Anatomy-to-Tract Mapping Infers White Matter Pathways Without Diffusion Streamline Propagation
Bibliographic record
Abstract
Diffusion tractography, a cornerstone of white matter mapping, relies on point-to-point streamline propagation-a process often compromised by errors stemming from inadequate signal-to-noise ratio and limited spatioangular resolution in diffusion MRI (dMRI) data. Here, we introduce Anatomy-to-Tract Mapping (ATM), the first model to our knowledge that generates bundle-specific streamlines directly from T1-weighted MRI without requiring orientation field estimation, voxelwise segmentation, and streamline propagation. ATM leverages the superior quality and minimal distortion of anatomical MRI and learns from multi-subject datasets to deliver robust, subject-specific streamline bundles with accurate preservation of structural connectivity. Trained on paired T1w and tractogram data, ATM learns to synthesize anatomically plausible streamlines conditioned on subject anatomy. This paradigm-shifting approach overcomes challenges associated with complex configurations, such as crossing, kissing, bending, and bottlenecks, providing anatomically guided bundle reconstructions. Using the TractoInferno dataset with 30 white matter bundles, we compared the performance of ATM against methods based on diffusion MRI, including MRtrix probabilistic tracking with BundleSeg for bundle segmentation, and Sherbrooke Connectivity Imaging Lab (SCIL) white matter atlas warping. ATM consistently showed strong performance across several metrics, including bundle similarity, volume coverage, angular correlation, streamline validity, geometric fidelity, and connection topology. ATM complements diffusion tractography by leveraging global anatomical features that are less susceptible to local uncertainties, providing a robust, anatomy-driven approach to reconstructing white matter pathways.
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 | 0.002 | 0.007 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".