RADIOLOGIYADA SUN’IY INTELLEKT
Abstract
Ushbu maqolada dunyoda rivojlanib borayotgan sun'iy intellekt (SI) algoritmlari, ayniqsa chuqur o'rganish, tasvirni aniqlash vazifalarida ajoyib yutuqlarni ko'rsatish haqida. Konvolyutsion neyron tarmoqlaridan tortib variatsion avtokoderlargacha bo'lgan usullar tibbiy tasvirni tahlil qilish sohasida ko'plab ilovalarni ishlab chiqildi va uni tez sur'atlar bilan oldinga siljitdi. Radiologiya amaliyotida o'qitilgan shifokorlar kasalliklarni aniqlash, tavsiflash va monitoring qilish uchun tibbiy tasvirlarni vizual ravishda baholaganlar. SI usullari tasvirlash ma'lumotlaridagi murakkab naqshlarni avtomatik ravishda tanib olishda va rentgenografik xususiyatlarni sifat jihatidan emas, balki miqdoriy baholashda ustunlik qiladi.
References
N. Auspicious machine learning. Nat. Biomed. Engineer 1, 0036 (2017).
Mnih V et al. Human-level control through deep reinforcement learning. Nature 518, 529–533 (2015).
Esteva A et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115–118 (2017).
Cheng J-Z et al. Computer-aided diagnosis with deep learning architecture: applications to breast lesions in US images and pulmonary nodules in CT scans. Sci. Rep 6, 24454 (2016).
van Ginneken B, Schaefer-Prokop CM & Prokop M Computer-aided diagnosis: how to move from the laboratory to the clinic. Radiology 261, 719–732 (2011).
