34 RISK STRATIFICATION USING DEEP FEATURES IN IDH-MUTANT GLIOMAS
Bibliographic record
Abstract
Abstract BACKGROUND The current diagnostic framework for IDH-mutant gliomas relies on molecular biomarkers, the most important of which being driver mutations in IDH1/2 and whole arm codeletion in chromosomes 1p and 19q. Despite these molecular indicators, a subset of patients with favourable prognosis still have poor outcomes. In this work, we explore whether morphological features, extracted using pathology foundation models, can be used to stratify IDH-mutant cases into high and low-risk cases. DESIGN Our dataset consisted of 886 IDH-mutant glioma cases from the The Cancer Genome Atlas Low Grade Glioma and Glioblastoma (TCGA-LGGGBM) studies, as well as two external validation sets of 145 patients (VIENNA) and 82 patients (VGH). We trained a self-supervised feature extractor on 256x256 pixel patches extracted at 20x magnification. These features were then used to train a multiple-instance learning model for survival prediction. RESULTS We achieved a c-index of 0.77 on the TCGA-LGG test dataset, and 0.63/0.65 on the two external datasets. Further analysis found that these risk scores can be used to identify two distinct risk groups, agnostic of the current diagnostic framework, that exhibit inherent morphological and genomic variation. CONCLUSIONS Our findings suggest that deep learning-based features can be used to predict outcome, and identify distinct risk groups in gliomas. These findings could lead to further refinement of the current diagnostic categories of IDH-mutant gliomas, and guide more targeted treatments in the future.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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 teacher head, 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".