The International Brain Tumor Segmentation (BraTS) Cluster of Challenges
Bibliographic record
Abstract
The International Brain Tumor Segmentation (BraTS) challenge. BraTS, since 2012, has focused on the generation of a benchmarking environment and dataset for the delineation of adult brain gliomas. The focus of this year’s challenge remains the generation of a common benchmarking environment, but its dataset is substantially<br> expanded to ~4,500 cases towards addressing additional i) populations (e.g., sub-Saharan Africa patients), ii) tumors (e.g., meningioma), iii) clinical concerns (e.g., missing data), and iv) technical considerations (e.g., augmentations). Specifically, the focus of BraTS 2023 is to identify the current state-of-the-art algorithms for addressing (Task 1) the same adult glioma population as in the RSNA-ANSR-MICCAI BraTS challenge, as well as (Task 2) the underserved sub-Saharan African brain glioma patient population, (Task 3) intracranial meningioma, (Task 4) brain metastasis, (Task 5) pediatric brain tumor patients, (Task 6) global & local missing data, (Task 7) useful augmentation techniques, and importantly (Task 8) the algorithmic generalizability across Tasks 1-5. Details for each ‘Task’ are listed in the rest of this documents. Notably, all data are routine clinically-acquired, multi-site multiparametric magnetic resonance imaging (mpMRI) scans of brain tumor patients. The BraTS 2023 challenge participants are able to obtain the training and validation data of the challenge at any point from the Synapse platform. These data will be used to develop, containerize, and evaluate their algorithms in unseen validation data until August 2023, when the organizers will stop accepting new submissions and evaluate the submitted algorithms in the hidden testing data. Ground truth reference annotations for all datasets are created and approved by expert neuroradiologists for every subject included in the training, validation, and testing datasets to quantitatively evaluate the performance of the participating algorithms.
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 | 0.001 | 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 | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.042 | 0.007 |
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; both teacher heads agree on what is shown here.
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".