artificial intelligence augmentation of radiologist performance in distinguishing covid-19 from pneumonia of other origin at chest ct.-360期刊网

您当前的位置: 首页 > SCI文献 > Artificial Intelligence Augmentation of Radiologist Performance in Distinguishing COVID-19 from Pneumonia of Other Origin at Chest CT.

Artificial Intelligence Augmentation of Radiologist Performance in Distinguishing COVID-19 from Pneumonia of Other Origin at Chest CT.

影响因子：29.146 DOI：10.1148/radiol.2020201491

作者： Bai HX,Wang R,Xiong Z,Hsieh B,Chang K,Halsey K,Tran TML,Choi JW,Wang DC,Shi LB,Mei J,Jiang XL,Pan I,Zeng QH,Hu PF,Li YH,Fu FX,Huang RY,Sebro R,Yu QZ,Atalay MK,Liao WH 发表时间：2020-08-29 10:55:52

from：《RADIOLOGY》

keywords： Bai HXWang RXiong ZHsieh BChang KHalsey KTran TMLChoi JWWang DCShi LBMei JJiang XLPan IZeng QHHu PFLi YHFu FXHuang RYSebro RYu QZAtalay MKLiao WH

关键词：

Abstract

:Background Coronavirus disease 2019 (COVID-19) and pneumonia of other diseases share similar CT characteristics, which contributes to the challenges in differentiating them with high accuracy. Purpose To establish and evaluate an artificial intelligence (AI) system for differentiating COVID-19 and other pneumonia at chest CT and assessing radiologist performance without and with AI assistance. Materials and Methods A total of 521 patients with positive reverse transcription polymerase chain reaction results for COVID-19 and abnormal chest CT findings were retrospectively identified from 10 hospitals from January 2020 to April 2020. A total of 665 patients with non-COVID-19 pneumonia and definite evidence of pneumonia at chest CT were retrospectively selected from three hospitals between 2017 and 2019. To classify COVID-19 versus other pneumonia for each patient, abnormal CT slices were input into the EfficientNet B4 deep neural network architecture after lung segmentation, followed by a two-layer fully connected neural network to pool slices together. The final cohort of 1186 patients (132 583 CT slices) was divided into training, validation, and test sets in a 7:2:1 and equal ratio. Independent testing was performed by evaluating model performance in separate hospitals. Studies were blindly reviewed by six radiologists without and then with AI assistance. Results The final model achieved a test accuracy of 96% (95% confidence interval [CI]: 90%, 98%), a sensitivity of 95% (95% CI: 83%, 100%), and a specificity of 96% (95% CI: 88%, 99%) with area under the receiver operating characteristic curve of 0.95 and area under the precision-recall curve of 0.90. On independent testing, this model achieved an accuracy of 87% (95% CI: 82%, 90%), a sensitivity of 89% (95% CI: 81%, 94%), and a specificity of 86% (95% CI: 80%, 90%) with area under the receiver operating characteristic curve of 0.90 and area under the precision-recall curve of 0.87. Assisted by the probabilities of the model, the radiologists achieved a higher average test accuracy (90% vs 85%, Δ = 5, P < .001), sensitivity (88% vs 79%, Δ = 9, P < .001), and specificity (91% vs 88%, Δ = 3, P = .001). Conclusion Artificial intelligence assistance improved radiologists' performance in distinguishing coronavirus disease 2019 pneumonia from non-coronavirus disease 2019 pneumonia at chest CT. © RSNA, 2020 Online supplemental material is available for this article.

摘要

期刊介绍

《RADIOLOGY》 (点击进入期刊详情)

英文简介 : Published regularly since 1923 by the Radiological Society of North America (RSNA), Radiology has long been recognized as the authoritative reference for the most current, clinically relevant and highest quality research in the field of radiology. Each month the journal publishes approximately 300 pages of peer-reviewed original research, authoritative reviews, well-balanced commentary on significant articles, and expert opinion on new techniques and technologies. Radiology is published 12 times a year, online and in print, and has an impact factor of 7.296 making it one of the top cited journals in the field.

中文简介 : （来自Google、百度翻译）自1923年北美放射学会(RSNA)定期出版以来，放射学一直被公认为放射学领域最新、临床相关和最高质量研究的权威参考。每个月，该杂志发表约300页的同行评审的原始研究，权威的评论，对重要文章的良好平衡的评论，以及对新技术和技术的专家意见。放射学每年出版12次，在线出版和印刷出版，其影响因子为7.296，是该领域内被引用次数最多的期刊之一。

CIRCULATION RESEARCH 期刊中科院评价数据

新中科院分区

大类(学科)	小类(学科)	学科排名
医学	RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING (核医学)	4/129

新发布的期刊年发文量

年度总发文量	年度论文发表量	年度综述发表量
340	322	18

总被引频次 :54641

特征因子 : 0.061300

影响因子趋势图

影响因子：1.44 DOI：10.1080/14767058.2018.1488961 来源期刊：PubMed

作者：Yılmaz Semerci S,Yücel B,Erbas IM,Gunkaya OS,Talmac M,Çetinkaya M 发表时间：2020-07-14 09:42:48

Journal of the Pediatric Infectious Diseases Society

影响因子：1.82 DOI：10.1093/jpids/piy107 来源期刊：PubMed

作者：Boonyaratanakornkit J,Englund JA,Magaret AS,Bu Y,Tielsch JM,Khatry SK,Katz J,Kuypers J,Shrestha L,LeClerq SC,Steinhoff MC,Chu HY 发表时间：2020-07-14 09:42:48

Journal of the Pediatric Infectious Diseases Society

影响因子：1.82 DOI：10.1093/jpids/piy118 来源期刊：PubMed

作者：Kitt E,Drew RJ,Cunney R,Beekmann SE,Polgreen P,Butler K,Zaoutis T,Coffin SE 发表时间：2020-07-14 09:42:48

Medical mycology

影响因子：2.79 DOI：10.1093/mmy/myz015 来源期刊：PubMed

作者：Patel D,Popple S,Claydon A,Modha DE,Gaillard EA 发表时间：2020-07-14 09:42:48

Journal of infection and chemotherapy : official journal of the Japan Society of Chemotherapy

影响因子：1.67 DOI：10.1016/j.jiac.2019.07.001 来源期刊：PubMed

作者：Igari H,Yamagishi K,Yamazaki S,Murata S,Yahaba M,Takayanagi S,Kawasaki Y,Taniguchi T 发表时间：2020-07-14 09:42:48

The Annals of thoracic surgery

影响因子：1.80 DOI：10.1016/j.athoracsur.2019.06.042 来源期刊：PubMed

作者：Stephens EH,Eltayeb O,Mongé MC,Forbess JM,Rastatter JC,Rigsby CK,Backer CL 发表时间：2020-07-14 09:42:48

European radiology

影响因子：4.08 DOI：10.1007/s00330-019-06412-4 来源期刊：PubMed

作者：Kim C,Do KH,Cha J,Song JW,Lee SM,Lee KY 发表时间：2020-07-14 09:42:48

The New England journal of medicine

影响因子：16.10 DOI：10.1056/NEJMoa1911614 来源期刊：PubMed

作者：Layden JE,Ghinai I,Pray I,Kimball A,Layer M,Tenforde MW,Navon L,Hoots B,Salvatore PP,Elderbrook M,Haupt T,Kanne J,Patel MT,Saathoff-Huber L,King BA,Schier JG,Mikosz CA,Meiman J 发表时间：2020-07-14 09:42:48

American journal of respiratory and critical care medicine

影响因子：5.24 DOI：10.1164/rccm.201904-0826OC 来源期刊：PubMed

作者：Critser PJ,Higano NS,Tkach JA,Olson ES,Spielberg DR,Kingma PS,Fleck RJ,Lang SM,Moore RA,Taylor MD,Woods JC 发表时间：2020-07-14 09:42:48

The Annals of otology, rhinology, and laryngology

影响因子：1.59 DOI：10.1177/0003489419880576 来源期刊：PubMed

作者：Patel A,Levi JR,Brook CD 发表时间：2020-07-14 09:42:48

服务推荐

基础SCI服务

医学领域资深专家团队

临床科研服务

一对一跟进，沉淀是辅导

课题基金服务

创新思路，真实数据

SCI论文翻译润色

母语化翻译润色