Effectiveness of Fourier, Wiener, Bilateral, and CLAHE Denoising Methods for CT Scan Image Noise Reduction
Bibliographic record
Abstract
The proper reduction of noise inside CTscan Images remains crucial to achieve both better diagnosis results and clinical choices. This research analyzes through quantitative metrics the effectiveness of four popular noise reduction methods which include Fourier-based denoising and Wiener filtering as well as bilateral filtering and Contrast Limited Adaptive Histogram Equalization (CLAHE) applied to more than 500 CTscan Images. The investigated methods were assessed quantitatively through Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) while Mean Squared Error (MSE) served as the additional metric for evaluation. The evaluated denoising methods revealed bilateral filtering as the best technique based on its 50.37 dB PSNR and 0.9940 SSIM together with its 0.5967 MSE. Denoising with Fourier-based methods succeeded in removing high-frequency noise however it produced PSNR of 25.89 dB along with SSIM of 0.8138 while maintaining MSE at 167.4976 indicating lost crucial Image information. The performance balance of Wiener filtering resulted in 40.87 dB PSNR and 0.9809 SSIM and 5.3270 MSE that outperformed Fourier denoising in SSIM yet demonstrated higher MSE. CLAHE produces poor denoising outcomes because it achieves the lowest PSNR of 21.51 dB together with SSIM of 0.5707, and the maximum MSE of 459.1894 while creating undesirable artifacts. This research stands out through a full evaluation of four denoising techniques on a big dataset to create more precise analysis than prior research. The research results show bilateral filtering to be the most reliable technique for CTscan Image noise reduction when maintaining picture quality and thus represents a suitable choice for clinical use. This research adds new information to medical imaging research about quality enhancement which directly benefits clinical diagnostics and therapeutic planning.
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 | 0.003 | 0.007 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 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 | 0.001 |
| 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".