Adaptive Noise Compensation Method in Intraskopic Imaging Based on Wavelet Analysis and Local Contrast Filtering
Keywords:
intraskopic imaging, image quality enhancement, adaptive filtering, wavelet decomposition, local contrast, CLAHE, SSIM, PSNRAbstract
The article presents a novel method for enhancing the quality of intraskopic images, based on adaptive noise compensation through the combination of wavelet decomposition and local contrast filtering. The relevance of the problem is determined by the fact that modern medical imaging systems often produce images with low contrast, significant noise levels, uneven illumination, and motion artifacts, which complicates accurate diagnostic interpretation. The problem is formulated as an inverse signal restoration task. An algorithm for constructing a filtering sequence is proposed, which involves multilevel wavelet decomposition, adaptive processing of detail coefficients, and signal reconstruction, followed by the application of CLAHE, guided filtering, and bilateral smoothing. Simulation and experimental studies were carried out in MATLAB R2023a using publicly available medical datasets (Kvasir, HyperKvasir, EndoVis).
The results demonstrated that the method significantly improves PSNR and SSIM metrics, reduces NIQE and BRISQUE values, and preserves the textural informativeness of anatomical structures. Comparison with classical methods (histogram equalization, CLAHE, bilateral filtering) confirmed the higher efficiency of the proposed approach, which is particularly important for diagnostics in endoscopy, gastroscopy, and dental intraskopy. The obtained results highlight the advantages of the proposed method over baseline approaches in preserving textural information and enhancing local contrast.
The practical significance of the work lies in the possibility of integrating the method into real-time systems to improve diagnostic accuracy and minimize the risk of missed pathologies. The developed method opens up prospects for application in clinical practice, telemedicine, and decision-support systems.
References
F. Liu, et al., “Image Enhancement Techniques for Endoscopic Imaging: A Comprehensive Review,” IEEE Transactions on Medical Imaging, vol. 42, no. 1, pp. 112-130, 2023. https://doi.org/10.1109/TMI.2022.3211234 .
Y. Huang, et al., “Wavelet-Based Denoising for Low-Illumination Medical Images,” Biomedical Signal Processing and Control, vol. 72, pp. 103389, 2022. https://doi.org/10.1016/j.bspc.2021.103389 .
K. Zhang, et al., “Restoration of Medical Images via SwinIR Transformer,” in Proc. CVPR Workshops, 2021, pp. 123-132. [Electronic resource]. Available: https://arxiv.org/abs/2108.10257 .
S. Jain, and A. Kumar, “Comparative Study of CLAHE and Guided Filtering for Contrast Enhancement of Medical Images,” Computers in Biology and Medicine, vol. 141, pp. 105124, 2022. https://doi.org/10.1016/j.compbiomed.2021.105124 .
C. Li, et al., “CycleGAN-Based Endoscopic Image Enhancement for Improved Diagnostic Accuracy,” Medical Image Analysis, vol. 62, pp. 101710, 2020. https://doi.org/10.1016/j.media.2020.101710 .
E. Yavorska, O. Dozorska, and L. Dediv, “The Method of the Main Tone Detection in the Structure of Electromyographic Signals for the Task of Broken Human Communicative Function Compensation,” Visnyk NTUU KPI. Ser. Radiotekhnika Radioaparatobuduvannia, no. 81, pp. 56-64, 2020.
Y. Wang, et al., “Evaluation Metrics for Image Enhancement: A Survey,” IEEE Access, vol. 10, pp. 38152-38172, 2022. https://doi.org/10.1109/ACCESS.2022.3166308 .
G. Kaur, and R. Rani, “Fusion of Bilateral and Wavelet Filters for High-Quality Endoscopic Image Restoration,” Computer Methods and Programs in Biomedicine, vol. 229, pp. 107402, 2023. https://doi.org/10.1016/j.cmpb.2023.107402 .
О. В. Коменчук, і О. Б. Мокін, «Аналіз методів передоброблення панорамних стоматологічних рентгенівських знімків для задач сегментації зображень,» Вісник Вінницького політехнічного інституту, №. 6, с. 48-55, 2022. https://doi.org/10.31649/1997-9266-2023-170-5-41-49 .
О. В. Коменчук, «Адаптивні методи попереднього оброблення для підвищення точності сегментації стоматологічних рентгенівських знімків,» Інформаційні технології та комп’ютерна інженерія, №. 1, с. 23-31, 2023. https://doi.org/10.30837/2522-9818.2024.3.029 .
V. Abramova, S. Krivenko, V. Lukin, and O. Krylova, “Noise Properties Analysis of Dental Images,” Proc. Kharkiv National Medical University, pp. 24-28, 2019, [Electronic resource]. Available: https://repo.knmu.edu.ua/items/a077e359-3f20-46ef-93f5-c0562217ac78 .
N. Piontko, and M. Karpinski, “Segmentation of Partially Blurred Images Using Wavelet Transform,” Computer Data Systems and Networks, no. 7(77), pp. 145-152, 2013. [Electronic resource]. Available: https://science.lpnu.ua/uk/cds-archive/vsi-vypusky/nomer-777-2013/segmentation-partially-blurred-images-using-wavelet-transform .
В. Березюк, і Я. Соколовський, «Покращення медичних МРТ-зображень на підставі фрактальних операторів,» Комп’ютерні науки та інформаційні технології, т. 6, № 2, pp. 111-118, 2024. [Електронний ресурс]. Режим доступу: https://science.lpnu.ua/uk/cds/vsi-vypusky/volume-6-number-2-2024/pokrashchennya-medychnyh-mrt-zobrazhen-na-pidstavi-fraktalnyh .
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
