Denoising Echocardiography with an Improved Diffusion Model
Bibliographic record
Abstract
Echocardiography has been a crucial role in diagnosing cardiac disease. However, its effectiveness is often hindered by poor image clarity. Acoustic interference arises from multipath reflections caused by skin layers, subcutaneous fat, and intercostal muscle between the US transducer and the heart. Consequently, the appearance of noise and other artifacts presents a substantial obstacle to the accuracy of cardiac ultrasound imaging. Therefore, effective despeckling techniques are necessary to enhance the interpretability of ultrasound images and diagnostic results. Recently, diffusion approach has become a trending topic in computer vision. This paper proposes a diffusion model-based denoising method with an interpolation technique and a simple U-Net architecture to enhance ultrasound images' quality in an unsupervised manner. The proposed method generates the interim image by interpolating the initial noise-free image and its corresponding noisy image at each diffusion step. This method iteratively reduces the noise and preserves its texture to improve the quality of degraded images. The proposed approach was trained and then validated on two benchmarks. The experimental outcomes demonstrate that the proposed approach outperforms the other denoising approaches in clinically relevant qualitative and quantitative visual metrics. The source code will be made available at https://github.com/RPRO5/DiffUS.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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 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".