SWO优化的LBP-CNN-模糊逻辑框架用于心脏CT血管造影图像增强与辐射剂量降低
A novel SWO-optimized LBP-CNN-fuzzy approach for angiographic image enhancement and radiation dose reduction in cardiologists and patients
该研究提出一种SWO蜘蛛蜂优化算法改进的LBP-CNN-模糊逻辑融合框架,用于心脏CT血管造影图像处理。实验表明,该方法在提升图像清晰度与对比度的同时,可使患者及医生接受的辐射剂量降低72.15%。
- Article
- Open access
- Published: 18 November 2026
Scientific Reports (2026) Cite this article
We’re sharing this article early to provide faster access to peer-reviewed, accepted research. It is citable and carries a permanent DOI. This version is subject to further edits and will be replaced automatically by the final Version of Record. All legal disclaimers apply.
Abstract
Cardiac CT (CCT) is one of the most important and accurate tools in diagnosing coronary artery diseases and guiding cardiac surgeries. However, it is necessary to reduce the radiation dose to avoid damage caused by X-rays. The main problem in low-dose scans (LDCT) is the increase of quantum noise and the appearance of streak artifacts, which leads to a decrease in the quality of the images. In this research, improving the quality of angiographic images and reducing the radiation dose received by patients and cardiologists has been investigated using the LBP CNN FUZZY method optimized by the SWO spider bee optimization algorithm. In this new framework, a combination of fuzzy logic system, convolutional neural network (CNN) and local binary pattern (LBP) has been used to increase the contrast and improve the quality of the images. The first part of the framework consists of a parser network based on fuzzy logic and LBP, which decomposes the image into illumination and reflectance components. In the next step, the CNN-based adjustment network balances the exposure level by correcting the brightness component and reconstructs the colors with high fidelity. The meta-heuristic SWO algorithm guides the optimization steps of both parts and reduces noise and improves resolution in real time. The results of the experiments showed that the proposed method has a superior performance compared to the traditional methods, so that while obtaining better clarity and contrast in the images, the radiation dose received by the body was reduced by 72.15%. This approach can be effective in cardiac angiography to increase the quality of imaging and reduce the risk of radiation for patients and doctors.
Funding
The authors did not receive any financial support for this study.
Author information
Authors and Affiliations
Department of Electrical and Computer Engineering, Kazerun Branch, Islamic Azad University, Kazerun, Iran
Ali Niazi, Mehdi Taghizadeh, Mohammad Amin Pirbonyeh, Jasem Jamali & Nahid Adlband
Authors
- Ali Niazi
- Mehdi Taghizadeh
- Mohammad Amin Pirbonyeh
- Jasem Jamali
- Nahid Adlband
Corresponding author
Correspondence to Mehdi Taghizadeh.
Ethics declarations
Competing interests
The authors declare no competing interests.
Ethical approval
Not applicable.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix A: Nomenclature
Appendix A: Nomenclature
Symbol/Variable | Description |
|---|---|
\(\:\left({x}_{c},{y}_{c}\right)\) | Coordinates of the central pixel |
\(\:{g}_{c}\)or \(\:{g}_{p}\) | Intensity (gray level) of the central pixel |
\(\:{g}_{i}\) | Intensity of the \(\:i\)-th neighboring pixel |
\(\:P\) | Number of neighboring pixels (set to \(\:P=8\)) |
\(\:r\) | Radius of the neighborhood (set to \(\:r=1\)) |
\(\:s\left(x\right)\) | Thresholding function: \(\:s\left(x\right)=1\)if \(\:x\ge\:0\), otherwise \(\:0\) |
\(\:{\text{LBP}}_{P,r}\left({x}_{c},{y}_{c}\right)\) | Local Binary Pattern value at the central pixel (standard definition) |
\(\:{g}_{1},{g}_{2},\dots\:,{g}_{8}\) | Intensity values of the eight neighbors used in the proposed LBP formulation (Eq. 3) |
\(\:{X}_{i}^{t,d}\) | Position of the \(\:i\)-th spider (agent) in dimension \(\:d\)at iteration \(\:t\) |
\(\:{X}_{\text{Gbest}}^{t}\) | Position of the global best spider at iteration \(\:t\) |
\(\:{X}_{\text{Lbest}}^{t}\) | Position of the local best spider in the neighborhood of agent \(\:i\)at iteration \(\:t\) |
\(\:\alpha\:,\beta\:\) | Control coefficients weighting the influence of global and local best positions |
\(\:\gamma\:\) | Control coefficient for the prey-capture movement |
\(\:\text{rand}\) | Uniformly distributed random number in \(\:\left[0,1\right]\) |
\(\:\mu\:\) | Mean (center) of a Gaussian membership function |
\(\:\sigma\:\) | Standard deviation (width parameter) of a Gaussian membership function |
\(\:{\mu\:}_{A}\left(x\right)\) | Membership degree of value \(\:x\)in fuzzy set \(\:A\) |
\(\:K\) | Histogram vector of the image intensity distribution (\(\:K=\text{imhist}\left(\text{image}\right)\)) |
Fitness Function | Objective function used by SWO: \(\:\text{std}\left(K\right)\)(standard deviation of the intensity histogram) |
BRISQUE | Blind/Referenceless Image Spatial Quality Evaluator score (lower is better) |
NIQE | Natural Image Quality Evaluator score (lower is better) |
PIQE | Perceptual Image Quality Estimator score (lower is better) |
NH, NL, Z, PL, PH | Output fuzzy linguistic terms: Negative High, Negative Low, Zero, Positive Low, Positive High |
L, LM, M, MH, H | Input fuzzy linguistic terms for pixel intensity: Low, Low-Medium, Medium, Medium-High, High |
Low, mide, high | Input fuzzy linguistic terms for the LBP-based edge/intensity-change level |
- All Gaussian membership functions are of the form \(\:{\mu\:}_{A}\left(x\right)=\text{exp}\left(-\frac{{\left(x-\mu\:\right)}^{2}}{2{\sigma\:}^{2}}\right)\).
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Niazi, A., Taghizadeh, M., Pirbonyeh, M.A. et al. A novel SWO-optimized LBP-CNN-fuzzy approach for angiographic image enhancement and radiation dose reduction in cardiologists and patients. Sci Rep (2026). https://doi.org/10.1038/s41598-026-79640-6
Received: 02 June 2026
Accepted: 02 November 2026
Published: 18 November 2026
DOI: https://doi.org/10.1038/s41598-026-79640-6
Keywords
来源:Nature 健康护理主题 · nature.com