KO‘KRAK QAFASI RENTGEN TASVIRLARI ASOSIDA VIRUSLI PNEVMONIYANI ANIQLOVCHI INTELLEKTUAL TASHXISLASH TIZIMINI ISHLAB CHIQISH

Dildora M. K., Naim N. A. & Mansurova M. Y.


Annotatsiya

Ushbu tadqiqotda ko‘krak qafasi rentgen tasvirlari (CXR) asosida virusli pnevmoniyani avtomatlashtirilgan tarzda aniqlovchi intellektual diagnostika tizimi ishlab chiqildi. Tasvir sifatini yaxshilash uchun CLAHE algoritmi, o‘pka zonalarini ajratish uchun UNet arxitekturasi, tasniflash bosqichida esa CNN–SVM gibrid modeli qo‘llandi. Taklif etilgan yondashuv diagnostika jarayonini avtomatlashtirish, aniqlik va sezgirlikni oshirish hamda radiologlar yuklamasini kamaytirishga xizmat qiladi. Tizimning funksional modeli IDEF0 yordamida rasmiylashtirildi.


Adabiyotlar

  1. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. CVPR.
  2. Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. (2017). Densely connected convolutional networks. CVPR.
  3. Tan, M., & Le, Q. (2019). EfficientNet: Rethinking model scaling for CNNs. ICML.
  4. Nguyen, H. et al. (2021). CNN–SVM hybrid for medical imaging classification. Pattern Recognition.
  5. Ronneberger, O., Fischer, P., Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. MICCAI.
  6. Zhou, Z. et al. (2019). UNet++: A nested U-Net architecture. TMI.
  7. Chen, J. et al. (2021). TransUNet: Transformers make strong encoders for medical image segmentation. ArXiv
  8. Rajpurkar, P. et al. (2017). CheXNet: Radiologist-level pneumonia detection on chest X-rays. arXiv.
  9. Kermany, D. et al. (2018). Identifying pneumonia from chest X-rays using deep learning. Cell.