An Adaptive Edge-Preserving Type-2 Fuzzy Filter for Medical Image Denoising: Performance Comparison with Traditional Methods

Öz

Reducing noise in medical imaging is essential to improve quality and diagnostic accuracy. Gaussian noise, common in MRI and X-ray images, reduces clarity and obscures pathological structures. Traditional denoising methods often fail to preserve edge details, leading to the loss of important anatomical information. To address this, an Adaptive Edge-Preserving Type-2 Fuzzy Filter is developed, aiming to reduce Gaussian noise while maintaining edge integrity. The proposed method integrates an adaptive mechanism into classical Type-2 Fuzzy Filtering, adjusting filtering parameters dynamically based on edge strength. This enables effective noise removal in both homogeneous and edge-rich regions. The performance of the methods was evaluated on real medical image datasets under varying noise levels and compared with Mean, Median, Fuzzy, and classical Type-2 Fuzzy Filtering methods. Results demonstrate superior performance in terms of Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM), providing a robust solution for improving medical image quality.

Anahtar Kelimeler

• Image Noise Reduction
• Adaptive Filtering
• Type-2 Fuzzy Filter
• Edge Preservation
• Medical Imaging.

Tıbbi Görüntü Gürültü Giderimi için Uyarlamalı Kenar-Koruyucu Tip-2 Bulanık Filtre: Geleneksel Yöntemlerle Performans Karşılaştırması

Öz

Tıbbi görüntülerdeki gürültünün azaltılması, görüntü kalitesinin ve tanısal doğruluğun artırılması açısından büyük önem taşımaktadır. Manyetik Rezonans (MR) ve X-ışını görüntülerinde yaygın olarak karşılaşılan Gauss gürültüsü, görüntü netliğini azaltmakta ve patolojik yapıları gizlemektedir. Geleneksel gürültü giderme yöntemleri, çoğu zaman kenar detaylarını korumakta yetersiz kalmakta ve bu durum önemli anatomik bilgilerin kaybına yol açmaktadır. Bu sorunu gidermek amacıyla, kenar bütünlüğünü koruyarak Gauss gürültüsünü azaltmayı hedefleyen Uyarlanabilir Kenar Koruyucu Tip-2 Bulanık Filtre geliştirilmiştir. Önerilen yöntem, klasik Tip-2 Bulanık Filtreleme tekniğine adaptif bir mekanizma entegre ederek, filtreleme parametrelerini kenar kuvvetine göre dinamik olarak ayarlamaktadır. Bu sayede hem homojen hem de kenar açısından zengin bölgelerde etkili bir gürültü giderimi sağlanmaktadır. Yöntemin performansı, farklı gürültü seviyelerinde gerçek tıbbi görüntü veri kümeleri üzerinde test edilmiş ve Ortalama, Medyan, Bulanık ve klasik Tip-2 Bulanık Filtreleme yöntemleri ile karşılaştırılmıştır. Elde edilen sonuçlar, Tepe Sinyal-Gürültü Oranı (PSNR) ve Yapısal Benzerlik İndeksi (SSIM) açısından üstün bir performans ortaya koymuş ve tıbbi görüntü kalitesini artırmak için sağlam bir çözüm sunduğunu göstermiştir.

Anahtar Kelimeler

• Görüntü Gürültüsü Azaltımı
• Uyarlanabilir Filtreleme
• Tip-2 Bulanık Filtre
• Kenar Koruma
• Tıbbi Görüntüleme.

Kaynakça

1. Al-Kadi, O.S., 2010. Assessment of texture measures susceptibility to noise in conventional and contrast enhanced computed tomography lung tumour images. Computerized Medical Imaging and Graphics, 34(6), 494–503.
2. Beinecke, J., Heider, D., 2021. Gaussian noise up-sampling is better suited than SMOTE and ADASYN for clinical decision making. BioData Mining, 14(1), 49.
3. Brown, M., 2024. Image processing in medicine: revolutionizing healthcare. Perspective, Imaging Medicine, 16(6).
4. Buades, A., Coll, B., Morel, J.M., 2005. A non-local algorithm for image denoising. Proc. of IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), 2, 60–65.
5. Donoho, D.L., 2002. De-noising by soft-thresholding. IEEE Transactions on Information Theory, 41(3), 613–627.
6. Gonzalez, R.C., 2009. Digital image processing, Pearson Education India, City.
7. Gonzalez, R.C., Woods, R.E., 2018. Digital image processing, 4th ed., Pearson Education, London.
8. Khanesar, M.A., Kayacan, E., Teshnehlab, M., Kaynak, O., 2011. Extended Kalman filter based learning algorithm for type-2 fuzzy logic systems and its experimental evaluation. IEEE Transactions on Industrial Electronics, 59(11), 4443–4455.

9. Krishnan, M., Viswanathan, R., 2013. A new concept of reduction of Gaussian noise in images based on fuzzy logic. Applied Mathematical Sciences, 7, 595–602.
10. Kumar, A., Kumar, S., Kar, A., 2024. Improved adaptive type-2 fuzzy detection and simple linear regression-based filter for removing salt & pepper noise. Circuits, Systems, and Signal Processing, 43(12), 7781–7819.
11. Kusk, M.W., Lysdahlgaard, S., 2023. The effect of Gaussian noise on pneumonia detection on chest radiographs, using convolutional neural networks. Radiography, 29(1), 38–43.
12. Lee, C.S., Kuo, Y.H., Yu, P.T., 1997. Weighted fuzzy mean filters for image processing. Fuzzy Sets and Systems, 89(2), 157–180.
13. Liang, Q., Mendel, J.M., 2000. Equalization of nonlinear time-varying channels using type-2 fuzzy adaptive filters. IEEE Transactions on Fuzzy Systems, 8(5), 551–563.
14. Mallat, S.G., 1989. A theory for multiresolution signal decomposition: The wavelet representation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 11(7), 674–693.
15. Maxim, V., Şendur, L., Fadili, J., Suckling, J., Gould, R., Howard, R., Bullmore, E., 2005. Fractional Gaussian noise, functional MRI and Alzheimer's disease. NeuroImage, 25(1), 141–158.
16. Mvd, A., 2019. Medical MNIST [Data set]. Kaggle. https://www.kaggle.com/datasets/andrewmvd/medical-mnist (Accessed: 13 January 2025).
17. Saini, A., Dogra, A., Kukreja, V., 2025. From spatial domain to learning based methods: A survey on MRI and HRCT image denoising methods. Biomedical and Pharmacology Journal, 18(3), 1801–1823.
18. Seddik, H., Braiek, E., 2012. Efficient noise removing based optimized smart dynamic Gaussian filter. International Journal of Computer Applications, 51(5), 1–13.
19. Senalp, F.M., 2023. A New Super Resolution Approach for Face Images and the Effects of the Datasets of Different Image Quality on the Success Performance. Journal of Engineering Science and Researches, 5(1), 1–8.
20. Sharma, T., Verma, N.K., 2021. Adaptive interval type-2 fuzzy filter: An AI agent for handling uncertainties to preserve image naturalness. IEEE Transactions on Artificial Intelligence, 2(1), 83–92.
21. Singh, V., Agrawal, P., Sharma, T., Verma, N.K., 2023. Improved adaptive type-2 fuzzy filter with exclusively two fuzzy membership function for filtering salt and pepper noise. Multimedia Tools and Applications, 82(13), 20015–20037.
22. Singh, V., Pal, V.C., Pati, A., 2024. Adaptive type-2 fuzzy filter with kernel density estimation for impulse noise removal. IEEE Transactions on Fuzzy Systems.
23. Tunç, A., Tasdemir, S., Koklu, M., Cinar, A.C., 2022. Age group and gender classification using convolutional neural networks with a fuzzy logic-based filter method for noise reduction. Journal of Intelligent & Fuzzy Systems, 42(1), 491–501.
24. Vautrot, P., Herbin, M., Hussenet, L., 2011. A fuzzy scheme for image noise reduction. International Conference on Fuzzy Computation Theory and Applications (FCTA), Vol. 2, October 2011, SCITEPRESS, pp. 441–445.
25. Virtue, P., Lustig, M., 2017. The empirical effect of Gaussian noise in undersampled MRI reconstruction. Tomography, 3(4), 211.
26. Yuksel, M.E., Basturk, A., 2012. Application of type-2 fuzzy logic filtering to reduce noise in color images. IEEE Computational Intelligence Magazine, 7(3), 25–35.