Advanced Analysis of Diffusion Tensor Imaging Along With Machine Learning Provides New Sensitive Measures of Tissue Pathology and Intra-Lesion Activity in Multiple Sclerosis
Bibliographic record
Abstract
Tissue pathology in multiple sclerosis (MS) is highly complex, requiring multi-dimensional analysis. In this study, our goal was to test the feasibility of obtaining high angular resolution diffusion imaging (HARDI) metrics through single-shell modeling of diffusion tensor imaging (DTI) data, and investigate how advanced measures from single-shell HARDI and DTI tractography perform relative to classical DTI metrics in assessing MS pathology. We examined 52 relapsing-remitting MS patients who had 3T anatomical brain MRI and DTI. Single-shell HARDI modeling yielded 5 sub-voxel-based metrics, totalling 11 diffusion measures including 4 DTI and 2 tractography metrics. Based on machine learning of 3-dimensional regions of interest, we evaluated the importance of the measures through several tissue classification tasks. These included two within-subject comparisons: lesion versus normal appearing white matter (NAWM); and lesion core versus shell. Further, by stratifying patients as having high (above 75%ile) and low (below 25%ile) number of MS lesions, we also performed 2 classifications between subjects for lesions and NAWM respectively. Results showed that in lesion-NAWM analysis, HARDI orientation distribution function (ODF) energy, DTI fractional anisotropy (FA), and HARDI orientation dispersion index were the top three metrics, which together achieved 65.2% accuracy and 0.71 area under the receiver operating characteristic curve (AUROC). In core-shell analysis, DTI mean diffusivity (MD), radial diffusivity, and FA were the top three metrics, and MD dominated the classification, which achieved 59.3% accuracy and 0.59 AUROC alone. Between patients, FA was the leading feature in lesion comparisons, while ODF energy was the best in NAWM separation. Collectively, single-shell modeling of common diffusion data can provide robust orientation measures of lesion and NAWM pathology, and DTI metrics are most sensitive to intra-lesion abnormality. Combined analysis of both advanced and classical diffusion measures may be critical for improved understanding of MS pathology.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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".