Heidelberg colorectal data set for surgical data science in the sensor operating room

被引：62

作者：

Maier-Hein, Lena ^{[1
]}

Wagner, Martin ^{[2
]}

Ross, Tobias ^{[1
,3
]}

Reinke, Annika ^{[1
,3
]}

Bodenstedt, Sebastian ^{[4
]}

Full, Peter M. ^{[3
,5
]}

Hempe, Hellena ^{[1
]}

Mindroc-Filimon, Diana ^{[1
]}

Scholz, Patrick ^{[1
,6
]}

Thuy Nuong Tran ^{[1
]}

Bruno, Pierangela ^{[1
,7
]}

Kisilenko, Anna ^{[2
]}

Mueller, Benjamin ^{[2
]}

Davitashvili, Tornike ^{[2
]}

Capek, Manuela ^{[2
]}

Tizabi, Minu D. ^{[1
]}

Eisenmann, Matthias ^{[1
]}

Adler, Tim J. ^{[1
]}

Groehl, Janek ^{[1
]}

Schellenberg, Melanie ^{[1
]}

Seidlitz, Silvia ^{[1
,6
]}

Lai, T. Y. Emmy ^{[5
]}

Pekdemir, Buenyamin ^{[1
]}

Roethlingshoefer, Veith ^{[8
]}

Both, Fabian ^{[8
,9
]}

Bittel, Sebastian ^{[8
,10
]}

Mengler, Marc ^{[8
]}

Muendermann, Lars ^{[11
]}

Apitz, Martin ^{[2
]}

Kopp-Schneider, Annette ^{[12
]}

Speidel, Stefanie ^{[4
,13
]}

Nickel, Felix ^{[2
]}

Probst, Pascal ^{[2
]}

Kenngott, Hannes G. ^{[2
]}

Mueller-Stich, Beat P. ^{[2
]}

机构：

[1] German Canc Res Ctr, Div Comp Assisted Med Intervent CAMI, Neuenheimer Feld 223, D-69120 Heidelberg, Germany

[2] Heidelberg Univ Hosp, Dept Gen Visceral & Transplantat Surg, Neuenheimer Feld 420, D-69120 Heidelberg, Germany

[3] Heidelberg Univ, Seminarstr 2, D-69117 Heidelberg, Germany

[4] Natl Ctr Tumor Dis, Partner Site Dresden, Div Translat Surg Oncol, Fetscherstr 74, D-01307 Dresden, Germany

[5] Div Med Image Comp MIC, Neuenheimer Feld 223, D-69120 Heidelberg, Germany

[6] HIDSS4Hlth Helmholtz Informat & Data Sci Sch Hlth, Neuenheimer Feld 223, D-69120 Heidelberg, Germany

[7] Univ Calabria, Dept Math & Comp Sci, Via Pietro Bucci, I-87036 Arcavacata Di Rende, CS, Italy

[8] understandAI GmbH, RaumFabr 34, D-76227 Karlsruhe, Germany

[9] Univ Tubingen, Int Max Planck Res Sch Intelligent Syst Tuebingen, Geschwister Scholl Pl, D-72074 Tubingen, Germany

[10] BMW Grp, Heidemannstr 164, D-80939 Munich, Germany

[11] KARL STORZ SE & Co KG, Corp Res & Technol, Data Assisted Solut, Dr Karl Storz Str 34, D-78532 Tuttlingen, Germany

[12] German Canc Res Ctr, Div Biostat, Neuenheimer Feld 581, D-69120 Heidelberg, Germany

[13] Tech Univ Dresden, Ctr Tactile Internet Human In The Loop CeTI, D-01307 Dresden, Germany

来源：

SCIENTIFIC DATA | 2021年 / 8卷 / 01期

关键词：

RECOGNITION;

D O I：

10.1038/s41597-021-00882-2

中图分类号：

O [数理科学和化学]; P [天文学、地球科学]; Q [生物科学]; N [自然科学总论];

学科分类号：

07 ; 0710 ; 09 ;

摘要：

Image-based tracking of medical instruments is an integral part of surgical data science applications. Previous research has addressed the tasks of detecting, segmenting and tracking medical instruments based on laparoscopic video data. However, the proposed methods still tend to fail when applied to challenging images and do not generalize well to data they have not been trained on. This paper introduces the Heidelberg Colorectal (HeiCo) data set - the first publicly available data set enabling comprehensive benchmarking of medical instrument detection and segmentation algorithms with a specific emphasis on method robustness and generalization capabilities. Our data set comprises 30 laparoscopic videos and corresponding sensor data from medical devices in the operating room for three different types of laparoscopic surgery. Annotations include surgical phase labels for all video frames as well as information on instrument presence and corresponding instance-wise segmentation masks for surgical instruments (if any) in more than 10,000 individual frames. The data has successfully been used to organize international competitions within the Endoscopic Vision Challenges 2017 and 2019.

引用

页数：11

共 20 条

[1] A Dataset and Benchmarks for Segmentation and Recognition of Gestures in Robotic Surgery [J].