ENHANCING CORONARY ANGIOGRAPHY IMAGES: A NOVEL HYBRID APPROACH MEAN TOTAL VARIATION FILTER FOR NOISE REDUCTION AND EDGE PRESERVATION

Sarwar Shah Khan; Ali Alferaidi

doi:10.46903/gjms/22.03.1584

ENHANCING CORONARY ANGIOGRAPHY IMAGES: A NOVEL HYBRID APPROACH MEAN TOTAL VARIATION FILTER FOR NOISE REDUCTION AND EDGE PRESERVATION

Sarwar Shah Khan, Ali Alferaidi

Abstract

Background: Angiography is a medical imaging technique that uses X-ray imaging to visualize blood vessels in the body, aiding in the diagnosis of vascular conditions. Coronary angiography is a vital medical procedure that provides detailed images of a patient’s coronary arteries and helps diagnose heart-related conditions. Challenges in coronary angiography involve image noise, which can reduce image quality and make it difficult to identify vascular structures. Additionally, variations in contrast and the presence of artifacts can impact the accuracy of diagnoses. To improve the image quality and enhance the image visibility needed to address the above challenges, this article proposed a novel hybrid approach called the Mean Total Variation Filter (MTVF).

Materials & Methods: The study used an experimental design to assess how well the Mean Total Variation Filter (MTVF) improves the quality of coronary angiography images. The medical images were obtained in a controlled lab setting, where the research was carried out and the subsequent analysis was performed. The study spanned approximately six months, covering the phases of developing the algorithm, acquiring images, and evaluating performance. To select images, a purposive sampling method was employed, focusing on coronary angiography images with various levels of noise and artifacts. This method ensures that the selected images represent common challenges found in clinical practice. Preliminary studies suggested a minimum of 30 images were needed to achieve statistically significant results, ensuring enough test cases to accurately evaluate the proposed algorithm’s performance. The effectiveness of the MTVF approach was measured using several quantitative metrics: Correlation Coefficient (CoC), Peak Signal-to-Noise Ratio (PSNR), Mean Square Error (MSE), and Root Mean Square Error (RMSE). These metrics were chosen to thoroughly assess the algorithm’s capability in reducing noise and enhancing image quality.

Results: The performance of the proposed algorithm was assessed using various parameters for test image 1. The evaluation results indicate a high CoC of 0.9997, an impressive PSNR of 51.01, a low MSE of 1.3020, and a minimal RMSE of 0.0133. These metrics collectively highlight the algorithm’s ability to produce excellent results in enhancing the quality of test image 1, making it a promising technique for noise reduction and image enhancement.

Conclusion: The analysis highlights the outstanding performance of the proposed hybrid MTVF method in removing noise, outperforming current techniques.

Keywords

Medical imaging; De-noise; Image Quality; Mean Filter; Total Variation.

Full Text:

PDF

References

Mustapha MT, Uzun B, Ozsahin DU, Ozsahin I. A comparative study of X-ray based medical imaging devices. In: Applications of Multi-Criteria Decision-Making Theories in Healthcare and Biomedical Engineering. Academic Press; 2021. p. 163-80. https://doi.org/10.1016/B978-0-12-824086-1.00011-6

Haq IU, Chhatwal K, Sanaka K, Xu B. Artificial intelligence in cardiovascular medicine: current insights and future prospects. Vasc Health Risk Manag. 2022;12:517-28. https://doi.org/10.2147/VHRM.S279337

Serruys PW, Hara H, Garg S, Kawashima H, Nørgaard BL, Dweck MR, et al. Coronary computed tomographic angiography for complete assessment of coronary artery disease: JACC state-of-the-art review. J Am Coll Cardiol. 2021;78(7):713-36. https://doi.org/10.1016/j.jacc.2021.06.019

Abdullah, Siddiqi MH, Salamah Alhwaiti Y, Alrashdi I, Ali A, Faisal M. Segmentation and classification of heart angiographic images using machine learning techniques. J Healthc Eng. 2021;2021(1):6666458. https://doi.org/10.1155/2021/6666458

Hsu JC, Nieves LM, Betzer O, Sadan T, Noël PB, Popovtzer R, Cormode DP. Nanoparticle contrast agents for X-ray imaging applications. Wiley Interdiscip Rev Nanomed Nanobiotechnol. 2020;12(6). https://doi.org/10.1002/wnan.1642

Aslam MA, Munir MA, Cui D. Noise removal from medical images using hybrid filters of technique. J Phys Conf Ser. 2020;1518(1):012061. https://doi.org/10.1088/1742-6596/1518/1/012061

Balasamy K, Shamia D. Feature extraction-based medical image watermarking using fuzzy-based median filter. IETE J Res. 2023;69(1):83-91. https://doi.org/10.1080/03772063.2021.1893231

Verma K, Singh BK, Thoke AS. An enhancement in adaptive median filter for edge preservation. Procedia Comput Sci. 2015;48:29-36. https://doi.org/10.1016/j.procs.2015.04.106

Ning CY, Liu SF, Qu M. Research on removing noise in medical image based on median filter method. In: 2009 IEEE International Symposium on IT in Medicine & Education; 2009. p. 384-8. https://doi.org/10.1109/ITIME.2009.5236393

Sagar P, Upadhyaya A, Mishra SK, Pandey RN, Sahu SS, Panda G. A circular adaptive median filter for salt and pepper noise suppression from MRI images. J Sci Ind Res. 2020;79(10):43588. https://doi.org/10.56042/jsir.v79i10.43588

Arulpandy P, Pricilla MT. Speckle noise reduction and image segmentation based on a modified mean filter. Comput Assist Methods Eng Sci. 2020;27(4):221-39. https://doi.org/10.24423/cames.290

Kalaiyarasi M, Janaki R, Sampath A, Ganage D, Chincholkar YD, Budaraju S. Non-additive noise reduction in medical images using bilateral filtering and modular neural networks. Soft Comput. 2023:1-0. https://doi.org/10.1007/s00500-023-08968-2

Bhonsle D, Rizvi T, Mishra S, Sinha GR, Kumar A, Jain VK. Reduction of ultrasound images using combined bilateral filter & median modified Wiener filter. In: 2022 Second International Conference on Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT); 2022. p. 1-5. https://doi.org/10.1109/ICAECT54875.2022.9807906

Radhika R, Mahajan R. An adaptive optimum weighted mean filter and bilateral filter for noise removal in cardiac MRI images. Meas Sens. 2023;29:100880. https://doi.org/10.1016/j.measen.2023.100880

Zahro UM, Anam C, Budi WS, Triadyaksa P, Saragih JH, Rukmana DA. Investigation of noise level and spatial resolution of CT images filtered with a selective mean filter and its comparison to an adaptive statistical iterative reconstruction. Iran J Med Phys. 2021;18(5):376-83.

Tan Z, Yang H. Total variation regularized multi-matrices weighted Schatten p-norm minimization for image denoising. Appl Math Model. 2023;124:518-31. https://doi.org/10.1016/j.apm.2023.08.002

Kaur R, Kaur S. Comparison of contrast enhancement techniques for medical image. In: 2016 conference on emerging devices and smart systems (ICEDSS); 2016. p. 155-9. https://doi.org/10.1109/ICEDSS.2016.7587782

Khan SS, Khan M, Alharbi Y, Haider U, Ullah K, Haider S. Hybrid sharpening transformation approach for multifocus image fusion using medical and nonmedical images. J Healthc Eng. 2021;2021:7000991. https://doi.org/10.1155/2021/7000991

Khan SS, Khan M, Alharbi Y. Multifocus image fusion using image enhancement techniques with wavelet transformation. Int J Adv Comput Sci Appl. 2020;11(5). https://doi.org/10.14569/IJACSA.2020.0110555

Khan SS, Ran Q, Khan M. Image pan-sharpening using enhancement based approaches in remote sensing. Multimed Tools Appl. 2020;79(43):32791-805. https://doi.org/10.1007/s11042-020-09682-z

Khan SS, Ran Q, Khan M, Ji Z. Pan-sharpening framework based on laplacian sharpening with Brovey. In: 2019 IEEE International Conference on Signal, Information and Data Processing (ICSIDP); 2019. p. 1-5. https://doi.org/10.1109/ICSIDP47821.2019.9173129

Khan SS, Khan M, Ran Q. Multi-focus color image fusion using laplacian filter and discrete fourier transformation with qualitative error image metrics. In: Proceedings of the 2nd International Conference on Control and Computer Vision; 2019. p. 41-5. https://doi.org/10.1145/3341016.3341019

Shah M, Khan M, Khan SS, Ali S. Multi-Focus Image Fusion using Unsharp Masking with Discrete Cosine Transform. In: 2023. p. 1-5.

Danyal MM, Khan SS, Khan RS, Jan S, ur Rahman N. Enhancing multi-modality medical imaging: A novel approach with laplacian filter+ Discrete Fourier Transform pre-processing and stationary wavelet transform fusion. J Image Med Healthc. 2024;2(2):35-53. https://doi.org/10.32604/jimh.2024.051340

DOI: https://doi.org/10.46903/gjms/22.03.1584