Biology subjects

for the Alzheimers Disease Neuroimaging Initiative,

Publications and source records attributed to for the Alzheimers Disease Neuroimaging Initiative,.

3 recordsLinked to original sources

bioRxiv2026

Machine learning on subcortical brain features: A study of sample size efficiency for neurodegenerative disease classification

Subcortical brain alterations are a key feature of dementia disease progression. Machine learning (ML) has been applied widely to MRI-based brain features in dementia, where performance depends on the model choice, training data size, and input feature characteristics. Most studies compare ML models using a single training sample size. Here, we evaluate the sample-size efficiency of ML models based on subcortical gross volume and vertex-wise shape features for dementia stage classification using 2,511 samples in the Alzheimer's Disease Neuroimaging Initiative (ADNI). Learning curves were generated for dementia vs. cognitively normal controls (CN), dementia vs. mild cognitive impairment (MCI), and MCI vs. CN across increasing training sample sizes. Classification performance improved when increasing sample size for all models, with late- fusion models consistently achieving the highest performance, and Logit-TVL1 outperforming the other shape-based models. Learning curve analysis showed that classification performance was driven by the training sample size and the magnitude of anatomical group differences, and can be used to optimize future model selection tasks in dementia and other brain disorders.

neuroscience↗

bioRxiv2024

Automatization and validation of the hippocampal-to-ventricle ratio in a clinical sample

BackgroundThe hippocampal-to-ventricle ratio (HVR) is a biomarker of medial temporal atrophy, particularly useful in the assessment of neurodegeneration in diseases such as Alzheimers disease (AD). To minimize subjectivity and inter-rater variability, an automated, accurate, precise, and reliable segmentation technique for the hippocampus (HC) and surrounding cerebro-spinal fluid (CSF) filled spaces -- such as the temporal horns of the lateral ventricles -- is essential. MethodsWe trained and evaluated three automated methods for the segmentation of both HC and CSF (Multi-Atlas Label Fusion (MALF), Nonlinear Patch-Based Segmentation (NLPB), and a Convolutional Neural Network (CNN)). We then evaluated these methods, including the widely used FreeSurfer technique, using baseline T1w MRIs of 1,641 participants from the AD Neuroimaging Initiative study with various degree of atrophy associated with their cognitive status on the spectrum from cognitively healthy to clinically probable AD. Our gold standard consisted in manual segmentation of HC and CSF from 80 cognitively healthy individuals. We calculated HC volumes and HVR and compared all methods in terms of segmentation reliability, similarity across methods, sensitivity in detecting between-group differences and associations with age, scores of the learning subtest of the Rey Auditory Verbal Learning Test (RAVLT) and the Alzheimers Disease Assessment Scale 13 (ADAS13) scores. ResultsCross validation demonstrated that the CNN method yielded more accurate HC and CSF segmentations when compared to MALF and NLPB, demonstrating higher volumetric overlap (Dice Kappa = 0.94) and correlation (rho = 0.99) with the manual labels. It was also the most reliable method in clinical data application, showing minimal failures. Our comparisons yielded high correlations between FreeSurfer, CNN and NLPB volumetric values. HVR yielded higher control:AD effect sizes than HC volumes among all segmentation methods, reinforcing the significance of HVR in clinical distinction. AssociationsThe positive association with age was significantly stronger for HVR compared to HC volumes on all methods except FreeSurfer. Memory associations with HC volumes or HVR were only significant for individuals with mild cognitive impairment. Finally, the HC volumes and HVR showed comparable negative associations with ADAS13, particularly in the mild cognitive impairment cohort. ConclusionThis study provides an evaluation of automated segmentation methods centered to estimate HVR, emphasizing the superior performance of a CNN-based algorithm. The findings underscore the pivotal role of accurate segmentation in HVR calculations for precise clinical applications, contributing valuable insights into medial temporal lobe atrophy in neurodegenerative disorders, especially AD. AuthorshipO_LISofia Fernandez-Lozano: Conceptualization, Methodology, Software, Investigation, Writing - Original Draft, Visualization. C_LIO_LIVladimir Fonov: Software, Data Curation. C_LIO_LIDorothee Schoemaker: Resources, Writing - Review & Editing. C_LIO_LIJens Pruessner: Resources, Writing - Review & Editing. C_LIO_LIOlivier Potvin: Resources, Writing - Review & Editing. C_LIO_LISimon Duchesne: Resources, Writing - Review & Editing. C_LIO_LID. Louis Collins: Conceptualization, Writing - Review & Editing, Supervision. C_LI

neuroscience↗

bioRxiv2020

The Temporal Relationships between White Matter Hyperintensities, Neurodegeneration, Amyloid β, and Cognition

INTRODUCTIONCognitive decline in Alzheimers disease is associated with amyloid-{beta} accumulation, neurodegeneration and cerebral small vessel disease, but the temporal relationships between these factors is not well established. METHODSData included white matter hyperintensity (WMH) load, grey matter (GM) atrophy and Alzheimers Disease Assessment Scale-Cognitive-Plus (ADAS13) scores for 720 participants and cerebrospinal fluid amyloid (A{beta}1-42) for 461 participants from the Alzheimers Disease Neuroimaging Initiative. Linear regressions were used to assess the relationships between baseline WMH, GM, and A{beta}1-42 to changes in WMH, GM, A{beta}1-42, and cognition at one-year follow-up. RESULTSBaseline WMHs and A{beta}1-42 predicted WMH increase and GM atrophy. Baseline WMHs, GM, and A{beta}1-42 predicted worsening cognition. Only baseline A{beta}1-42 predicted change in A{beta}1-42. DISCUSSIONBaseline WMHs lead to greater future GM atrophy and cognitive decline, suggesting that WM damage precedes neurodegeneration and cognitive decline. Baseline A{beta}1-42 predicted WMH increase, suggesting a potential role of amyloid in WM damage. Research in ContextO_LISystematic Review: Both amyloid {beta} and neurodegeneration are primary pathologies in Alzheimers disease. White matter hyperintensities (indicative of presence of cerebrovascular disease) might also be part of the pathological changes in Alzheimers. However, the temporal relationship between white matter hyperintensities, amyloid {beta}, neurodegeneration, and cognitive decline is still unclear. C_LIO_LIInterpretation: Our results establish a potential temporal order between white matter hyperintensities, amyloid {beta}, neurodegeneration, and cognitive decline, showing that white matter hyperintensities precede neurodegeneration and cognitive decline. The results provide some evidence that amyloid {beta} deposition, in turn, precedes accumulation of white matter hyperintensities. C_LIO_LIFuture Directions: The current findings reinforce the need for future longitudinal investigations of the mechanisms through which white matter hyperintensities impact the aging population in general and Alzheimers disease patients, in particular. C_LI

neuroscience↗