P17.04 Radiomics analysis of primary central nervous system lymphoma (PCNSL) - A LOC network study
Bibliographic record
Abstract
BACKGROUND: PCNSL are rare extranodal, malignant non-Hodgkin lymphomas of diffuse large B-cell type confined to the CNS. In the last years, several recurrent molecular genetic alterations have been described in PCNSL but whether they are correlated with the tumor anatomical localization has never been investigated. OBJECTIVES: We sought to analyze a genotype (molecular alterations) - phenotype (MRI data) in PCNSL. MATERIAL AND METHODS: 50 PCNSL MR images of treatment-naïve patients were correlated with molecular alterations (i.e. MYD88 L265P, CD79B and TERT promoter mutations as well as a novel chimeric transcript that our laboratory has recently identified in PCNSL) obtained by Sanger sequencing. MRI data was analyzed as follows: (i) NIfTI data were registered to a 1.0 mm isotropic, high-resolution T1-weighted brain atlas provided by the Montreal Neurological Institute (MNI152) using a mutual information algorithm with a 12-degree of freedom transformation with FSL-FLIRT; (ii) gadolinium-enhancing lesions were manually segmented and saved as voxels-of-interest (VOIs); (iii) A heat-map for the frequency of lesion occurrence was reconstructed and superimposed on the reference MNI152; (iv) Structure probability maps (brain regions) were defined according to Talairach MRI Atlas and (v) genotype - phenotype correlation was performed using voxel-based lesion-symptom mapping (VLSM) using FDR < 0.05 after 4000 permutations. RESULTS: We found mutations of MYD88 in 18 patients, of CD79B in 15 patients and of TERT promoter in 6 patients. The novel chimeric transcript was identified in 11 patients. PCNSL harboring TERT promoter mutations and the chimeric transcript were more frequently found in the corpus callosum (FDR < 0.05). Conversely, we did not find a specific genotype-phenotype correlation with the rest of molecular alterations. CONCLUSION: We provide a MRI probabilistic atlas linking genotype to phenotype in PCNSL. These results need further investigation. Acknowledgements: Association pour la Recherche sur les Tumeurs Cérébrales (ARTC), Ligue contre le Cancer, Fondation pour la recherche médicale, Institut National du Cancer (INCa), Cancéropôle Île-de-France, Département de la Recherche Clinique de l’APHP, CRC de l’APHP, réseau Lymphomes Oculo-Cérébraux (LOC).
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) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| 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".