Advanced MRI Biomarkers and Deep Learning for Efficient Clinical Trials in Frontotemporal Dementia Subtypes
Bibliographic record
Abstract
BACKGROUND: Frontotemporal Dementia (FTD) encompasses a spectrum of neurodegenerative disorders characterized by progressive atrophy in the frontal and temporal lobes. These disorders manifest in three primary subtypes: behavioral variant FTD (bvFTD), semantic variant primary progressive aphasia (svPPA), and non-fluent variant primary progressive aphasia (nfvPPA). Each subtype presents unique clinical and anatomical changes. Understanding these patterns is critical for early diagnosis, tracking disease progression, and designing effective clinical trials for potential disease-modifying therapies. This study leverages advanced imaging techniques and automated processing pipelines to identify sensitive biomarkers and optimize clinical trial design. METHODS: MRI data from the Frontotemporal Lobar Degeneration Neuroimaging Initiative (FTLDNI) were analyzed using the PIANO™ automated pipeline for volumetric and diffusion MRI (dMRI) analyses. Gray matter density, mean diffusivity (MD), and free water (FW) were assessed in 238 participants: 52 bvFTD, 32 nfvPPA, 35 svPPA, and 117 healthy controls. Sample size calculations were performed to estimate the number of participants required to detect a 60% reduction in brain atrophy and diffusion metrics over 6 to 24 months. Deep learning-based segmentation, particularly for the hippocampus, enhanced reliability and reduced variability. RESULTS: Distinct patterns of brain atrophy emerged across FTD variants as illustrated in Figure 1, with svPPA (green) exhibiting the most rapid progression, particularly in the hippocampus, temporal cortex, and amygdala, with up to 15% volume loss over 24 months. bvFTD (blue) primarily showed frontal and cingulate cortical changes, while nfvPPA (orange) demonstrated moderate, less localized changes. Sample size requirements were lowest for svPPA, with fewer than 35 participants per arm needed to detect therapeutic effects in key brain regions within 6 to 12 months. PIANO™-based analyses demonstrated greater sensitivity and smaller sample size needs compared to other methods. CONCLUSION: This study highlights the utility of advanced imaging biomarkers in differentiating FTD subtypes and monitoring progression. The integration of volumetric and dMRI metrics, along with deep learning segmentation, offers precise, early detection of changes, thereby reducing sample size requirements and enabling cost-effective, efficient clinical trials. Furthermore, this approach offers insights into the unique spatial and temporal progression patterns of each FTD subtype, paving the way for personalized intervention strategies.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.036 | 0.055 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".