Evaluating noise reduction techniques while considering anatomical noise in dual‐energy contrast‐enhanced mammography
Bibliographic record
Abstract
PURPOSE: The authors describe modifications to previously developed cascaded systems analysis to include the anatomical noise in evaluation of dual-energy noise reduction techniques. Previous models have ignored the anatomical noise in theoretical analysis of noise reduction techniques. The inclusion of anatomical noise leads to more accurate estimation of potential noise reduction improvements and optimization. METHODS: The model is applied to dual-energy contrast-enhanced mammography. The effect of linear noise reduction filters on the anatomical noise is taken into account using cascaded systems analysis. The noise model is included in the ideal observer detectability for performance evaluation of the noise reduction techniques. RESULTS: Dual-energy image noise with and without including the effect of anatomical noise in noise reduction technique analysis is reported. The theoretical model is compared with clinical images from a previous dual-energy contrast enhanced mammography clinical study and good agreement is observed. The results suggest that the inclusion of anatomical noise in the evaluation and comparison of noise reduction techniques is highly warranted for more accurate analysis. CONCLUSIONS: This work establishes a useful extension to dual-energy cascaded systems analysis for maximizing image quality using noise reduction techniques. The extension includes the effect of linear image filtering, such as that used for noise reduction, on anatomical noise. The results suggest that the inclusion of anatomical noise in the evaluation of noise reduction techniques can lead to more accurate optimization, noise, and performance estimations.
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) | 0.000 | 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".