AT-19SYSTEMATIC RADIOLOGICAL PHENOTYPING OF ATYPICAL TERATOID RHABDOID TUMOURS USING LANGUAGE MODELLED MACHINE LEARNING APPROACHES
Bibliographic record
Abstract
BACKGROUND: Despite multiparametric MRI, uncertainty remains in the radiological phenotyping of intracranial tumours and their specific molecular subtype. We introduce a systematic, reproducible, descriptive imaging model that integrates MRI imaging metrics into one data repository. This dataset underpins a radiological decision support system (DSS) that informs on radiological phenotyping of childhood intracranial tumours and, we propose, informs on their underlying biological makeup. METHODS: Using atypical teratoid rhabdoid tumours (ATRTs) as a test case, a language based systematic analysis and scoring system modelled the imaging phenotype and was correlated with published transcriptional ATRT sub-grouping for each case. Machine learning techniques were employed to drive a classification DSS. RESULTS: In total 35 tumours were analysed of which 46% were male with an age range of 0.14 - 15.6 years. There were 16 supratentorial, 18 infratentorial and 1 spinal tumour. The descriptive model contained 30 major attributes which accommodated 127 variables giving just under 1 million variable permutations per patient. Multiple machine learning approaches were then employed for stratification into ASCL1 positive and negative subtypes. These techniques included neural networks, decision tree stratification, support vector machine analysis and Bayesian networks. CONCLUSIONS: This study presents the first systematic descriptive model of ATRTs integrating any radiological metric to drive a DSS for phenotyping the biological subset of the tumour type. Validation will require the analysis of larger numbers of scans from patients with tumours of known and unknown phenotype. These systems have significant potential as diagnostic and decision making clinical aids.
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 | 0.003 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| 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".