Multiclass Epilepsy Classification Using Radiomics Features From T1-Weighted MRI
Bibliographic record
Abstract
Temporal lobe epilepsy (TLE) is the most common drug-resistant epilepsy subtype, with critical differences between right (R-TLE) and left (L-TLE) forms. This study presents a multiclass machine learning framework utilizing radiomics features from T1-weighted MRI to differentiate RTLE, L-TLE, and healthy controls (HC). A total of 210 participants (110 TLE, 100 HC) underwent high-resolution 3T MRI. From 92 brain regions segmented via FreeSurfer, 105 radiomics features per region were extracted using PyRadiomics, yielding 9,660 features per subject. Fifteen machine learning classifiers and two feature selection methods (Recursive Feature Elimination (RFE) and K-best) were implemented. To ensure robust evaluation, three performance strategies were implemented: (1) individual region-wise metrics, reporting accuracy (ACC), area under the curve (AUC), sensitivity (SEN), specificity (SPE), Positive Predictive Value (PPV), and Negative Predictive Value (NPV) for each brain region; (2) average metrics of the top 10 best-performing models per region, identifying the most robust ROIs; and (3) inputting all features from all regions to the models, selecting the top 15 features globally to train final classifiers. The Decision Tree classifier using RFE on all 9,660 features achieved the highest classification performance (ACC: 0.92 AUC: 0.95 SEN: [1.0, 0.93, 0.92], SPE: [1.0, 0.95, 0.95], PPV: [1.0, 0.94, 0.90], NPV: [1.0, 0.95, 1.0]). Among individual regions, the left Cuneus showed the strongest performance when averaged across the top 10 models (ACC: 0.85, AUC: 0.91). Texture and shape-based features were most predictive, and bilateral analysis revealed <5% hemispheric performance difference. This multiclass radiomics-based pipeline offers a powerful, non-invasive diagnostic tool for epilepsy subtyping, outperforming traditional binary classification methods and supporting personalized medicine 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 | 0.002 | 0.003 |
| 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 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| 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".