P4‐074: Automated quantification of [18F]flutemetamol amyloid imaging data
Bibliographic record
Abstract
Although visual read can be used to categorize amyloid imaging scans into raised or normal uptake levels, image quantification can help in equivocal cases and will also be necessary for longitudinal comparisons. For use in routine clinical practice, a fully automated quantification method will be beneficial to aid in image analysis and reporting. An application for quantification of [F]flutemetamol data was developed. It takes the patient's PET and MR scan as input and the following processing steps are applied: 1) the MR is co-registered to the PET; 2) the PET is spatially normalized to Montreal Neurological Institute (MNI) space and the transformation is applied to the co-registered MR; 3) counts in a reference region (cerebellum gray matter or pons) and a Standardized Uptake Value Ratio (SUVR) image is computed; 4) a volume of interest (VOI) atlas is applied and SUVR values within cortical regions defined by the atlas are computed; 5) cortical surface projections are computed; and 6) the results are compared to a normals database and z-scores are computed. Result views include VOI SUVR values and z-scores, voxel-based z-scores projected on the subject's MR as well as SUVR and z-score surface projections. The MR is optional and if not available, an MR template (ICBM-152) is used for display purposes. 27 patients with early-stage Alzheimer's disease (AD), 20 with mild cognitive impairment (MCI) and 25 healthy volunteers (HV) from the [F]flutemetamol Phase II study were used to evaluate the application. The HV data was used to build a normals database. All scans were analyzed and were categorized into raised or normal levels of amyloid based on the Z score value of a composite cortical VOI using a Z score threshold of 2.0. The results were compared to a blinded visual read by five independent trained readers. The categorization of scans made by the automated application showed concordance with the visual read results in all the AD and HV scans and in 19 of 20 MCI scans. The results were identical for both reference region methods. The figure shows results from an Aβ- and an Aβ+ subject with comparison to normal
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 | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 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 | 0.000 |
| Insufficient payload (model declined to judge) | 0.018 | 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; 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".