Denoising RF Data via Robust Principal Component Analysis: Results in Ultrasound Elastography
Bibliographic record
Abstract
Ultrasound data often suffers from an excessive amount of noise especially from deep tissue or in synthetic aperture imaging where the acoustic wave is weak. Such noisy data renders Time Delay Estimation (TDE) inaccurate in the context of ultrasound elastography. Herein, a novel two-step elastography technique is presented to ensure accurate TDE while dealing with noisy ultrasound data. In the first step, instead of one, we acquire several Radio-Frequency (RF) frames from both pre- and post-deformed positions of the tissue. We stack the frames collected from pre- and post-deformed planes in separate data matrices. Since each set is collected from the same level of tissue compression, we assume that the Casorati data matrices exhibit underlying low-rank structures, which are sought by taking the low-rank and sparse decomposition framework into account. This Robust Principal Component Analysis (RPCA) approach removes the random noise from the datasets as sparse error components. In the second step, we select one frame from each denoised ensemble and employ GLobal Ultrasound Elastography (GLUE) to perform the strain elastography. We call the proposed technique RPCA-GLUE. Our preliminary validation of RPCA-GLUE against simulation phantoms containing hard and soft inclusions proves its robustness to large noise. Substantial improvement in Signal-to-Noise Ratio (SNR) and Contrast-to-Noise Ratio (CNR) has also been observed. Simulation results show that in the presence of large noise, the proposed method substantially improves CNR from 5.0 to 22.6 in a soft inclusion and from 2.2 to 21.7 in a hard inclusion phantom.
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 | 0.012 |
| Meta-epidemiology (narrow) | 0.002 | 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 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".