Saturation Transfer Imaging Radiomics using Machine Learning Improves Differentiation of Tumour Progression from Radiation Necrosis in Brain Metastases
Bibliographic record
Abstract
Abstract Objectives This study aimed to develop a machine learning classifier that integrates, along with structural MRI, radiomic features from saturation transfer (ST) MRI techniques, including magnetization transfer (MT) and chemical exchange saturation transfer (CEST), to distinguish tumour progression (TP) from radiation necrosis (RN) in brain metastases following stereotactic radiosurgery (SRS). Methods 174 lesions from 88 patients were analyzed, extracting 2823 radiomic features from T1-, T2-, FLAIR-, and magnetization transfer ratio (MTR)-based images at APT and NOE offsets. After applying feature selection, a 20-feature subset composed mainly of high B1-saturation MTR metrics and quantitative T1 map features was identified. Classifier performance was assessed using cross-validation, with sensitivity and specificity as primary metrics. Results The best performing classifier was Extra Trees, achieving a sensitivity of 0.91 and a specificity of 0.85. Highly ranked features included those derived from MTR maps at higher saturation amplitudes (2.5 µT) and quantitative T1 maps. With the exclusion of MTR-based features, accuracy dropped from 88% to 73% and AUC from 0.89 to 0.77, with a corresponding increase in false positives. Conclusions Results demonstrated that integrating CEST-derived radiomics with conventional MRI provides robust diagnostic performance in differentiating TP from RN. Features derived from MTR maps—especially at higher saturation amplitudes—and quantitative T1 mapping were among the most discriminative, with their exclusion resulting in significantly lower classification performance. This combined radiomics approach may offer a clinically feasible and non-invasive means of guiding treatment decisions to improve patient management for brain metastases post-SRS.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 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 | 0.001 |
| 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 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".