Baptist Neurological Institute Reports Findings in Artificial Intelligence (Use of Artificial Intelligence Software to Detect Intracranial Aneurysms: A Comprehe nsive Stroke Center Experience)
Baptist Neurological Institute Reports Findings in Artificial Intelligence (Use of Artificial Intelligence Software to Detect Intracranial Aneurysms: A Comprehe nsive Stroke Center Experience)
浸信会神经研究所报告人工智能的发现（使用人工智能软件检测颅内动脉瘤：卒中中心综合经验）
扫码查看
点击上方二维码区域，可以放大扫码查看
摘要
一位新闻记者-机器人与机器学习的工作人员新闻编辑每日新闻-人工智能的新研究是一篇报道的主题。根据NewsRx通讯员从Florida Jacksonville传来的消息，研究表明：“通过比较常规CT血管造影(CTA)图像（Standard Care）和人工智能软件，评估神经ysm检测的变异性和人工智能(AI)软件作为筛查工具的潜力。神经放射学家回顾了770个CTA IMA，并报告了囊状动脉瘤的存在与否。”我们的新闻记者从Baptist Neurologica L Institute的研究中获得了一句话:“随后,这些图像被人工智能软件分析。如果该软件怀疑有动脉瘤,它会标记相应的图像。如果放射科医生的报告和人工智能的发现不匹配,一位经验丰富的神经外科医生评估CTA图像，对动脉瘤的存在或不存在提供了明确的结论。AI软件标记出33例潜在的动脉瘤，16例放射科医生确诊为动脉瘤，17例被排除。AI软件判断为阴性的737例，同一组为阴性。CTA诊断动脉瘤28例,与放射科报告比较,AI诊断动脉瘤的敏感性36%,特异度97.6%,敏感性36%。AI与放射科医师有45例不匹配病例，AI标记17例显示动脉瘤，神经外科专家证实17例显示动脉瘤，28例AI认为ED阴性。放射科医师提示有动脉瘤,其中17例经神经外科医师证实.人工智能有可能提高未破裂颅内动脉瘤的诊断水平."
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Artificial Intelligenc e is the subject of a report. According to news originating from Jacksonville, F lorida, by NewsRx correspondents, research stated, "To evaluate variability in a neurysm detection and the potential of artificial intelligence (AI) software as a screening tool by comparing conventional computed tomography angiography (CTA) images (standard care) with AI software. Neuroradiologists reviewed 770 CTA ima ges and reported the presence or absence of saccular aneurysms." Our news journalists obtained a quote from the research from Baptist Neurologica l Institute, "Subsequently, the images were analyzed by AI software. If the soft ware suspected an aneurysm, it flagged the corresponding image. In cases where t here was a mismatch between the radiologist's report and the AI findings, an exp ert neurosurgeon evaluated CTA images providing a definitive conclusion on the p resence or absence of an aneurysm. AI software flagged 33 cases as potential ane urysms; 16 cases were positively identified as aneurysms by radiologists, and 17 were dismissed. A total of 737 cases were considered negative by AI software, w hile in the same group, radiologists identified aneurysms in 28 CTA images. Comp ared with the radiologist's report, AI performance had a sensitivity of 36% , specificity of 97.6%, and negative predictive value of 96.2% . There were 45 mismatch cases between AI and radiologists. AI flagged 17 images as showing an aneurysm that was unreported by radiologists; the expert neurosur geon confirmed that 7 of the 17 images showed an aneurysm. In 28 images consider ed negative by AI, radiologists indicated aneurysms; 17 of those confirmed by th e neurosurgeon. AI has the potential to increase the diagnosis of unruptured int racranial aneurysms."
Key words
Jacksonville/Florida/United States/No rth and Central America/Aneurysm/Artificial Intelligence/Brain Diseases and C onditions/Cardiovascular Diseases and Conditions/Central Nervous System Diseas es and Conditions/Cerebrovascular Disorders/Emerging Technologies/Health and Medicine/Intracranial Aneurysm/Intracranial Arterial Diseases and Conditions/Machine Learning/Software/Vascular Diseases and Conditions
NETL
NSTL