METHODS AND METRICS FOR MONITORING AND IMROVING THE QUALITY OF MRI DIAGNOSTICS
DOI:
https://doi.org/10.24867/31RB03TomasevicKeywords:
MRI, noise reduction, wavelet method, NLM method, anisotropic diffusion, PSNR, SSIM, MAE, MSE, SNR, segmentation, DSCAbstract
The application of noise reduction methods, such as wavelet, NLM method and anisotropic diffusion, aimed at improving the quality of MRI diagnostics and preparing for more precise segmentation of glandular and adipose breast tissue. The effectiveness of the applied methods was analyzed using various evaluation metrics.
References
[1] World Health Organization: "Breast cancer"
[2] Ahmet Hakan Tunçay: "Realistic Microwave Breast Models Through T1-Weighted 3-D MRI Data", 2019
[3] Poonam Jaglan, Rajeshwar Dass, Manoj Duhan: "Detection of Breast Cancer using MRI: A Pictorial Essay of the Image Processing Techniques," International Journal of Computer Engineering In Research Trends, 2019
[4] Sachin D. Ruikar, Dharmpal D. Doye: "Wavelet Based Image Denoising Technique," International Journal of Advanced Computer Science and Applications, 2011
[5] Damini: "Denoising MRI images using NLM filter," International Journal of Computer Sciences and Engineering, 2019
[6] Shahare, N., & Yadav, D. M. Filtering Method for Preprocessing Mammogram Images for Breast Cancer Detection. International Journal of Engineering and Advanced Technology, 2019
[7] Caixia Liu, Li Zhang: "A Novel Denoising Algorithm Based on Wavelet and Non-Local Moment Mean Filtering," Electronics, 2023
[8] F. S. Jorgensen, “Segmentation of male abdominal fat using MRI,” Mas ter’s thesis, Dept. Informat. Math. Modelling, Tech. Univ. Denmark, Kongens Lyngby, Denmark, 2006
[9] Podobnik, G., & Vrtovec, T. Metrics for Biomedical Segmentation, 2024
[10] Scikit-learn Documentation on Hyperparameter Tuning
