Speckle Noise Reduction Techniques in Ultrasound Imaging: A comprehensive review of the last two decades (2005–2024)
Bibliographic record
Abstract
Ultrasound imaging has become a widely used medical modality over the past few decades. Despite technological advances, ultrasound images are susceptible to inherent noise that arises from tissue inhomogeneities and other acquisition-related uncertainties. The presence of noise degrades image quality and impacts diagnostic accuracy, necessitating the development of effective denoising techniques. In ultrasound denoising, the preservation of important structural information while reducing noise poses a significant challenge. Therefore, various techniques have been presented to enhance the quality of ultrasound images, each method having its own assumptions, strengths, and limitations. In this study, a comprehensive survey of significant work on ultrasound image denoising was presented. Understanding the nature of noise in ultrasound images and selecting an appropriate denoising method tailored to specific needs can be challenging for researchers. To address these challenges, basics of ultrasound imaging, including the characteristics of noise in ultrasound images, is clearly explained in this paper. This study involved a comprehensive search across six digital databases, considering studies published over the last two decades, up to 2024. Initially, 538 studies were identified. From these, 85 studies were selected for detailed examination. For these 85 studies, we used snowballing and direct searches to locate additional relevant publications by the researchers and their associated research groups. Ultimately, we reviewed a total of 97 studies focusing on speckle noise reduction in ultrasound imaging. In addition, the merits and drawbacks of existing methods are analyzed and tabulated.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.002 | 0.001 |
| Meta-epidemiology (broad) | 0.003 | 0.001 |
| Bibliometrics | 0.005 | 0.005 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.004 | 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".