Assessing the Potential of a Deep Learning Tool to Improve Fracture Detection by Radiologists and Emergency Physicians on Extremity Radiographs

医学 射线照相术 接收机工作特性 急诊分诊台 放射科 急诊科 考试(生物学) 诊断准确性 核医学 回顾性队列研究 医学物理学 急诊医学 外科 内科学 古生物学 精神科 生物
作者
Tianyuan Fu,Vidya Sankar Viswanathan,Alexandre Attia,Elie Zerbib-Attal,Vijaya Kosaraju,Richard Barger,Julien Vidal,Leonardo Kayat Bittencourt,Navid Faraji
出处
期刊:Academic Radiology [Elsevier]
卷期号:31 (5): 1989-1999 被引量:3
标识
DOI:10.1016/j.acra.2023.10.042
摘要

Rationale and Objectives To evaluate the standalone performance of a deep learning (DL) based fracture detection tool on extremity radiographs and assess the performance of radiologists and emergency physicians in identifying fractures of the extremities with and without the DL aid. Materials and Methods The DL tool was previously developed using 132,000 appendicular skeletal radiographs divided into 87% training, 11% validation, and 2% test sets. Stand-alone performance was evaluated on 2626 de-identified radiographs from a single institution in Ohio, including at least 140 exams per body region. Consensus from three US board-certified musculoskeletal (MSK) radiologists served as ground truth. A multi-reader retrospective study was performed in which 24 readers (eight each of emergency physicians, non-MSK radiologists, and MSK radiologists) identified fractures in 186 cases during two independent sessions with and without DL aid, separated by a one-month washout period. The accuracy (area under the receiver operating curve), sensitivity, specificity, and reading time were compared with and without model aid. Results The model achieved a stand-alone accuracy of 0.986, sensitivity of 0.987, and specificity of 0.885, and high accuracy (> 0.95) across stratification for body part, age, gender, radiographic views, and scanner type. With DL aid, reader accuracy increased by 0.047 (95% CI: 0.034, 0.061; p = 0.004) and sensitivity significantly improved from 0.865 (95% CI: 0.848, 0.881) to 0.955 (95% CI: 0.944, 0.964). Average reading time was shortened by 7.1 s (27%) per exam. When stratified by physician type, this improvement was greater for emergency physicians and non-MSK radiologists. Conclusion The DL tool demonstrated high stand-alone accuracy, aided physician diagnostic accuracy, and decreased interpretation time. To evaluate the standalone performance of a deep learning (DL) based fracture detection tool on extremity radiographs and assess the performance of radiologists and emergency physicians in identifying fractures of the extremities with and without the DL aid. The DL tool was previously developed using 132,000 appendicular skeletal radiographs divided into 87% training, 11% validation, and 2% test sets. Stand-alone performance was evaluated on 2626 de-identified radiographs from a single institution in Ohio, including at least 140 exams per body region. Consensus from three US board-certified musculoskeletal (MSK) radiologists served as ground truth. A multi-reader retrospective study was performed in which 24 readers (eight each of emergency physicians, non-MSK radiologists, and MSK radiologists) identified fractures in 186 cases during two independent sessions with and without DL aid, separated by a one-month washout period. The accuracy (area under the receiver operating curve), sensitivity, specificity, and reading time were compared with and without model aid. The model achieved a stand-alone accuracy of 0.986, sensitivity of 0.987, and specificity of 0.885, and high accuracy (> 0.95) across stratification for body part, age, gender, radiographic views, and scanner type. With DL aid, reader accuracy increased by 0.047 (95% CI: 0.034, 0.061; p = 0.004) and sensitivity significantly improved from 0.865 (95% CI: 0.848, 0.881) to 0.955 (95% CI: 0.944, 0.964). Average reading time was shortened by 7.1 s (27%) per exam. When stratified by physician type, this improvement was greater for emergency physicians and non-MSK radiologists. The DL tool demonstrated high stand-alone accuracy, aided physician diagnostic accuracy, and decreased interpretation time.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
更新
大幅提高文件上传限制,最高150M (2024-4-1)

科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
zhengmin发布了新的文献求助10
刚刚
1秒前
haifang发布了新的文献求助10
1秒前
1秒前
Membranes完成签到,获得积分10
3秒前
3秒前
香蕉觅云应助qi采纳,获得10
4秒前
看论文发布了新的文献求助20
4秒前
4秒前
SBGLP发布了新的文献求助10
5秒前
5秒前
5秒前
小旺旺发布了新的文献求助20
5秒前
7秒前
超级水壶发布了新的文献求助10
8秒前
shice951229完成签到,获得积分10
8秒前
tracy10完成签到,获得积分10
9秒前
mm发布了新的文献求助10
9秒前
10秒前
脑洞疼应助高兴的万宝路采纳,获得10
11秒前
矮小的茹妖完成签到 ,获得积分10
11秒前
12秒前
金。。。完成签到,获得积分10
14秒前
tracy10发布了新的文献求助10
15秒前
bkagyin应助暴躁的信封采纳,获得10
15秒前
NexusExplorer应助杜晓雯采纳,获得10
15秒前
GU发布了新的文献求助10
16秒前
Stanford完成签到,获得积分10
17秒前
子车茗应助苗儿采纳,获得10
17秒前
雷家发布了新的文献求助10
19秒前
Simons完成签到,获得积分10
19秒前
plain完成签到,获得积分10
20秒前
20秒前
万能图书馆应助自由千风采纳,获得10
20秒前
Jasper应助123采纳,获得10
21秒前
汉堡包应助开心小小采纳,获得10
23秒前
Stanford发布了新的文献求助10
23秒前
23秒前
dpp发布了新的文献求助10
24秒前
柳炳完成签到 ,获得积分10
25秒前
高分求助中
Evolution 10000
Sustainability in Tides Chemistry 2800
The Young builders of New china : the visit of the delegation of the WFDY to the Chinese People's Republic 1000
юрские динозавры восточного забайкалья 800
English Wealden Fossils 700
Foreign Policy of the French Second Empire: A Bibliography 500
Chen Hansheng: China’s Last Romantic Revolutionary 500
热门求助领域 (近24小时)
化学 医学 生物 材料科学 工程类 有机化学 生物化学 物理 内科学 纳米技术 计算机科学 化学工程 复合材料 基因 遗传学 催化作用 物理化学 免疫学 量子力学 细胞生物学
热门帖子
关注 科研通微信公众号,转发送积分 3146297
求助须知:如何正确求助?哪些是违规求助? 2797687
关于积分的说明 7825144
捐赠科研通 2454059
什么是DOI,文献DOI怎么找? 1305990
科研通“疑难数据库(出版商)”最低求助积分说明 627630
版权声明 601503