MANYETIK REZONANS GÖRÜNTÜLEMEDE GÜRÜLTÜ GIDERME IÇIN 3D DERIN ÖĞRENME MODELI

Abstract

Manyetik Rezonans Görüntüleme (MRI), beyin dokularını incelemek ve çeşitli durumları teşhis etmek için yaygın olarak kullanılan bir görüntüleme tekniğidir. Ancak, MRI görüntüleri genellikle cihaz kısıtlamaları, çevre koşulları, hasta hareketi ve manyetik alan girişimi gibi faktörlerin neden olduğu gürültüleri içerir. Bu gürültü kritik ayrıntıları gizleyebilir ve doğru tanı ve tedavi planlamasını zorlaştırabilir. Bu çalışmada, MRI görüntülerinden Rician gürültüsünün giderilmesine odaklanılmıştır. Bu zorluğun üstesinden gelmek için M-UNet+ResNet ve M-UNet+DenseNet adlı iki 3B otokodlayıcı modeli geliştirilmiştir. Bu modeller, gürültü azaltma yeteneklerini iyileştirmeyi amaçlayan yoğun ve kalıntı bağlantıları entegre edilerek geliştirilmiş bir UNet mimarisine dayanmaktadır. Modeller, %3 ila %15 arasında değişen gürültü seviyelerine sahip IXI veri setinden T1 ve T2 ağırlıklı MRI görüntüleri üzerinde eğitilmiştir. Modellerin performansları, tepe sinyal-gürültü oranı, yapısal benzerlik indeksi ölçümü ve ortalama mutlak hata gibi ölçütler kullanılarak değerlendirilmiştir. Sonuçlar, her iki modelin de çeşitli seviyelerde gürültüyü etkili bir şekilde azalttığını ve M-UNet+ResNet'in genel olarak M-UNet+DenseNet'ten daha iyi performans gösterdiğini göstermiştir. Özellikle, M-UNet+ResNet, IXI-HH-T2 ve IXI-Guys-T2 veri setlerinde sırasıyla 38,72 dB ve 37,04 dB PSNR değerlerine ve 0,82 ve 0,81 SSIM değerlerine ulaşmış olup, bu da modelin görüntü kalitesini korumadaki güçlü kabiliyetini göstermektedir. Bu çalışma, DL modellerine kalıntı bağlantılar eklemenin, MRI görüntülerinden gürültüyü giderme yeteneklerini ve klinik ortamlarda tıbbi görüntülerin bütünlüğünü korumak için bir çözüm sunduğu sonucuna varmıştır.

Keywords

• Gürültü giderimi
• Manyetik rezonans görüntüleme
• Derin öğrenme
• Artık bağlantı
• UNet

NOISE REMOVAL IN MAGNETIC RESONANCE IMAGING USING 3D DEEP LEARNING MODEL

Abstract

Magnetic Resonance Imaging (MRI) is a widely used imaging technique for examining brain tissues and diagnosing various conditions. However, MRI images often contain noise caused by factors such as equipment limitations, environmental conditions, patient movement, and magnetic field interference. This noise can obscure critical details, making accurate diagnosis and treatment planning challenging. In this study, the focus is on the removal of Rician noise from MRI images. To address this challenge, two 3D autoencoder models, named M-UNet+ResNet and M-UNet+DenseNet, were developed. These models are based on an enhanced UNet architecture that integrates dense and residual connections, aimed at improving noise reduction capabilities. The models were trained using T1 and T2-weighted MRI images from the IXI dataset, incorporating noise levels varying from 3% to 15%. Their performance was evaluated using metrics such as peak signal-to-noise ratio, structural similarity index measure, and mean absolute error. The results demonstrated that both models effectively reduced noise across various levels, with M-UNet+ResNet generally outperforming M-UNet+DenseNet. Notably, M-UNet+ResNet achieved PSNR values of 38.72 dB and 37.04 dB, and SSIM values of 0.82 and 0.81 in the IXI-HH-T2 and IXI-Guys-T2 datasets, respectively, indicating its strong capability in preserving image quality. This study concludes that incorporating residual connections in DL models enhances their ability to remove noise from MRI images, offering a solution for maintaining the integrity of medical images in clinical settings.

Keywords

• Noise removal
• Magnetic resonance imaging
• Deep learning
• Residual connection
• UNet

References

1. Oyar, O., “Magnetik Rezonans Görüntüleme MRG’nin klinik uygulamaları ve endikasyonları”, Harran Üniversitesi Tıp Fakültesi Dergisi, Vol. 5, No. 2, 31-40, 2008.
2. Gürkahraman, K., and Karakiş, R., “Brain tumors classification with deep learning using data augmentation”, Journal of the Faculty of Engineering and Architecture of Gazi University, Vol. 36, No. 2, 997-1011, 2021.
3. Yapıcı, M., Karakış, R., and Gürkahraman, K., “Improving brain tumor classification with deep learning using synthetic data”, Computers, Materials and Continua, Vol. 74, No. 3, 2023.
4. Karakis, R., Gurkahraman, K., Mitsis, G. D., Boudrias, M. H., “Deep learning prediction of motor performance in stroke individuals using neuroimaging data”, Journal of Biomedical Informatics, Vol. 141, article id: 104357, 2023.
5. Tian, C., Fei, L., Zheng, W., Xu, Y., Zuo, W., Lin, C. W.,”Deep learning on image denoising: An overview”, Neural Networks, Vol. 131, 251-275, 2020.
6. Buades, A., Coll, B., Morel, J. M., “A review of image denoising algorithms, with a new one”. Multiscale modeling & simulation, Vol. 4, No. 2, 490-530, 2005.
7. Dabov, K., Foi, A., Katkovnik, V., Egiazarian, K. “Image denoising by sparse 3-D transform-domain collaborative filtering”, IEEE Transactions on image processing, Vol. 16, No. 8, 2080-2095, 2007.
8. Manjón, J. V., Carbonell-Caballero, J., Lull, J. J., García-Martí, G., Martí-Bonmatí, L., Robles, M., “MRI denoising using non-local means”, Medical image analysis, Vol. 12, No. 4, 514-523, 2008.

9. Krissian, K., and Aja-Fernández, S., “Noise-driven anisotropic diffusion filtering of MRI”, IEEE transactions on image processing, Vol. 18, No. 10, 2265-2274, 2009.
10. Perona, P., and Malik, J., “Scale-space and edge detection using anisotropic diffusion”, IEEE Transactions on pattern analysis and machine intelligence, Vol. 12, No. 7, 629-639, 1990.
11. Patil, R., and Bhosale, S., “Medical Image Denoising Techniques: A Review”, International Journal on Engineering, Science and Technology (IJonEST), Vol. 4, No. 1, 21-33, 2022.
12. Lundervold, A. S., and Lundervold, A. “An overview of deep learning in medical imaging focusing on MRI”, Zeitschrift für Medizinische Physik, Vol. 29, No. 2, 102-127, 2019.
13. Ilesanmi, A. E., and Ilesanmi, T. O., “Methods for image denoising using convolutional neural network: a review”, Complex & Intelligent Systems, Vol. 7, No. 5, 2179-2198, 2021.
14. Zhang, K., Zuo, W., Chen, Y., Meng, D., Zhang, L., “Beyond a gaussian denoiser: Residual learning of deep cnn for image Denoising”, IEEE Transactions on Image Processing, Vol. 26, No. 7, 3142-3155, 2017.
15. Jiang, D., Dou, W., Vosters, L., Xu, X., Sun, Y., Tan, T., “Denoising of 3D magnetic resonance images with multi-channel residual learning of convolutional neural network”, Japanese journal of radiology, Vol. 36, No. 9, 566-574, 2018.
16. Li, S., Zhou, J., Liang, D., & Liu, Q., “MRI denoising using progressively distribution-based neural network”, Magnetic resonance imaging, Vol. 71, 55-68, 2020.
17. Wu, L., Hu, S., Liu, C., “Denoising of 3D Brain MR images with parallel residual learning of convolutional neural network using global and local feature extraction”, Computational Intelligence and Neuroscience, Vol. 2021, article id: 5577956, 1-18, 2021.
18. Li, Y., Zhang, K., Shi, W., Miao, Y., Jiang, Z., “A Novel Medical Image Denoising Method Based on Conditional Generative Adversarial Network”, Computational and Mathematical Methods in Medicine, Vol. 2021, article id: 9974017, 1-11, 2021.
19. Ran, M., Hu, J., Chen, Y., Chen, H., Sun, H., Zhou, J., Zhang, Y., “Denoising of 3D magnetic resonance images using a residual encoder–decoder Wasserstein generative adversarial network”, Medical image analysis, Vol. 55, 165-180, 2019.
20. Gondara, L., “Medical image denoising using convolutional denoising autoencoders”, 2016 IEEE 16th international conference on data mining workshops (ICDMW), 241-246, 2016.
21. Bermudez, C., Plassard, A. J., Davis, L. T., Newton, A. T., Resnick, S. M., Landman, B. A., “Learning implicit brain MRI manifolds with deep learning”, In Medical Imaging 2018: Image Processing- SPIE, 10574, 408-414, 2018.
22. Tripathi, P. C., and Bag, S., “CNN-DMRI: a convolutional neural network for denoising of magnetic resonance images”, Pattern Recognition Letters, Vol. 135, 57-63, 2020.
23. Yang, H., Zhang, S., Han, X., Zhao, B., Ren, Y., Sheng, Y., Zhang, X. Y., “Denoising of 3D MR images using a voxel-wise hybrid residual MLP-CNN model to improve small lesion diagnostic confidence”, In International Conference on Medical Image Computing and Computer-Assisted Intervention, Springer, Cham, 292-302, 2022.
24. Savaji, S., and Arora, P., “Denoising of MRI images using thresholding techniques through wavelet”, International Journal of Innovative Science, Engineering & Technology, Vol. 1, No. 7, 422-427, 2014.
25. Coupé, P., Manjón, J. V., Gedamu, E., Arnold, D., Robles, M., Collins, D. L. “Robust Rician noise estimation for MR images”, Medical image analysis, Vol. 14, No. 4, 483-493, 2010.
26. Gudbjartsson, H., and Patz, S., “The Rician distribution of noisy MRI data”, Magnetic resonance in medicine, Vol. 34, No. 6, 910-914, 1995.
27. Ronneberger, O., Fischer, P., Brox, T., “U-net: Convolutional networks for biomedical image segmentation”, In Medical Image Computing and Computer-Assisted Intervention–MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18, Springer International Publishing, 234-241, 2015.
28. Topdağ, T., “Beyin görüntülerindeki gürültülerin derin öğrenme kullanılarak giderilmesi”, Yüksek Lisans Tezi, Sivas Cumhuriyet Üniversitesi Fen Bilimleri Enstitüsü, Sivas, 2023.
29. He, K., Zhang, X., Ren, S., Sun, J., “Deep residual learning for image recognition”, In Proceedings of the IEEE conference on computer vision and pattern recognition, 770-778, 2016.
30. Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q., “Densely connected convolutional networks”, In Proceedings of the IEEE conference on computer vision and pattern recognition, 4700-4708, 2017.
31. Targ, S., Almeida, D., Lyman, K., “Resnet in resnet: Generalizing residual architectures”, arXiv preprint, arXiv:1603.08029, 2016.
32. Gurkahraman, K., and Daşgın, Ç., “Brain Extraction from Magnetic Resonance Images Using UNet modified with Residual and Dense Layers”, Türk Doğa ve Fen Dergisi, Vol. 12, No. 3, 144-151, 2023.
33. Savaş, S., “Detecting the stages of Alzheimer’s disease with pre-trained deep learning architectures”, Arabian Journal for Science and Engineering, Vol. 47, No. 2, 2201-2218, 2022.
34. Savaş, S., and Damar, Ç., “Transfer‐learning‐based classification of pathological brain magnetic resonance images”, ETRI Journal, Vol. 46, No. 2, 263-276, 2024.
35. Alhatemi, R. A. J., and Savaş, S., “A weighted ensemble approach with multiple pre-trained deep learning models for classification of stroke”, Medinformatics, Vol. 1, No. 1, 10-19, 2024.
36. Maggioni, M., Katkovnik, V., Egiazarian, K., Foi, A., “Nonlocal transform-domain filter for volumetric data denoising and reconstruction”, IEEE transactions on image processing, Vol. 22, No. 1, 119-133, 2012.