Sun’iy intellekt algoritmlari yordamida hiqildoq saratoni diagnostikasini avtomatlashtirish
Аннотация
Hiqildoq saratoni (Laryngeal cancer) dunyo miqyosida keng tarqalgan bosh va bo‘yin sohasining xavfli o‘smalaridan biri hisoblanib, kasallikning kech bosqichlarda aniqlanishi o‘lim ko‘rsatkichining yuqori bo‘lishiga sabab bo‘lmoqda. Zamonaviy tibbiyotda sun’iy intellekt va chuqur o‘rganish texnologiyalarining rivojlanishi endoskopik tasvirlarni avtomatik tahlil qilish orqali kasalliklarni erta aniqlash imkoniyatlarini kengaytirmoqda. Ushbu tadqiqotda hiqildoqning endoskopik tasvirlarini tahlil qilish asosida saratondan oldingi holatlar va xavfli o‘smalarni aniqlovchi ResNet50 arxitekturasiga asoslangan sun’iy intellekt modeli ishlab chiqildi. Modelni o‘qitishda 1200 ta klinik tasvirdan foydalanildi. Tadqiqot natijalariga ko‘ra, yaratilgan tizim 94,5% aniqlik, 93,2% sezuvchanlik va 95,8% spetsifiklik ko‘rsatkichlariga erishdi. Ishlab chiqilgan model real vaqt rejimida ishlash imkoniyatiga ega bo‘lib, shifokorlarning diagnostika jarayonida qaror qabul qilishiga samarali yordam berishi mumkin.
Kalit so‘zlar: sun’iy intellekt, hiqildoq saratoni, chuqur o‘rganish, ResNet50, laringoskopiya, CNN, endoskopik tasvir, tibbiy diagnostika.
Библиографические ссылки
1. Alabdalhussein, M., et al. (2025). Deep learning applications in head and neck oncology: A focusing on laryngeal lesions classification. Journal of Cancer Research and Clinical Oncology, 151(2), 112–124.
2. Halicek, M., et al. (2019). In vivo detection of head and neck cancer using hyperspectral imaging and deep learning. Scientific Reports, 9(1), 12431.
3. Li, X., Wang, L., & Zhang, Y. (2025). Artificial intelligence-based clinical decision support systems for the evaluation of laryngeal endoscopies. JMIR Formative Research, 9, e66110.
4. Ren, J., et al. (2020). Deep learning-based computer-aided diagnosis of laryngeal cancer by using laryngoscopic images. Microvascular Research, 131, 104021.
5. Sławiński, T., Sójkowska-Sławińska, O., Leśniewska, A., Macuk, P., & Rutecka, N. (2025). Artificial intelligence in the diagnosis of laryngeal cancer based on endoscopic images: A comprehensive narrative review. International Journal of Innovative Technologies in Social Science, 3(47).
6. Smith, J., & Johnson, R. (2025). Artificial intelligence in laryngeal cancer detection: A systematic review and meta-analysis. Current Oncology, 32(6), 338–351.
7. Wang, G., et al. (2026). Development of AI-based laryngeal cancer diagnostic models using FCN–ResNet101 arxitecture. Diagnostics, 16(2), 227.
8. Xu, C., et al. (2026). Development and validation of a deep learning model for quality assessment and documentation in laryngoscopy. Scientific Reports, 16, 4825.
Опубликован
Как цитировать
Выпуск
Раздел
Лицензия

Это произведение доступно по лицензии Creative Commons «Attribution» («Атрибуция») 4.0 Всемирная.

