How AI May Transform Musculoskeletal Imaging

被引：22

作者：

Guermazi, Ali ^{[1
,2
]}

Omoumi, Patrick ^{[3
,4
]}

Tordjman, Mickael ^{[5
,6
]}

Fritz, Jan ^{[7
]}

Kijowski, Richard ^{[7
]}

Regnard, Nor-Eddine ^{[8
,9
,10
]}

Carrino, John ^{[11
,12
]}

Kahn, Charles E., Jr. ^{[13
,14
]}

Knoll, Florian ^{[15
,17
]}

Rueckert, Daniel ^{[18
,19
]}

Roemer, Frank W. ^{[1
,16
]}

Hayashi, Daichi ^{[1
,20
]}

机构：

[1] Boston Univ, Sch Med, Dept Radiol, Boston, MA 02215 USA

[2] VA Boston Healthcare Syst, Dept Radiol, 1400 VFW Pkwy,Suite 1B105, West Roxbury, MA 02132 USA

[3] Lausanne Univ Hosp, Dept Radiol, Lausanne, Switzerland

[4] Univ Lausanne, Lausanne, Switzerland

[5] Hop Hotel Dieu, Dept Radiol, Paris, France

[6] Univ Paris Cite, Paris, France

[7] NYU, Grossman Sch Med, Dept Radiol, New York, NY USA

[8] Gleamer, Paris, France

[9] Clin Mousseau Ramsay Sante, Clin Mousseau Ramsay St, Evry, France

[10] Pole Med Senart, Lieusaint, France

[11] Hosp Special Surg, Dept Radiol & Imaging, New York, NY USA

[12] Weill Cornell Med, New York, NY USA

[13] Univ Penn, Dept Radiol, Philadelphia, PA USA

[14] Univ Penn, Inst Biomed Informat, Philadelphia, PA USA

[15] Univ Klinikum Erlangen, Dept Artificial Intelligence Biomed Engn, Erlangen, Germany

[16] Univ Klinikum Erlangen, Dept Radiol, Erlangen, Germany

[17] Friedrich Alexander Univ Erlangen Nurnberg, Erlangen, Germany

[18] Tech Univ Munich, Klinikum Rechts Isar, Sch Med & Computat Informat, Munich, Germany

[19] Imperial Coll London, Dept Comp, London, England

[20] Tufts Univ, Tufts Med Ctr, Sch Med, Dept Radiol, Boston, MA USA

来源：

RADIOLOGY | 2024年 / 310卷 / 01期

基金：

“创新英国”项目; 英国工程与自然科学研究理事会; 英国惠康基金;

关键词：

METAL ARTIFACT CORRECTION; ARTIFICIAL-INTELLIGENCE; SIMULTANEOUS MULTISLICE; HIP-ARTHROPLASTY; DECISION-SUPPORT; KNEE MRI; RADIOLOGY; DIAGNOSIS; WORKFLOW; OPTIMIZATION;

D O I：

10.1148/radiol.230764

中图分类号：

R8 [特种医学]; R445 [影像诊断学];

学科分类号：

1002 ; 100207 ; 1009 ;

摘要：

While musculoskeletal imaging volumes are increasing, there is a relative shortage of subspecialized musculoskeletal radiologists to interpret the studies. Will artificial intelligence (AI) be the solution? For AI to be the solution, the wide implementation of AI-supported data acquisition methods in clinical practice requires establishing trusted and reliable results. This implementation will demand close collaboration between core AI researchers and clinical radiologists. Upon successful clinical implementation, a wide variety of AI-based tools can improve the musculoskeletal radiologist's workflow by triaging imaging examinations, helping with image interpretation, and decreasing the reporting time. Additional AI applications may also be helpful for business, education, and research purposes if successfully integrated into the daily practice of musculoskeletal radiology. The question is not whether AI will replace radiologists, but rather how musculoskeletal radiologists can take advantage of AI to enhance their expert capabilities.

引用

页数：13

共 129 条

[21] Super-resolution musculoskeletal MRI using deep learning [J].