JBT Journal
Advanced

Raqamli Transformatsiya va Sun’iy Intellekt

ANNOTATSIYASI KAM SHAROITLARDA KO‘P TILLI MAMMOGRAFIK O‘CHOQLARNI ANIQLASH UCHUN YOPIQ HALQALI TIZIM: RADIOLOG-INSON-HAMKORLIGI BILAN MATNGA YO‘NALTIRILGAN ZAIF NAZORATLI O‘QITISH

Khamdamov Rustam1, Turaqulov Shoxrux Xudayarovich1

1 Raqamli texnologiyalar va sun’iy intellektni rivojlantirish ilmiy-tadqiqot instituti

Zenodo DOI: 10.5281/zenodo.20816862

Keywords

FCOS ko‘krak bezi saratonini aniqlash FiLM zaif nazoratli o‘qitish radiolog-inson-hamkorligi multimodal chuqur o‘rganish kam resursli tibbiy tasvirlash ko‘p tilli tabiiy tilni qayta ishlash kod almashinuvli klinik matn. Mammografiya

Abstract

Mammografiyada ko‘krak bezi saratonini kompyuter yordamida aniqlash (CAD) tibbiy tasvirlash uchun sun’iy intellekt sohasidagi eng ko‘p o‘rganilgan vazifalardan biri bo‘lib qoldi, biroq past va o‘rta daromadli mamlakatlardagi shifoxonalarda amaliy joriy etish uchta o‘tkir muammo bilan cheklangan: (i) mahalliy DICOM tasvirlarda chegaraviy quti annotatsiyalarining yo‘qligi, (ii) klinik hisobotlarning bir vaqtning o‘zida uchta alifboda — o‘zbekcha kirillcha, o‘zbekcha lotincha va ruscha — ba’zan bir hujjat ichida ham kod almashtirilgan holda yozilishi, (iii) model chiqishlarini radiolog tomonidan tekshirib, oltin yorliqlar sifatida o‘qitishga qaytarishga to‘sqinlik qiluvchi ish oqimi integratsiyasi tanqisligi. Ushbu maqolada xom klinik DICOM va erkin matnli radiologik hisobotlarni radiolog tomonidan tekshirilgan, oltin yorlikli aniqlash modeliga aylantiradigan o‘n bosqichli, to‘liq takrorlanuvchi quvur taqdim etiladi. Tizim to‘rtta mahsulotni birlashtiradi: MAMOGRAF annotatsiya platformasi, XS-Classifier ko‘p tilli klassifikatori, TILLNet-Det multimodal detektori va ko‘p tilli zaif nazoratli o‘qitish quvuri. Uchta bosqichli o‘qitish dasturi turli sifatdagi ma’lumotlardan tartibli foydalanadi. Arxitektura va o‘qitish hissalari nazorat-tahliliy tajribalar orqali ajratiladi.

Views: 91 Published: 2026-06-23 Pages: 214-229 Volume: 4 Issue: 3

References

  1. Lin T.-Y., Dollár P., Girshick R., He K., Hariharan B., Belongie S. Feature pyramid networks for object detection // IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR). — Honolulu, HI, USA, 2017. — P. 2117–2125. doi: 10.1109/CVPR.2017.106
  2. Radford A., Kim J.W., Hallacy C., Ramesh A., Goh G., Agarwal S., et al. Learning transferable visual models from natural language supervision // Proc. Int. Conf. Mach. Learn. (ICML). — 2021. — P. 8748–8763.
  3. Rezatofighi H., Tsoi N., Gwak J., Sadeghian A., Reid I., Savarese S. Generalized intersection over union: A metric and a loss for bounding box regression // IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR). — Long Beach, CA, USA, 2019. — P. 658–666. doi: 10.1109/CVPR.2019.00075
  4. Zhang Y., Jiang H., Miura Y., Manning C.D., Langlotz C.P. Contrastive learning of medical visual representations from paired images and text // Proc. Mach. Learn. Healthc. Conf. — 2022. — Vol. 182. — P. 2–25.
  5. Lee R.S., Gimenez F., Hoogi A., Miyake K.K., Gorovoy M., Rubin D.L. A curated mammography data set for use in computer-aided detection and diagnosis research (CBIS-DDSM) // Scientific Data. — 2017. — Vol. 4. — Art. 170177. doi: 10.1038/sdata.2017.177
  6. Armato III S.G., McLennan G., Bidaut L., McNitt-Gray M.F., Meyer C.R., Reeves A.P., et al. The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A completed reference database of lung nodules on CT scans // Medical Physics. — 2011. — Vol. 38, No. 2. — P. 915–931. doi: 10.1118/1.3528204
  7. Tiu E., Talius E., Patel P., Langlotz C.P., Ng A.Y., Rajpurkar P. Expert-level detection of pathologies from unannotated chest X-ray images via self-supervised learning // Nature Biomedical Engineering. — 2022. — Vol. 6. — P. 1399–1406. doi: 10.1038/s41551-022-00936-9
  8. Cardoso M.J., Li W., Brown R., Ma N., Kerfoot E., Wang Y., et al. MONAI: An open-source framework for deep learning in healthcare // arXiv preprint arXiv:2211.02701. — 2022.
  9. Tian Z., Shen C., Chen H., He T. FCOS: Fully convolutional one-stage object detection // Proc. IEEE Int. Conf. Comput. Vis. (ICCV). — Seoul, Korea, 2019. — P. 9627–9636. doi: 10.1109/ICCV.2019.00972
  10. Johnson A.E.W., Pollard T.J., Berkowitz S.J., Greenbaum N.R., Lungren M.P., Deng C.-Y., et al. MIMIC-CXR, a de-identified publicly available database of chest radiographs with free-text reports // Scientific Data. — 2019. — Vol. 6. — Art. 317. doi: 10.1038/s41597-019-0322-0
  11. Pizer S.M., Amburn E.P., Austin J.D., Cromartie R., Geselowitz A., Greer T., et al. Adaptive histogram equalization and its variations // Computer Vision, Graphics, and Image Processing. — 1987. — Vol. 39, No. 3. — P. 355–368. doi: 10.1016/S0734-189X(87)80186-X
  12. Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A.N., Kaiser Ł., Polosukhin I. Attention is all you need // Adv. Neural Inf. Process. Syst. (NeurIPS). — 2017. — Vol. 30. — P. 5998–6008.
  13. Perez E., Strub F., de Vries H., Dumoulin V., Courville A. FiLM: Visual reasoning with a general conditioning layer // Proc. AAAI Conf. Artif. Intell. — New Orleans, LA, USA, 2018. — Vol. 32, No. 1. — P. 3942–3951. doi: 10.1609/aaai.v32i1.11671
  14. He K., Zhang X., Ren S., Sun J. Deep residual learning for image recognition // IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR). — Las Vegas, NV, USA, 2016. — P. 770–778. doi: 10.1109/CVPR.2016.90
  15. Pedraza L., Vargas C., Narváez F., Durán O., Muñoz E., Romero E. An open access thyroid ultrasound image database (TNSCUI) // Proc. SPIE Medical Imaging. — 2015. — Vol. 9287. doi: 10.1117/12.2073532
  16. Wang X., Peng Y., Lu L., Lu Z., Bagheri M., Summers R.M. ChestX-ray8: Hospital-scale chest X-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases // IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR). — Honolulu, HI, USA, 2017. — P. 3462–3471. doi: 10.1109/CVPR.2017.369
  17. Mason D. Pydicom: An open source DICOM library // GitHub repository. — 2008. — URL: https://github.com/pydicom/pydicom
  18. Ronneberger O., Fischer P., Brox T. U-Net: Convolutional networks for biomedical image segmentation // Medical Image Computing and Computer-Assisted Intervention (MICCAI). — Munich, Germany, 2015. — Lecture Notes in Computer Science, Vol. 9351. — P. 234–241. doi: 10.1007/978-3-319-24574-4_28
  19. Lin T.-Y., Goyal P., Girshick R., He K., Dollár P. Focal loss for dense object detection // IEEE Trans. Pattern Anal. Mach. Intell. — 2020. — Vol. 42, No. 2. — P. 318–327. doi: 10.1109/TPAMI.2018.2858826
  20. Khamdamov R., Turaqulov Sh.Kh. Mammogrammalarda mikrokal'tsifikatsiyalarni aniqlash uchun bipolyar noravshan segmentatsiya usuli // Raqamli Transformatsiya va Sun'iy Intellekt. — 2025. — № 3. — B. 45–58.