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), Год журнала: 2024, Номер unknown

Опубликована: Дек. 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.

Язык: Английский

Interpretable MRI-Based Deep Learning for Alzheimer's Risk and Progression DOI Creative Commons
Bin Lu, Yanrong Chen, Ruixian Li

и другие.

medRxiv (Cold Spring Harbor Laboratory), Год журнала: 2025, Номер unknown

Опубликована: Май 7, 2025

Timely intervention for Alzheimer's disease (AD) requires early detection. The development of immunotherapies targeting amyloid-beta and tau underscores the need accessible, time-efficient biomarkers diagnosis. Here, we directly applied our previously developed MRI-based deep learning model AD to large Chinese SILCODE cohort (722 participants, 1,105 brain MRI scans). - initially trained on North American data demonstrated robust cross-ethnic generalization, without any retraining or fine-tuning, achieving an AUC 91.3% in classification with a sensitivity 95.2%. It successfully identified 86.7% individuals at risk progression more than 5 years advance. Individuals as high-risk exhibited significantly shorter median times. By integrating interpretable map approach, subtypes, including MCI subtype associated rapid cognitive decline. model's scores showed significant correlations measures plasma biomarkers, such proteins neurofilament light chain (NfL). These findings underscore exceptional generalizability clinical utility models, especially diverse populations, offering valuable tools therapeutic intervention. has been made open-source deployed free online website prediction, assist screening

Язык: Английский

Процитировано

0
Characterization of Portable Ultra‐Low Field MRI Scanners for Multi‐Center Structural Neuroimaging DOI Creative Commons
Emil Ljungberg, Francesco Padormo, Megan Poorman

и другие.

Human Brain Mapping, Год журнала: 2025, Номер 46(8)

Опубликована: Май 23, 2025

ABSTRACT The lower infrastructure requirements of portable ultra‐low field MRI (ULF‐MRI) systems have enabled their use in diverse settings such as intensive care units and remote medical facilities. UNITY Project is an international neuroimaging network harnessing this technology, deploying ULF‐MRI globally to expand access for studies into brain development. Given the wide range environments where may operate, there are external factors that might influence image quality. This work aims introduce quality control (QC) framework used by investigate how robust QC metrics compare between sites over time. We present a using commercially available phantom, scanned with 64 mT at 17 across 12 countries on four continents. Using automated, open‐source analysis tools, we quantify signal‐to‐noise, contrast, geometric distortions. Our results demonstrated varying operational environment, example, electromagnetic noise interference temperature. Larmor frequency was significantly correlated room temperature, contrast. Image distortions were less than 2.5 mm, high robustness Similar higher field, found changes pulse sequence parameters from software updates had impact metrics. study demonstrates can be deployed variety multi‐center produce results.

Язык: Английский

Процитировано

0
DNA methylation age from peripheral blood predicts progression to Alzheimer’s disease, white matter disease burden, and cortical atrophy DOI Creative Commons
Luke W. Bonham, Daniel W. Sirkis, Alina P.S. Pang

и другие.

Опубликована: Май 27, 2025

Abstract Cross-sectional studies suggest a limited relationship between accelerated epigenetic aging derived from clocks, and Alzheimer’s disease (AD) pathophysiology or risk. However, most prior analyses have not utilized longitudinal whole-brain neuroimaging biomarkers of AD. Herein, we employed modeling structural to test the hypothesis that would predict AD progression. Using survival analyses, found two second-generation DNAmPhenoAge DNAmGrimAge, predicted progression cognitively normal mild cognitive impairment worse outcomes. Epigenetic age was also strongly associated with cortical thinning in AD-relevant regions white matter burden. Thus, contrast earlier work suggesting applicability blood-based clocks AD, our novel analytic framework suggests broad utility may represent promising predictors risk pathophysiology.

Язык: Английский

Процитировано

0
Positron emission tomography harmonization in the Alzheimer's Disease Neuroimaging Initiative: A scalable and rigorous approach to multisite amyloid and tau quantification DOI Creative Commons

Susan Landau,

Theresa M. Harrison, Suzanne L. Baker

и другие.

Alzheimer s & Dementia, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 19, 2024

Abstract INTRODUCTION A key goal of the Alzheimer's Disease NeuroImaging Initiative (ADNI) positron emission tomography (PET) Core is to harmonize quantification β‐amyloid (Aβ) and tau PET image data across multiple scanners tracers. METHODS We developed an analysis pipeline (Berkeley Imaging Pipeline, B‐PIP) for ADNI Aβ images applied it from other multisite studies. Steps include pre‐processing, refacing, magnetic resonance imaging (MRI)/PET co‐registration, visual quality control (QC), tracer uptake, standardization standardized uptake value ratios (SUVrs) RESULTS Measurements 10,105 cross‐sectional longitudinal scans acquired in several studies between 2010 2024 can be processed, harmonized, directly merged tracers cohorts. DISCUSSION The B‐PIP a scalable harmonization approach used observational clinical trials that facilitates rigorous sharing. Highlights Quantitative results are generated using rigorous, processing This has been large, outcomes harmonizable shared with scientific community

Язык: Английский

Процитировано

2
Cerebrovascular markers of WMH and infarcts in ADNI: A historical perspective and future directions DOI Creative Commons
Pauline Maillard, Evan Fletcher, Owen Carmichael

и другие.

Alzheimer s & Dementia, Год журнала: 2024, Номер unknown

Опубликована: Ноя. 13, 2024

Abstract White matter hyperintensities (WMH) and infarcts found on magnetic resonance imaging (MR infarcts) are common biomarkers of cerebrovascular disease. In this review, we summarize the methods, publications, conclusions stemming from Alzheimer's Disease Neuroimaging Initiative (ADNI) related to these measures. We combine analysis WMH MR infarct data across three main ADNI cohorts with a review existing literature discussing new methodologies scientific findings derived data. Although inclusion criteria were designed minimize vascular risk factors disease, all consistent trends increasing volumes associated advancing age, female sex, cognitive impairment. ADNI, initially proposed as study investigate AD pathology, has also helped elucidate impact asymptomatic brain injury cognition within cohort relatively free Future work will emphasize additional biomarkers. Highlights (WMHs) age likely reflect among older individuals. lesser extent, (MR) infarcts, affect for transition WMHs present, even participants highly selected have disease (AD) primary pathology. burden in is greater individuals impairment been neurodegenerative markers cerebral amyloidosis. The negative additive effects appear select populations, future biomarker needs further explore relationship.

Язык: Английский

Процитировано

0
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), Год журнала: 2024, Номер unknown

Опубликована: Дек. 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.

Язык: Английский

Процитировано

0