Poster — Wed Eve—09: Quest for a “Gold Standard” for Breast Density Evaluation
Bibliographic record
Abstract
We have examined the breast density evaluation process using commonly employed methods, visual BIRADS estimate, standard thresholding method (Cumulus) and a newly developed automatic assessment algorithm (Bden) in order to obtain clues for a “gold standard” for breast density estimation. According to these results the experts were in exact agreement for 23 out of 36 images, corresponding to the 63.9 % of the total sample and kappa statistics with indicates the proportion of the chance agreement (expected) is as 30.9 %. Agreement between the two experts found to be less than 70%. It was always possible to include a given image one class lower or higher. Furthermore, systematical shifts in the BIRADS category estimates between the readers have been noticed. The results obtained, although within a limited sample and from only one patient population, indicate that it is difficult to obtain a gold standard using the visual method as judgment plays an important role. Furthermore, there exist systematical shifts in the BIRADS category estimates between the observers. As a result, assessments given by different observers or obtained at a later time are not easily comparable. Hence, there may be even no “gold standard” unless a new scale of breast density using an automated method is defined.
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 | 0.019 | 0.014 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.000 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.008 | 0.004 |
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".