Perfusion MRI in automatic classification of multiple sclerosis lesion subtypes
Bibliographic record
Abstract
Abstract This retrospective and exploratory study investigated the efficiency of the 3T perfusion magnetic resonance imaging (MRI) at the classification of MS lesion subtypes. For the MS lesion subtype classification, firstly, it was necessary to segment all MS lesions. Therefore, a Bayesian classifier based on the adaptive mixture method was used to segment all lesions, and an artificial neural network (ANN) employed a multi‐layer Perceptron as a subtype classifier. The Bayesian classifier accomplished the segmentation of lesions using Fluid Attenuated Inversion Recovery automatically, and the ANN part was used as a subtype classifier that worked based on extracted information from perfusion MRI (i.e. Mean Transit Time and Cerebral Blood Volume maps) along with the intensity information of the conventional multi‐channel MRI in segmented lesions. Adding 3‐Tesla perfusion MRI to the proposed model for the subtype classification led to an increment of about 7% and 13% in the sensitivity of acute and chronic lesion classifications, respectively. The sensitivity of T 2 lesions did not meaningfully change. The overall accuracy of the classification for acute, chronic, and T 2 lesion classifications was 96.1%, 90.5%, and 92.9%, respectively. The proposed architectures reached high sensitivity in discrimination between MS lesion subtypes when 3T perfusion MRIs were used.
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 | 0.004 | 0.008 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".