BIPOLYAR NORAVSHAN TO‘PLAMLAR ASOSIDA MRT MIYA TASVIRIGA DASTLABKI ISHLOV BERISH ALGORITMI
Keywords:
bipolyar noravshan to‘plam, MRT tasviri, Rician shovqin, dastlabki ishlov berish, defuzzifikatsiya, segmentatsiya, tibbiy informatika.Abstract
Maqolada bipolyar noravshan to‘plamlar (bipolar fuzzy sets) nazariyasiga asoslangan MRT miya tasvirlariga dastlabki ishlov berishning yangi algoritmi — BiFMRI taklif etiladi. Algoritmda pikselning «foydali signalga tegishlilik» (μ⁺) va «shovqinga tegishlilik» (μ⁻) darajalari bir vaqtda modellashtiriladi va mahalliy gradient hamda dispersiya statistikalariga bog‘liq adaptiv parametrlash mexanizmi qo‘llaniladi. IXI, BraTS-2023 va BrainWeb to‘plamlarida olingan natijalar BiFMRI ning klassik usullardan PSNR bo‘yicha 4.2–5.4 dB, klassik noravshan filtrlardan 2.1–2.4 dB ustunligini ko‘rsatdi (PSNR = 33.86 dB, SSIM = 0.923). U-Net asosidagi segmentatsiya Dice koeffitsienti 8.2– 11.8% ga oshdi, Hausdorff masofasi 25.8% ga kamaydi
References
1. Gudbjartsson H., Patz S. The Rician distribution of noisy MRI data // Magnetic
Resonance in Medicine. — 1995. — Vol. 34, № 6. — P. 910–914.
2. Zhang W.-R. Bipolar fuzzy sets and relations: a computational framework for
cognitive modeling and multiagent decision analysis // Proc. IEEE Conf. on
Fuzzy Information Processing Society. — 1994. — P. 305–309.
3. Menze B.H., Jakab A., Bauer S., et al. The multimodal brain tumor image
segmentation benchmark (BRATS) // IEEE Transactions on Medical Imaging.
— 2015. — Vol. 34, № 10. — P. 1993–2024.
4. Ronneberger O., Fischer P., Brox T. U-Net: convolutional networks for
biomedical image segmentation // MICCAI. — 2015. — P. 234–241.
5. Wang Z., Bovik A.C., Sheikh H.R., Simoncelli E.P. Image quality assessment:
from error visibility to structural similarity // IEEE Transactions on Image
Processing. — 2004. — Vol. 13, № 4. — P. 600–612.