Gadgetron Global Network and Intelligence Computing: Clinical Imaging Application Development and Software Infrastructure

在刚刚过去的2019-2020财年，Gadgetron AI研发取得了成功，更多的AI应用程序被开发并部署到临床实践中。来自50K名患者的数据被收集并存储在NHLBI。Gadgetron AI登上了国际新闻，我们在临床成像AI方面的研究发表在顶级期刊上。在这份报告之后，我列出了几个。 。开发人工智能反馈和患者历史界面软件，因此Gadgetron将成为管理成像数据、患者记录和临床反馈的独特平台。有了这三个关键要素，我们计划进入疾病诊断和自动分析领域(例如，预测心脏结果和对患者是否应该接受干预程序进行分类)。 。开发完整的AI Powered CMR分析解决方案，并将其部署到医院的日常使用，包括电影、LGE、灌注、T1/T2/T2*标测、脂肪水成像等。这里的动机是以全自动化提取患者特定的成像信息。这些信息将用于患者病史和队列训练的疾病模型。 。开发磁共振扫描仪对重大心脏疾病的精确成像。其目标是开发一个特定于患者的模型，以预测a)患者是否应该接受介入性手术；b)患者是否会在未来发生心脏事件。实现这些的技术路线是：1)自由呼吸的CMR成像；2)AI派生的成像信息和生物标志物；3)在Gadgetron中接收患者的病史和记录；4)使用队列模型根据步骤1-3的信息进行预测。 入选出版物列表： 利用卷积神经网络检测心脏磁共振成像中的标志点。许雪，杰西卡·阿尔蒂科，玛丽安娜·丰塔纳，詹姆斯·C·穆恩，罗德里·H·戴维斯，彼得·凯尔曼。Arxiv：2008.06142 eess.IV(正在审查中)。 基于深度学习的心肌灌注MRI自动在线分析。惠雪，罗德里·戴维斯，路易斯·艾·布朗，克里斯托弗·D·诺特，图沙尔·科特查，玛丽安娜·丰塔纳，斯文·普莱恩，詹姆斯·C·穆恩，彼得·凯尔曼。放射学：人工智能(印刷中)。Arxiv：1911.00625 Q-Bio.QM。 新冠肺炎：幸存者的心肌损伤。丹尼尔·S·奈特、图沙尔·科特查、尤素夫·拉兹维、丽莎·查科、詹姆斯·T·布朗、帕拉吉特·S·杰特利、詹姆斯·戈德林、迈克尔·雅各布斯、露西·E·兰姆、鲁伯特·内格斯、安东尼·沃尔夫、詹姆斯·C·穆恩、慧雪、彼得·凯尔曼、尼基特·帕特尔和玛丽安娜·丰塔纳。发行量，https://doi.org/10.1161/CIRCULATIONAHA.120.049252 使用深度学习在动脉输入功能图像中自动检测用于在线灌注图的左心室：一项对15,000名患者的研究。许雪，伊桑·曾，克里斯托弗·D·诺特，图沙尔·科特查，路易丝·布朗，斯文·普莱恩，玛丽安娜·丰塔纳，詹姆斯·C·穆恩，彼得·凯尔曼。《医学中的磁共振》，第84卷，第5期，2020年11月，2788-2800页。 定量心肌灌注的预后意义：一种基于人工智能的使用灌注图的方法。Kristopher D Knott，Andreas Seraphim，Joao B Augusto，Huue Xue，Liza Chacko，Nay Aung，Steffen E Petersen，Jackie A Cooper，Charlotte Manisty，Anish N Buva，Tushar Kotecha，Christos V Bourantas，Rhodri H Davies，Louise AE Brown，Sven Plein，Marianna Fontana，Peter Kellman，James C Moon。发行量。2020年；第141：12821291。 媒体新闻： Https://www.newscientist.com/article/2224403-an-ai-doctor-is-analysing-heart-scans-in-dozens-of-hospitals/#ixzz6VfVSiMrH Https://www.beckershospitalreview.com/artificial-intelligence/ai-measures-blood-flow-in-real-time-predicting-heart-attack-and-stroke-study-finds.html Https://time.com/5784090/ai-heart-attack-stroke/

The past FY of 2019-2020 was successful for Gadgetron AI R&D. More AI applications were developed and deployed to clinical practice. Data from 50K patients were collected and stored at NHLBI. Gadgetron AI was on international news and our research in clinical imaging AI was published at top journals. I listed a few after this report. . Develop AI feedback and patient history interface software, so Gadgetron will be an unique platform to curate imaging data, patient record and clinical feedback. With these three key ingredients, we plan to move into disease diagnosis and automated analysis fields (e.g. to predict cardiac outcome and classify whether a patient should receive intervention procedure). . Develop complete AI powered CMR analysis solution and deploy them to hospitals for daily usage, including cine, LGE, perfusion, T1/T2/T2* mapping, fat water imaging etc. The motivation here is to extract patient specific imaging information with full automation. These info will be used with patient history and cohort trained disease model. . Develop precision imaging on MR scanner for major cardiac disease. The target is to develop a patient specific model to predict a) whether a patient should receive intervention surgery or not; b) whether a patient will have cardiac events down the road. The technical route to achieve these are: 1) free-breathing CMR imaging; 2) AI derived imaging information and biomarkers; 3) Patient history and record received in Gadgetron; 4) Make prediction using cohort model with info from step 1-3. List of selected publications: Landmark detection in Cardiac Magnetic Resonance Imaging Using A Convolutional Neural Network. Hui Xue, Jessica Artico, Marianna Fontana, James C Moon, Rhodri H Davies, Peter Kellman. arXiv:2008.06142 eess.IV (under review). Automated Inline Analysis of Myocardial Perfusion MRI with Deep Learning. Hui Xue, Rhodri Davies, Louis AE Brown, Kristopher D Knott, Tushar Kotecha, Marianna Fontana, Sven Plein, James C Moon, Peter Kellman. Radiology: Artificial Intelligence (In Press). arXiv:1911.00625 q-bio.QM. COVID-19: Myocardial injury in survivors. Daniel S. Knight , Tushar Kotecha , Yousuf Razvi , Liza Chacko , James T. Brown , Paramjit S. Jeetley , James Goldring , Michael Jacobs , Lucy E. Lamb , Rupert Negus , Anthony Wolff , James C. Moon , Hui Xue , Peter Kellman , Niket Patel , and Marianna Fontana. Circulation, https://doi.org/10.1161/CIRCULATIONAHA.120.049252 Automated detection of left ventricle in arterial input function images for inline perfusion mapping using deep learning: A study of 15,000 patients. Hui Xue, Ethan Tseng, Kristopher D Knott, Tushar Kotecha, Louise Brown, Sven Plein, Marianna Fontana, James C Moon, Peter Kellman. Magnetic Resonance in Medicine, Volume84, Issue 5, November 2020, Pages 2788-2800. The prognostic significance of quantitative myocardial perfusion: an artificial intelligencebased approach using perfusion mapping. Kristopher D Knott, Andreas Seraphim, Joao B Augusto, Hui Xue, Liza Chacko, Nay Aung, Steffen E Petersen, Jackie A Cooper, Charlotte Manisty, Anish N Bhuva, Tushar Kotecha, Christos V Bourantas, Rhodri H Davies, Louise AE Brown, Sven Plein, Marianna Fontana, Peter Kellman, James C Moon. Circulation. 2020;141:12821291. Media press: https://www.newscientist.com/article/2224403-an-ai-doctor-is-analysing-heart-scans-in-dozens-of-hospitals/#ixzz6VfVSiMrH https://www.beckershospitalreview.com/artificial-intelligence/ai-measures-blood-flow-in-real-time-predicting-heart-attack-and-stroke-study-finds.html https://time.com/5784090/ai-heart-attack-stroke/