Artificial intelligence system could cut critical chest x-rays assessment time

华威大学开发人工智能系统,辅助缩短胸部 X射线检查时间

2019-01-30 06:30:00 digitalhealth

本文共683个字,阅读需2分钟

A team in Warwick have developed an artificial intelligence system which could cut the time it takes to assess critical chest x-rays from 11 days to less than three. Professor Giovanni Montana, chair in data science at Warwick Manufacturing Group (WMG) at The University of Warwick, led a team that developed the system which can recognise radiological abnormalities in chest x-rays. The system can asses how severe the abnormality is and, therefore, how quickly a patient needs treatment. They also developed a natural language processing algorithm which can read a radiologist report, understand their finding and automatically prioritise cases based on their severity. The AI system can be used from the moment a patient is admitted to hospital. Montana said: “When a patient is admitted to the hospital to have a diagnostic chest x-ray, the image goes into a queue waiting for a radiologist to visually inspect it and write a report. “The longer a patient waits for a report, the higher the chances that a potentially harmful condition is diagnosed too late. “Using our technology, we have demonstrated that a radiologist can potentially identify scans presenting critical finding as soon as they are acquired, even before the patient leaves the hospital. “This can make a tremendous difference in the diagnosis of life-threatening conditions such as lung cancer.” In the United Kingdom, it is estimated that at any time there are over 300,000 radiographs waiting over 30 days for reporting. Chest radiographs account for 40 per cent of all diagnostic imaging performed worldwide but the research shows alternative models of care, including AI, could be used to reduce delays. The team have recently secured funding from the Wellcome Trust Initiative to continue the project, which they hope will be commercially available this year. A Digital Health News feature, published in March 2017, looked into how AI is already beginning to reshape radiology imaging and diagnostics at NHS trusts.
沃里克的一个团队开发了一个人工智能系统,可以将评估胸部 X 射线的时间从11天缩短到不到3天。 Warwick 大学 Warwick Manufacturing Group ( WMG )数据科学主任 Giovanni 蒙大拿州教授领导了一个研究小组,该小组开发了该系统,可识别胸部 X 射线中的放射异常。 系统可以判断异常的严重程度,因此,病人需要治疗的速度有多快。 他们还开发了一种自然语言处理算法,可以读取放射科医生的报告,了解他们的发 现,并根据案件的严重程度自动对案件进行优先排序。 人工智能系统可以从病人住院之时起使用。 蒙大拿州表示:“当一名患者被送往医院接受诊断胸部 X 光检查时,图像进入排队等待放射科医生对其进行视觉检查并撰写报告。 “病人等待报告的时间越长,诊断出潜在有害疾病的可能性就越高。 “利用我们的技术,我们已经证明,即使在病人离开医院之前,一位放射科医生也能在获得关键发现后立即识别扫描结果。 “这可能在肺癌等威胁生命的疾病的诊断上产生巨大差异。” 在联合王国,据估计,任何时候都有300,000多张 X 线片等待30天以上的报告。 胸部 X 线占全世界所有诊断成像的40%,但研究表明,包括人工智能在内的其他护理模式可用于减少延迟。 该团队最近从 Wellcome Trust Initiative 获得了资金,以继续该项目,他们希望该项目将在今年商业化。 2017年3月发布的《数字健康新闻》( Digital Health News )功能,探讨了人工智能已经开始重塑 NHS 信托公司的放射影像和诊断。

以上中文文本为机器翻译,存在不同程度偏差和错误;偶尔因源网页结构局限,内容无法一次完整呈现。请理解并参考原站原文阅读。

阅读原文