Raqamli Transformatsiya va Sun’iy Intellekt
ULTRATOVUSHLI TIBBIY TASVIRLARNI SINFLASHTIRISHDA INFORMATIVLIK KO‘RSATKICHINI BAHOLASH ALGORITMI
1 Muhammad al-Xorazmiy nomidagi Toshkent axborot texnologiyalari universiteti
2 Denov tadbirkorlik va pedagogika instituti
Zenodo DOI: 10.5281/zenodo.23537377
Keywords
Abstract
Bachadon miomasini ultratovush tasvirlari asosida avtomatlashtirilgan aniqlashda tasvir sifatining o‘zgaruvchanligi muhim muammolardan biridir. Nuqtali shovqin, past kontrastlilik, to‘qima intensivligining notekis taqsimlanishi va patologik hudud chegaralarining xiraligi bir xil chuqur o‘qitish modeli turli tasvirlarda turlicha natija berishiga olib kelishi mumkin. Mazkur tadqiqotda ultratovushli tasvirning diagnostik va algoritmik jihatdan foydalilik darajasini oldindan baholash uchun kompleks informativlik ko‘rsatkichi ishlab chiqildi. Taklif etilgan algoritm kontrast, entropiya, tekstura, gradient asosidagi chegara ravshanligi va shovqin darajasini alohida hisoblab, ularni normallashtirish va vaznli birlashtirish orqali yagona informativlik qiymatini hosil qiladi. Tadqiqotda 3050 ta ultratovush tasviridan tashkil topgan balanslangan ma’lumotlar to‘plamidan foydalanildi; unda 1525 ta miomali va 1525 ta miomasiz tasvir mavjud bo‘ldi. Informativlikni hisoblash natijalari CRITIC, entropiya vaznlash usuli (EWM) va taklif etilgan kombinatsiyalangan W* yondashuvi bilan baholandi. Shifokor etaloni bilan qiyoslashda W* yondashuvi Accuracy-98,89%, Precision-98,22%, Recall-99,67% va Specificity-96,08% qiymatlarini ko‘rsatdi. Natijalar tasvir informativligini klassifikatsiyadan oldingi alohida bosqich sifatida hisobga olish ultratovush tasvirlarini avtomatlashtirilgan tahlil qilishda barqaror va obyektiv qaror qabul qilish uchun foydali ekanligini ko‘rsatadi.
References
- Ronneberger, O., Fischer, P., & Brox, T. (2015). U-Net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention (MICCAI), 234–241. https://doi.org/10.1007/978-3-319-24574-4_28
- Bajaj, S., Gopal, N., Clingan, M. J., & Bhatt, S. (2022). A pictorial review of ultrasonography of the FIGO classification for uterine leiomyomas. Abdominal Radiology, 47(1), 341–351. https://doi.org/10.1007/s00261-021-03283-6
- Awiwi, M. O., Badawy, M., Shaaban, A. M., et al. (2022). Review of uterine fibroids: imaging of typical and atypical features, variants, and mimics with emphasis on workup and FIGO classification. Abdominal Radiology, 47(7), 2468–2485. https://doi.org/10.1007/s00261-022-03545-x
- Litjens, G., Kooi, T., Bejnordi, B. E., et al. (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
- Huang, G., Liu, Z., Van Der Maaten, L., & Weinberger, K. Q. (2017). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 4700–4708. https://doi.org/10.1109/CVPR.2017.243
- LeCun, Y., Bengio, Y., & Hinton, G. (2015). Deep learning. Nature, 521, 436–444. https://doi.org/10.1038/nature14539
- Wang, Z., Bovik, A. C., Sheikh, H. R., & Simoncelli, E. P. (2004). Image quality assessment: From error visibility to structural similarity. IEEE Transactions on Image Processing, 13(4), 600–612. https://doi.org/10.1109/TIP.2003.819861
- Haralick, R. M., Shanmugam, K., & Dinstein, I. (1973). Textural features for image classification. IEEE Transactions on Systems, Man, and Cybernetics, SMC-3(6), 610–621. https://doi.org/10.1109/TSMC.1973.4309314
- He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 770–778. https://doi.org/10.1109/CVPR.2016.90
- Shannon, C. E. (1948). A mathematical theory of communication. Bell System Technical Journal, 27(3), 379–423; 27(4), 623–656. https://doi.org/10.1002/j.1538-7305.1948.tb01338.x
- Xi, H., & Wang, W. (2024). Deep learning based uterine fibroid detection in ultrasound images. BMC Medical Imaging, 24, 218. https://doi.org/10.1186/s12880-024-01389-z
- Slabaugh, G., Unal, G., Wels, M., Fang, T., & Rao, B. (2009). Statistical region-based segmentation of ultrasound images. Ultrasound in Medicine & Biology, 35(5), 781–795. https://doi.org/10.1016/j.ultrasmedbio.2008.10.014
- Shahzad, A., Mushtaq, A., Sabeeh, A. Q., et al. (2023). Automated uterine fibroids detection in ultrasound images using deep convolutional neural networks. Healthcare, 11(10), 1493. https://doi.org/10.3390/healthcare11101493
- Huo, T., Li, L., Chen, X., et al. (2023). Artificial intelligence-aided method to detect uterine fibroids in ultrasound images: a retrospective study. Scientific Reports, 13, 3714. https://doi.org/10.1038/s41598-023-30717-0
- Yang, T., Yuan, L., Li, P., & Liu, P. (2023). Real-time automatic assisted detection of uterine fibroid in ultrasound images using a deep learning detector. Ultrasound in Medicine & Biology, 49(7), 1616–1626. https://doi.org/10.1016/j.ultrasmedbio.2023.03.013
- Baird, D. D., Dunson, D. B., Hill, M. C., Cousins, D., & Schectman, J. M. (2003). High cumulative incidence of uterine leiomyoma in black and white women: ultrasound evidence. American Journal of Obstetrics and Gynecology, 188(1), 100–107.
- Diakoulaki, D., Mavrotas, G., & Papayannakis, L. (1995). Determining objective weights in multiple criteria problems: The CRITIC method. Computers & Operations Research, 22(7), 763–770. https://doi.org/10.1016/0305-0548(94)00059-H
- Stewart, E. A., Cookson, C. L., Gandolfo, R. A., & Schulze-Rath, R. (2016). Epidemiology of uterine fibroids: a systematic review. BJOG, 124(10), 1501–1512. https://doi.org/10.1111/1471-0528.14640
- Tan, M., & Le, Q. (2019). EfficientNet: Rethinking model scaling for convolutional neural networks. Proceedings of the 36th International Conference on Machine Learning, 6105–6114.
- Oktay, O., Schlemper, J., Folgoc, L. L., et al. (2018). Attention U-Net: Learning where to look for the pancreas. arXiv:1804.03999.
- Jiang, Z., et al. (2025). Speckle2Self: Self-supervised ultrasound speckle reduction without clean data. Medical Image Analysis, 103755. https://doi.org/10.1016/j.media.2025.103755
- Al-jaburi, A. A., & AL-sudani, A. H. (2022). Medical ultrasound image quality enhancement and regions segmentation. Iraqi Journal of Science, 63(10). https://doi.org/10.24996/ijs.2022.63.10.35
- Stewart, E. A. (2016). Uterine fibroids. New England Journal of Medicine, 372, 1646–1655. https://doi.org/10.1056/NEJMra1209993