A deep autoencoder for fast spectral–temporal fitting of dynamic deuterium metabolic imaging data at 7T
Bibliographic record
Abstract
Deuterium metabolic imaging (DMI) is a non-invasive magnetic resonance spectroscopic imaging technique enabling in vivo mapping of glucose metabolism. Dynamic DMI provides time-resolved metabolite maps and allows spatially resolved fitting of metabolic models to capture metabolite concentration dynamics. However, conventional fitting tools often require long processing times for high-resolution datasets, limiting their practical utility. To address this bottleneck, we propose a deep autoencoder (DAE) for rapid spectral-temporal fitting of dynamic DMI data, supporting arbitrary parametric model constraints to describe metabolite concentration dynamics. The DAE was benchmarked against spectral-temporal fitting using FSL-MRS and LCModel. Fitting accuracy was evaluated on in vivo and synthetic whole-brain dynamic DMI data acquired at 7T using Bland-Altman metrics, Pearson correlation coefficients, structural similarity index measures, and root mean squared errors for both metabolite concentrations and model constraint parameters. The DAE achieved processing times of 0.29 ms per voxel, corresponding to an acceleration of more than three orders of magnitude compared to LCModel/FSL-MRS (0.55/0.65 s per voxel). On in vivo data, it showed excellent agreement with LCModel, and on synthetic data, it consistently outperformed both reference methods across all evaluation metrics. The proposed DAE enables accurate spectral-temporal fitting for whole-brain dynamic DMI scans within less than a second, matching or exceeding the performance of conventional state-of-the-art fitting methods. This makes it a promising tool for integration into efficient post-processing pipelines for research and clinical DMI workflows.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 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".