Adaptive Data Function for Robust Ultrasound Elastography
Bibliographic record
Abstract
Regularized optimization-based ultrasound elastography techniques minimize an energy function consisting of data and continuity terms to obtain the displacement tensor between radio-frequency (RF) frames. The data term associated with the existing energy-based techniques takes only the amplitude similarity into account and hence lacks robustness to the outlier samples present in the RF frames. This drawback creates noticeable artifacts in the strain image. To address this issue, we devise the data function as a linear combination of the amplitude and gradient residuals. We follow an iterative scheme to estimate the adaptive weight associated with each similarity term. Finally, we convert the non-linear optimization problem to a sparse system of linear equations which is solved for millions of variables in an efficient manner. We name our technique rGLUE: robust data term in GLobal Ultrasound Elastography. We validate rGLUE using simulation and in vivo breast datasets. In both of the experiments, rGLUE proves its robustness to outliers and outperforms state-of-the-art time-delay estimation technique both visually and quantitatively. For the noisy simulation data, the proposed rGLUE technique improves the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) from 1.67 to 7.04 and 2.89 to 13.46, respectively. In case of the breast datasets, SNR and CNR improves from 6.35 to 7.81 and 7.94 to 9.90, respectively.
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 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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".