KLASSIK U-NET MODELIDAN FOYDALANIB TIBBIY ENDOSKOPIK TASVIRLARNI SEGMENTATSIYALASH: CPU VA GPU ORASIDAGI SAMARADORLIK TAHLILI

Yaxshiboev D. S., Jalgasbayeva A. A. & Dilmurodov S. S.


Annotatsiya

Ushbu maqola tibbiy endoskopik tasvir ma’lumotlari asosida klassik U-Net modelining ishlashini tahlil qiladi. Trening va test bosqichlari ikki xil hisoblash muhiti — markaziy protsessor (CPU) va grafik protsessor (GPU) — yordamida amalga oshirildi. Model kichik hajmdagi tasvirlar to‘plamida o‘qitildi, soxta maskalar yordamida segmentatsiya sifat baholandi. Har bir konfiguratsiya uchun o‘qitish vaqti, sekundiga o‘qitilgan namunalar soni, yuklash vaqti, aniqlik va yo‘qotish ko‘rsatkichlari baholandi. Natijalar shuni ko‘rsatdiki, GPUda trening va inferensiya sezilarli darajada tezroq va samaraliroq. Ushbu tadqiqot chuqur o‘rganish modellarining tibbiy tasvirni tahlil qilishdagi ishlashini yaxshilashga qaratilgan.


Adabiyotlar

  1. Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention (MICCAI), 234–241. https://doi.org/10.1007/978-3-319-24574-4_28
  2. Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., ... & Sánchez, C. I. (2017). A Survey on Deep Learning in Medical Image Analysis. Medical Image Analysis, 42, 60–88. https://doi.org/10.1016/j.media.2017.07.005
  3. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
  4. Jha, D., Smedsrud, P. H., Riegler, M. A., Johansen, D., De Lange, T., Halvorsen, P., & Johansen, H. D. (2020). Kvasir-SEG: A Segmented Polyp Dataset. International Conference on Multimedia Modeling, 451–462. https://doi.org/10.1007/978-3-030-37734-2_37
  5. Tajbakhsh, N., Shin, J. Y., Gurudu, S. R., Hurst, R. T., Kendall, C. B., Gotway, M. B., & Liang, J. (2020). Convolutional Neural Networks for Medical Image Analysis: Full Training or Fine Tuning? IEEE Transactions on Medical Imaging, 35(5), 1299–1312. https://doi.org/10.1109/TMI.2016.2535302
  6. Chollet, F. (2017). Deep learning with Python. Manning Publications.
  7. TensorFlow documentation. (n.d.). Retrieved from https://www.tensorflow.org/
  8. NVIDIA CUDA Toolkit documentation. (n.d.). Retrieved from https://developer.nvidia.com/cuda-toolkit
  9. Kirk, D. B., & Hwu, W. W. (2016). Programming massively parallel processors. Morgan Kaufmann.
  10. Bahns, E., Shankar, V., Jung, A., Bordes, F., Urban, G., & Uszkoreit, J. (2017). Aggregate gradient: Cross-replica gradient averaging for distributed data-parallel training. In Advances in neural information processing systems (pp. 1296-1304).