今年，人们对人工智能(AI)的兴趣激增，ChatGPT等工具使人工智能程序比以往任何时候都更容易获得. 人工智能几乎触及了每个领域，研究人员开始研究这项技术能做什么，以及它如何改善我们的生活. Radiology is no exception. 

At Johns Hopkins, 放射科教师和运营经理通过放射学人工智能发展(RAID)小组委员会共同探索这项新技术. 放射科增值分析指导委员会的一个分支, RAID is chaired by Cheng Ting Lin, 他是一名专攻心胸影像的放射学副教授，也是一名经过认证的影像信息学专家.

RAID has over a dozen members, including representatives from radiology faculty, departmental administrators, and medical imaging information technology professionals, 并定期咨询外部团体，如JHM数据信托委员会, 机构审查委员会和约翰霍普金斯医疗系统供应链系统.

At each monthly meeting, RAID成员讨论了几个临床和研究人工智能项目的进展情况. 该组织的目标是创建一个医生主导的治理结构来进行评估, prioritize, implement and monitor the use of AI in the radiology department, 从研究算法到fda批准的医疗设备.

放射学中的人工智能涉及使用算法分析大量数据和医学成像. This has the potential to help radiologists by triaging cases, highlighting abnormalities, and improving diagnostic confidence in the reading room.

Right now, Lin said, medical imaging AI offerings are highly variable in quality, which limits their widespread adoption. RAID小组委员会的主要职责之一是评估第三方人工智能算法, one day, be deployed in our clinical environment.

According to Andrew Menard, 放射学战略和创新的执行主任和RAID小组委员会的成员, 目前市场上有400种放射人工智能产品已通过食品和药物管理局的批准, and more are cleared every month. These products focus on different areas, from improving image acquisition to triage, but, as Menard explained, “最重要的算法是那些让执业放射科医生的生活更美好的算法.”

Radiologists today face ever-increasing volumes and clinical demands, along with diminishing reimbursements. AI technology, he said, 将是约翰霍普金斯大学放射学对这些需求的重要组成部分.”

“人工智能有可能将低价值的工作自动化，这样放射科医生就可以专注于高价值的工作,” Menard said, adding, “Implemented properly, 这将提高生产力和专业满意度，同时保持放射护理的质量.”

Lin echoed this sentiment, noting, “人工智能也有可能通过增加放射科医生对解释的信心来提高推荐十大正规网赌平台护理的质量.”

Emily Ambinder, 放射学和放射学助理教授，专门研究乳房成像, 加入RAID，帮助研究如何最好地将新的人工智能工具纳入乳房x光检查.

She is working with Lisa Mullen, breast imaging fellowship director, 谁是RAID第一个医生主导的专注于人工智能辅助乳房x光筛查分析的倡议的先锋. Ambinder, Mullein和他的团队已经完成了对两种领先人工智能算法的初步评估, and negotiations with the preferred vendor are ongoing. 

According to Ambinder, 市场上有许多很有前途的人工智能乳房x光检查工具已经获得了fda的批准, 许多大型医疗机构已经在使用人工智能来分析乳房x线照片.

虽然阿姆宾德理解人工智能可能“接管”并取代人类教师的担忧, she is excited about bringing AI into the reading room. AI is meant to aid radiologists, Ambinder explained, not to replace human intelligence in the reading room.

As such technology is incorporated into routine radiologist workflow, 放射科医生希望看到癌症检测的增加和回调的减少.

“把它想象成另一双眼睛，或者另一位放射科医生和你一起看乳房x光片,” Ambinder said. 

AI programs do not run autonomously, Ambinder noted. 放射科医生将继续审查所有病例和发现——人工智能只是一种帮助检测的新工具, diagnosis and triage. 

林解释说:“我们正在寻找能够增加放射科医生价值的工具，而不是取代他们。. 

That said, there are some limitations to current AI technology. 

约翰霍普金斯大学以外的第三方算法可能不那么准确. Lin said, 并指出，这些项目使用的患者数据与在约翰霍普金斯寻求治疗的患者的人口统计学和特征不同. 因此，算法在实现后可能执行得不太好，需要持续监控.

然而，随着自主开发的人工智能工具的开发，这些问题可能会被克服. 

For Lin, the future of AI in the radiology reading room looks bright. 他预计，约翰霍普金斯大学有一天会成为人工智能领域的一流机构，利用这种机器学习程序更快、更准确地识别疾病和潜在的治疗方法.

An equally important goal, Dr. Lin explained, 是支持内部开发的算法，并与约翰霍普金斯大学的专家合作，将他们的人工智能工具从实验室带到床边.

RAIL(放射学人工智能实验室)正在努力扩大人工智能在医学成像分析中的应用。, a partnership among the Johns Hopkins radiology department, the Malone Center for Engineering in Healthcare, the Applied Physics Laboratory and the Whiting School of Engineering. 

Headed by Haris Sair, director of the division of neuroradiology, RAIL与约翰霍普金斯大学的部门合作开发机器学习应用程序，以更好地帮助医学图像分类和分析. 

然而，就像罗马不是一天建成的一样，构建一个人工智能程序也需要时间. 

As Lin noted, it is imperative to have a robust governance structure in place, allowing methodical development, piloting and evaluation of AI tools across the department and system. 

“There are no shortcuts for this process,” Lin said. 

Lin envisions a future when, due to assisted analysis, detection and diagnosis, more lives are saved than ever before.