SUN’IY INTELLEKT TIZIMLARIDA CHUQUR O‘RGANISH USULLARINING QO‘LLANILISHI VA ULARNING AMALIY MUAMMOLARNI HAL ETISHDAGI ROLI
Keywords:
U-net, MRT, segmentlash, Dice, ReLU, CNN, neyron tarmoqAbstract
Ushbu tadqiqot sun’iy intellekt sohasidagi chuqur o‘rganish modellaridan biri bo‘lgan U-net modeli asosida tibbiy tasvirlarda xususan bosh miya magnit-rezonans tomografiya(MRT) tasvirlarida o‘simtalarni avtomatik segmentlash va modelning samaradorligini o‘rganishga qaratilgan. Tadqiqotda U-net modeli yordamida ma’lumotlar to‘plamidagi turli MRT tasvirlaridan o‘simta ajratib olindi. Natijalar modelning yuqori Dice koeffitsienti 82.06% ni tashkil etgan holda va boshqa baholash metrikalarida an’anaviy usullarga nisbatan ustunligini ko‘rsatdi, bu esa klinik amaliyotda tashxislash sifatini oshirish salohiyatiga ega ekamligidan dalolat beradi.
References
1. Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015) (pp. 234–241). Springer. http://lmb.informatik.uni-freiburg.de/
2. Kumar, J., Dalal, N., & Sethi, M. (2024). Hyperparameters in deep learning: A comprehensive review. International Journal of Intelligent Systems and Applications in Engineering, 12(1), 1–18. https://ijisae.org/index.php/IJISAE/article/view/6967
3. Taha, A. A., & Hanbury, A. (2015). Metrics for evaluating 3D medical image segmentation: Analysis, selection, and tool. BMC Medical Imaging, 15, Article 29. https://doi.org/10.1186/s12880-015-0068-x
4. Luo, G., An, P., Ji, Z., Chen, Y., & Li, M. (2022). Post-processing for medical image segmentation: A review. Frontiers in Biomedical Technologies, 9(3), 15–28. https://doi.org/10.3389/fbioe.2022.869542
5. Ito Aramendia, A. (n.d.). Decoding the U-Net: A complete guide. Medium. https://medium.com/@alejandro.itoaramendia/decoding-the-u-net-a-complete-guide-810b1c6d56d8
6. Terven, J. R., Córdova-Esparza, D. M., Ramírez-Pedraza, A., & Chávez-Urbiola, E. A. (2023). Loss functions and metrics in deep learning: A review (arXiv:2307.02694v1). arXiv. https://doi.org/10.48550/arXiv.2307.02694
