Surgical data science-from concepts toward clinical translation

被引：142

作者：

Maier-Hein, Lena ^{[1
,2
,3
]}

Eisenmann, Matthias ^{[1
]}

Sarikaya, Duygu ^{[4
,5
]}

Maerz, Keno ^{[1
]}

Collins, Toby ^{[6
]}

Malpani, Anand ^{[7
]}

Fallert, Johannes ^{[8
]}

Feussner, Hubertus ^{[9
]}

Giannarou, Stamatia ^{[10
]}

Mascagni, Pietro ^{[11
,12
]}

Nakawala, Hirenkumar ^{[13
]}

Park, Adrian ^{[14
,15
]}

Pugh, Carla ^{[16
]}

Stoyanov, Danail ^{[17
]}

Vedula, Swaroop S. ^{[7
]}

Cleary, Kevin ^{[19
]}

Fichtinger, Gabor ^{[20
]}

Forestier, Germain ^{[21
,22
]}

Gibaud, Bernard ^{[5
]}

Grantcharov, Teodor ^{[23
,24
]}

Hashizume, Makoto ^{[25
,26
]}

Heckmann-Noetzel, Doreen ^{[1
]}

Kenngott, Hannes G. ^{[18
]}

Kikinis, Ron ^{[27
,28
]}

Muendermann, Lars ^{[8
]}

Navab, Nassir ^{[29
,30
]}

Onogur, Sinan ^{[1
]}

Ross, Tobias ^{[1
,3
]}

Sznitman, Raphael ^{[31
]}

Taylor, Russell H. ^{[30
]}

Tizabi, Minu D. ^{[1
]}

Wagner, Martin ^{[18
]}

Hager, Gregory D. ^{[7
,30
]}

Neumuth, Thomas ^{[32
]}

Padoy, Nicolas ^{[11
,12
]}

Collins, Justin ^{[33
]}

Gockel, Ines ^{[34
]}

Goedeke, Jan ^{[35
]}

Hashimoto, Daniel A. ^{[28
,36
,37
]}

Joyeux, Luc ^{[38
,39
,40
,41
,42
]}

Lam, Kyle ^{[43
]}

Leff, Daniel R. ^{[10
,44
,45
]}

Madani, Amin ^{[46
]}

Marcus, Hani J. ^{[47
,48
]}

Meireles, Ozanan ^{[28
,49
]}

Seitel, Alexander ^{[1
]}

Teber, Dogu ^{[50
]}

Ueckert, Frank ^{[51
]}

Mueller-Stich, Beat P. ^{[18
]}

Jannin, Pierre ^{[5
]}

机构：

[1] German Canc Res Ctr, Div Comp Assisted Med Intervent CAMI, Heidelberg, Germany

[2] Heidelberg Univ, Fac Math & Comp Sci, Heidelberg, Germany

[3] Heidelberg Univ, Med Fac, Heidelberg, Germany

[4] Gazi Univ, Fac Engn, Dept Comp Engn, Ankara, Turkey

[5] Univ Rennes 1, UMR 1099, INSERM, LTSI, Rennes, France

[6] IRCAD, Strasbourg, France

[7] Johns Hopkins Univ, Malone Ctr Engn Healthcare, Baltimore, MD USA

[8] KARL STORZ SE & Co KG, Tuttlingen, Germany

[9] Tech Univ Munich, Dept Surg, Klinikum Rechts Isar, Munich, Germany

[10] Imperial Coll London, Hamlyn Ctr Robot Surg, London, England

[11] Univ Strasbourg, CNRS, ICube, Strasbourg, France

[12] IHU Strasbourg, Strasbourg, France

[13] Univ Verona, Altair Robot Lab, Verona, Italy

[14] Anne Arundel Hlth Syst, Dept Surg, Annapolis, MD USA

[15] Johns Hopkins Univ, Sch Med, Baltimore, MD USA

[16] Stanford Univ, Dept Surg, Sch Med, Stanford, CA USA

[17] UCL, Wellcome EPSRC Ctr Intervent & Surg Sci, London, England

[18] Heidelberg Univ Hosp, Dept Gen Visceral & Transplantat Surg, Heidelberg, Germany

[19] Childrens Natl Hosp, Sheikh Zayed Inst Pediat Surg Innovat, Washington, DC USA

[20] Queens Univ, Perk Lab, Kingston, ON, Canada

[21] Univ Haute Alsace, Inst Rech Informat Math Automat & Signal IRIMAS, Mulhouse, France

[22] Monash Univ, Fac Informat Technol, Clayton, Vic, Australia

[23] Univ Toronto, Toronto, ON, Canada

[24] St Michaels Hosp, Li Ka Shing Knowledge Inst, Toronto, ON, Canada

[25] Kyushu Univ, Fukuoka, Japan

[26] Kitakyushu Koga Hosp, Fukuoka, Japan

[27] Brigham & Womens Hosp, Dept Radiol, 75 Francis St, Boston, MA 02115 USA

[28] Harvard Med Sch, Boston, MA 02115 USA

[29] Tech Univ Munich, Comp Aided Med Procedures, Munich, Germany

[30] Johns Hopkins Univ, Dept Comp Sci, Baltimore, MD 21218 USA

[31] Univ Bern, ARTORG Ctr Biomed Engn Res, Bern, Switzerland

[32] Univ Leipzig, Innovat Ctr Comp Assisted Surg ICCAS, Leipzig, Germany

[33] UCL, Div Surg & Intervent Sci, London, England

[34] Leipzig Univ Hosp, Dept Visceral Transplant Thorac & Vasc Surg, Leipzig, Germany

[35] Ludwig Maximilians Univ Munchen, Dr von Hauner Childrens Hosp, Pediat Surg, Munich, Germany

[36] Case Western Reserve Univ, Univ Hosp Cleveland, Med Ctr, Cleveland, OH 44106 USA

[37] Massachusetts Gen Hosp, Surg AI & Innovat Lab, Boston, MA 02114 USA

[38] Katholieke Univ Leuven, Dept Dev & Regenerat, My FetUZ Fetal Res Ctr, Biomed Sci, Leuven, Belgium

[39] Katholieke Univ Leuven, Ctr Surg Technol, Fac Med, Leuven, Belgium

[40] Univ Hosp Leuven, Dept Obstet & Gynecol, Div Woman & Child, Fetal Med Unit, Leuven, Belgium

[41] Texas Childrens Hosp, Michael E DeBakey Dept Surg, Houston, TX 77030 USA

[42] Baylor Coll Med, Houston, TX 77030 USA

[43] Imperial Coll London, Dept Surg & Canc, London, England

[44] Imperial Coll London, Dept BioSurg & Surg Technol, London, England

[45] Imperial Healthcare NHS Trust, Breast Unit, London, England

[46] Univ Hlth Network, Dept Surg, Toronto, ON, Canada

[47] Natl Hosp Neurol & Neurosurg, London, England

[48] UCL Queen Sq Inst Neurol, London, England

[49] Massachusetts Gen Hosp, Boston, MA 02114 USA

[50] City Hosp Karlsruhe, Dept Urol, Karlsruhe, Germany

来源：

MEDICAL IMAGE ANALYSIS | 2022年 / 76卷

基金：

英国工程与自然科学研究理事会; 加拿大自然科学与工程研究理事会; 美国国家卫生研究院; 欧洲研究理事会; 欧盟地平线“2020”;

关键词：

Surgical data science; Artificial intelligence; Deep learning; Clinical translation; Computer aided surgery; OPERATING-ROOM; ARTIFICIAL-INTELLIGENCE; NEURAL-NETWORK; REAL-TIME; IBM WATSON; BIG DATA; SURGERY; SAFETY; RECOGNITION; PERFORMANCE;

D O I：

10.1016/j.media.2021.102306

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Recent developments in data science in general and machine learning in particular have transformed the way experts envision the future of surgery. Surgical Data Science (SDS) is a new research field that aims to improve the quality of interventional healthcare through the capture, organization, analysis and modeling of data. While an increasing number of data-driven approaches and clinical applications have been studied in the fields of radiological and clinical data science, translational success stories are still lacking in surgery. In this publication, we shed light on the underlying reasons and provide a roadmap for future advances in the field. Based on an international workshop involving leading researchers in the field of SDS, we review current practice, key achievements and initiatives as well as available standards and tools for a number of topics relevant to the field, namely (1) infrastructure for data acquisition, storage and access in the presence of regulatory constraints, (2) data annotation and sharing and (3) data analytics. We further complement this technical perspective with (4) a review of currently available SDS products and the translational progress from academia and (5) a roadmap for faster clinical translation and exploitation of the full potential of SDS, based on an international multi-round Delphi process.

引用

页数：46

共 458 条

[1] 3D slicer, 3D SLIC IM COMP PLAT
[2] AAMI, 2012, MED DEV INT
[3] Pivotal trial of an autonomous AI-based diagnostic system for detection of diabetic retinopathy in primary care offices
Abramoff, Michael D.
Lavin, Philip T.
Birch, Michele
Shah, Nilay
Folk, James C.
[J]. NPJ DIGITAL MEDICINE, 2018, 1
[4] ACS Committee on Trauma, STOP THE BLEED
[5] AdaptOR, DEEP GEN MOD CHALL D
[6] Adebayo J, 2018, ADV NEUR IN, V31
[7] Validation and Utility Testing of Clinical Prediction Models Time to Change the Approach
Adibi, Amin
Sadatsafavi, Mohsen
Ioannidis, John P. A.
[J]. JAMA-JOURNAL OF THE AMERICAN MEDICAL ASSOCIATION, 2020, 324 (03): : 235 - 236
[8] Uncertainty-aware performance assessment of optical imaging modalities with invertible neural networks
Adler, Tim J.
Ardizzone, Lynton
Vemuri, Anant
Ayala, Leonardo
Groehl, Janek
Kirchner, Thomas
Wirkert, Sebastian
Kruse, Jakob
Rother, Carsten
Koethe, Ullrich
Maier-Hein, Lena
[J]. INTERNATIONAL JOURNAL OF COMPUTER ASSISTED RADIOLOGY AND SURGERY, 2019, 14 (06) : 997 - 1007
[9] AI Medical Service Inc. (Tokyo Japan), AIM LIB CAT
[10] AIDA-E, AN IM DET ABN END AI

← 1 2 3 4 5 6 7 8 9 10 →