TIBBIY TASVIRLARNI TAHLIL QILISH USUL VA ALGORITMLARI
Kalit so‘zlar:
Segmentatsiya algoritmlari, tasniflash, chuqur o‘qitish, convolutional Neural Networks (CNN), U-Net, thresholding, Watershed algoritmi.Annotatsiya
Mazkur ishda buyrak kasalliklarini erta aniqlashda tibbiy tasvirlarni tahlil
qilishni zamonaviy yondashuvlari tahlil qilingan bo’lib, unda KT, MRT va ultratovush tasvirlari
asosida buyrakdagi o‘simta, tosh va boshqa patologik holatlarni aniqlashda segmentatsiya va
tasniflash algoritmlarini o‘rni tadqiq etilgan. Ayniqsa, CNN va U-Net kabi chuqur o‘qitish
modellarini yuqori aniqlikka ega ekanligi ta’kidlangan. Tadqiqot so‘ngida algoritmlarni qiyosiy
tahlili keltirilgan.
Manbalar
Zhou S.K. et al. UNet: Hybrid Deep Learning for Automated Kidney Tumor Segmentation // Medical Image Analysis. – 2017. – Vol. 39. – P. 212–221. – DOI: 10.1016/j.media.2017.07.004.
Litjens G. et al. A Survey of Deep Learning in Medical Image Analysis // Medical Image Analysis. – 2017. – Vol. 42. – P. 60–88. – DOI: 10.1016/j.media.2017.07.005.
Esteva A. et al. Dermatologist-Level Classification of Skin Cancer with Deep Neural Networks // Nature. – 2017. – Vol. 542, No. 7639. – P. 115–118. – DOI: 10.1038/nature21056.
Goodfellow I. et al. Generative Adversarial Nets // Advances in Neural Information Processing Systems (NeurIPS). – 2014. – Vol. 27.
Xu Y. et al. Automated Kidney Tumor Segmentation and Classification Using Deep Learning: A Review // Computers in Biology and Medicine. – 2020. – Vol. 122. – Article 103803. – DOI: 10.1016/j.compbiomed.2020.103803.
Ronneberger O. et al. U-Net: Convolutional Networks for Biomedical Image Segmentation // Medical Image Computing and Computer-Assisted Intervention (MICCAI 2015). – 2015. – P. 234–241. – DOI: 10.1007/978-3-319-24574-4_28.
Rakhlin A. et al. Kidney Tumor Detection Using Deep Learning-Based Segmentation and Classification // Medical Imaging and Health Informatics. – 2017. – Vol. 6, No. 3. – P. 23–35.