AI-MK:用于评估和监测微生物炎的人工智能
Colby Hart1, Xu Chen2,3, Mahmoud Ahmed4
1Cornea, The Royal Victorian Eye and Ear Hospital, East Melbourne, Victoria, Australia.
BMJ open ophthalmology
|January 13, 2026
概括
一个人工智能 (AI) 模型在使用前段光学连贯断层扫描 (AS-OCT) 检测微生物角质炎 (MK) 病变方面表现出高精度. 这种AI框架可靠地识别了MK并跟踪了病变变化,显示出高灵敏度和特异性.
科学领域:
- 眼科医生 眼科 眼科
- 医疗成像医学成像
- 人工智能的人工智能
背景情况:
- 微生物角膜炎 (MK) 是一种严重的眼部感染,需要及时诊断和监测.
- 前段光学连贯断层扫描 (AS-OCT) 是可视化角膜结构的宝贵工具.
- 对MK进展的客观评估可能具有挑战性.
研究的目的:
- 评估人工智能 (AI) 模型使用AS-OCT检测和监测微生物角质炎 (MK) 的性能.
- 评估AI模型的诊断MK病变和跟踪其尺寸随时间变化的能力.
主要方法:
- 一项前性观察性研究,包括疑似MK患者和健康对照.
- 在MK患者的每次诊所访问时都进行了AS-OCT成像.
- 基于DeepLabV3网络的AI模型被用于分析AS-OCT图像,用于MK检测和病变大小监测.
主要成果:
- 人工智能模型在93%的病例中 (152/163) 准确检测到MK病变.
- 该模型实现了93%的灵敏度和100%的特异性,在健康的眼睛中没有虚假阳性.
- 在76%的病例中,AI与角膜专家在追踪病变变化方面达成一致.
结论:
- 人工智能框架可靠地使用AS-OCT高精度识别MK病变.
- 人工智能模型显示了对MK进展和治疗反应的客观监测的潜力.
- 这种人工智能工具可以帮助临床医生管理微生物角质炎.
相关概念视频
Microbiome of the Eye
67
The human eye has a specialized microbiota that reflects its unique anatomical and immunological environment. This low-biomass microbial community predominantly colonizes the conjunctiva and eyelid margins, playing a vital role in ocular surface homeostasis and defense. Despite its proximity to the richly colonized facial skin, the ocular surface maintains a distinct microbial profile due to continuous mechanical and biochemical defense mechanisms.The conjunctival surface hosts fewer microbial...
67
Automated Microbial Diagnostics
77
Automated diagnostic analyzers have transformed clinical microbiology by providing rapid and reliable methods for pathogen identification and antibiotic susceptibility testing. Among these systems, the Vitek 2 is widely used because it automates the traditionally labor-intensive processes of microbial identification (ID) and antibiotic susceptibility testing (AST), delivering standardized and timely results that are essential for effective patient care.Microbial Identification with ID CardsThe...
77


