, Volume and Issue: unknown

Published: July 1, 2024

Language: Английский

Citations

1
Beyond group classification: Probabilistic differential diagnosis of frontotemporal dementia and Alzheimer’s disease with MRI and CSF biomarkers DOI Creative Commons
Agnès Pérez‐Millan, Bertrand Thirion, Neus Falgàs

et al.

Neurobiology of Aging, Journal Year: 2024, Volume and Issue: 144, P. 1 - 11

Published: Aug. 30, 2024

niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français étrangers, laboratoires publics privés.

Citations

1
Medial amygdalar tau is associated with anxiety symptoms in preclinical Alzheimer's disease DOI Creative Commons

Joyce S Li,

Samantha M Tun,

Bronte Ficek

et al.

bioRxiv (Cold Spring Harbor Laboratory), Journal Year: 2024, Volume and Issue: unknown

Published: June 3, 2024

ABSTRACT BACKGROUND While the amygdala receives early tau deposition in Alzheimer’s disease (AD) and is involved social emotional processing, relationship between amygdalar neuropsychiatric symptoms AD unknown. We sought to determine whether focal binding abnormal connectivity were detectable a preclinical cohort identify relationships these self-reported mood symptoms. METHODS examined n=598 individuals (n=347 amyloid-positive (58% female), n=251 amyloid-negative (62% female); subset into PET fMRI cohorts) from A4 Study. In our cohort, we used segmentations examine representative nuclei three functional divisions of amygdala. analyzed between-group differences division-specific AD. conducted seed-based analyses each division cohort. Finally, exploratory post-hoc correlation neuroimaging biomarkers interest anxiety depression scores. RESULTS Amyloid-positive demonstrated increased medial lateral ( F (4, 442)=14.61, p =0.00045; 442)=5.83, =0.024, respectively). Across divisions, had relatively regional other temporal regions, insula, orbitofrontal cortex. There was an interaction by amyloid group anxiety. Medial retrosplenial negatively correlated with (r s =-0.103, =0.015). CONCLUSIONS Our findings suggest that may result meaningful changes which predispose patients

Language: Английский

Citations

0