JBT Journal
Advanced

Raqamli Transformatsiya va Sun’iy Intellekt

U-NET CHUQUR O‘QITISH MODELI YORDAMIDA UMURTQA POG‘ONASINING KOMPYUTER TOMOGRAFIYASI TASVIRLARINI SEGMENTATSIYA QILISH

Nishanov Axram Xasanovich1, Zaripov Fazil Maxsetovic1, Jo‘raqulov Nodirbek Sobirovich1, Qambarov Baxriddin Panji o‘g‘li1

1 Toshkent axborot texnologiyalari universiteti

Zenodo DOI: 10.5281/zenodo.19707377

Keywords

tibbiy tasvirlarni qayta ishlash KT tasvirlari chuqur o‘qitish (deep learning) Jaccard indeksi Dice koeffitsiyenti U-Net umurtqa pog‘onasi segmentatsiyasi

Abstract

Ushbu maqolada umurtqa pog‘onasi tibbiy tasvirlaridan vertebra tuzilmalarini segmentatsiya qilishda U-Net konvolyutsion neyron tarmog‘i asosida semantik segmentatsiya modelini qo‘llash masalasi qaralgan. Kompyuter tomografiyasi (KT) tasvirlaridan umurtqa segmentlarini aniq ajratib olish kasalliklarni erta va ishonchli aniqlashda muhim ahamiyatga ega. U-Net arxitekturasi encoder–decoder tuzilmasi va skip-connection bog‘lanishlari orqali tasvir xususiyatlarini chuqur o‘rganib, yuqori aniqlikdagi segmentatsiya xaritasini hosil qiladi. Tajriba natijalariga ko‘ra, model samaradorligini baholandi va Jaccard indeksi (IoU) metrikasi ko‘rsatkichi 90% va Dice koeffitsiyenti ko‘rsatkichi 92% ni tashkil qildi. Olingan natijalar mazkur modelning boshqa segmentatsiya modellariga nisbatan umurtqa vertebra segmentlarini aniq va ishonchli ajratish imkoyatiga ega ekanligini ko‘rsatadi.

Views: 145 Published: 2026-04-28 Pages: 32-39 Volume: 4 Issue: 2

References

  1. Jaeger S., Candemir S., Antani S., Wang Y., Lu P., Thoma G. Two public chest X-ray datasets for computer-aided screening of pulmonary diseases. Quantitative Imaging in Medicine and Surgery, 2014, vol. 4, no. 6, pp. 475–484.
  2. Shorten C., Khoshgoftaar T. A survey on image data augmentation for deep learning. Journal of Big Data, 2019, vol. 6, no. 1, pp. 60.
  3. World Health Organization. Musculoskeletal conditions. Available: https://www.who.int/news-room/fact-sheets/detail/musculoskeletal-conditions
  4. Models for Accurate Spine Segmentation in CT Scans,” Int. J. Math. Eng. Manag. Sci., vol. 10, no. 6, pp. 2125–2145, 2025, doi: 10.33889/IJMEMS.2025.10.6.099
  5. Loffler, M. T. et al. Improved prediction of incident vertebral fractures using opportunistic QCT compared to DXA. Eur Radiol 29,4980–4989 (2019).
  6. Litjens G., Kooi T., Bejnordi B. E., et al. A survey on deep learning in medical image analysis. Medical Image Analysis, 2017, vol. 42, pp. 60–88.
  7. Shen D., Wu G., Suk H. Deep learning in medical image analysis. Annual Review of Biomedical Engineering, 2017, vol. 19, pp. 221–248.
  8. Doi K. Computer-aided diagnosis in medical imaging: Historical review, current status and future potential. Computerized Medical Imaging and Graphics, 2007, vol. 31, no. 4–5, pp. 198–211.
  9. T. Nemoto et al., “Efficacy evaluation of 2D, 3D U-Net semantic segmentation and atlas-based segmentation of normal lungs excluding the trachea and main bronchi,” J. Radiat. Res., vol. 61, no. 2, pp. 257–264, 2020, doi: 10.1093/jrr/rrz086.\
  10. Ghesu F. C., Georgescu B., Zheng Y., et al. Multi-scale deep reinforcement learning for real-time 3D vertebrae localization in CT images. IEEE Transactions on Medical Imaging, 2017, vol. 36, no. 6, pp. 1264–1274.
  11. M. Arabboev and S. Begmatov, “U-NET BASED POLYP SEGMENTATION ON KVASIR- SEG DATASET: PERFORMANCE EVALUATION AND COMPARISON WITH STATE-OF-THE-ART METHODS,” MUHANDISLIK VA IQTISODIYOT, no. 12, pp. 289–299, 2025, doi: https://doi.org/10.5281/zenodo.17874308.
  12. Suzani A., Seitel A., Rasoulian A., et al. Automatic vertebrae detection and localization in CT images. IEEE Transactions on Medical Imaging, 2015, vol. 34, no. 2, pp. 530–541.
  13. R. Kumar, M. Gupta, and A. Abraham, “A Critical Analysis on Vertebra Identification and Cobb Angle Estimation Using Deep Learning for Scoliosis Detection,” IEEE Access, vol. 12, no. December 2023, pp. 11170–11184, 2024, doi: 10.1109/ACCESS.2024.3353794.
  14. H. Batool et al., “Knowledge Distillation and Transformer-Based Framework for Automatic Spine CT Report Generation,” IEEE Access, vol. 13, no. January, pp. 42949–42964, 2025, doi: 10.1109/ACCESS.2025.3546131.
  15. Korez R., Ibragimov B., Likar B., Pernuš F., Vrtovec T. A framework for automated spine and vertebrae interpolation-based detection and model-based segmentation. IEEE Transactions on Medical Imaging, 2015, vol. 34, no. 8, pp. 1649–1662.
  16. Sekuboyina, A. et al. VerSe: a vertebrae labelling and segmentation benchmark for multi-detector CT images. Med Image Anal 73,102166 (2021)
  17. M. Arabboev and S. Begmatov, “Deep learning-based pneumonia detection from chest X-ray images using a convolutional neural network,” Современные инновации, системы и технологии - Mod. Innov. Syst. Technol., vol. 5, no. 3, pp. 1018–1026, 2025, doi: 10.47813/2782-2818-2025-5-3-1018-1026.
  18. N. Micallef, D. Seychell, and C. J. Bajada, “Exploring the U-Net++ Model for Automatic Brain Tumor Segmentation,” IEEE Access, vol. 9, pp. 125523–125539, 2021, doi: 10.1109/ACCESS.2021.3111131
  19. R. Singh, C. Prabha, M. Malik, and R. K. Lodhi, “Leveraging DeepLabv3+ and U-Net
  20. Ronneberger O., Fischer P., Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI), 2015, pp. 234–241.
  21. Chen L. C., Zhu Y., Papandreou G., Schroff F., Adam H. Encoder–decoder with atrous separable convolution for semantic image segmentation. Proceedings of the European Conference on Computer Vision (ECCV), 2018, pp. 801–818.
  22. S. F. Qadri, L. Shen, M. Ahmad, S. Qadri, S. S. Zareen, and S. Khan, “OP-convNet: A Patch Classification-Based Framework for CT Vertebrae Segmentation,” IEEE Access, vol. 9, pp. 158227–158240, 2021, doi: 10.1109/ACCESS.2021.3131216.
  23. Sekuboyina A., Bayat A., Husseini M. E., et al. VerSe: A vertebrae segmentation challenge. Medical Image Analysis, 2021, vol. 73, 102166.