计算机视觉
人工智能
地质学
医学
计算机科学
遥感
碎石术
作文(语言)
图像处理
放射科
生物医学工程
取石位
作者
Polina Ibragimova,Olga Baytsaeva,Ignat Golubev,Danila Lesnykh,Timofey Khramov,Alexey Martov,Viktoria Andreeva
出处
期刊:
[Institute of Electrical and Electronics Engineers]
日期:2026-06-01
卷期号:: 355-355
标识
DOI:10.1109/iclo69056.2026.11624686
摘要
In this study we developed a deep-learning computer-vision model embedded in the Urolase Vision System to detect and classify urinary stones from intraoperative endoscopic video in real time, supporting thulium fiber laser (TFL) parameter selection. Trained and tested on clinically sourced videos with lab-confirmed fragments, the model achieved mAP50 ≈87.5% across urate, COM, COD, and phosphate stones.
科研通智能强力驱动
Strongly Powered by AbleSci AI