RETOUCH: The Retinal OCT Fluid Detection and Segmentation Benchmark and Challenge

Hrvoje Bogunovic; Freerk Venhuizen; Sophie Klimscha; Stefanos Apostolopoulos; Alireza Bab-Hadiashar; Ulas Bagci; Mirza Faisal Beg; Loza Bekalo; Qiang Chen; Carlos Ciller; Karthik Gopinath; Amirali K. Gostar; Kiwan Jeon; Zexuan Ji; Sung Ho Kang; Dara D. Koozekanani; Donghuan Lu; Dustin Morley; Keshab K. Parhi; Hyoung Suk Park; Abdolreza Rashno; Marinko Sarunic; Saad Shaikh; Jayanthi Sivaswamy; Ruwan Tennakoon; Shivin Yadav; Sandro De Zanet; Sebastian M. Waldstein; Bianca S. Gerendas; Caroline Klaver; Clara I. Sanchez; Ursula Schmidt-Erfurth

doi:10.1109/TMI.2019.2901398

RETOUCH: The Retinal OCT Fluid Detection and Segmentation Benchmark and Challenge

Hrvoje Bogunovic, Freerk Venhuizen, Sophie Klimscha, Stefanos Apostolopoulos, Alireza Bab-Hadiashar, Ulas Bagci, Mirza Faisal Beg, Loza Bekalo, Qiang Chen, Carlos Ciller, Karthik Gopinath, Amirali K. Gostar, Kiwan Jeon, Zexuan Ji, Sung Ho Kang, Dara D. Koozekanani, Donghuan Lu, Dustin Morley, Keshab K. Parhi, Hyoung Suk ParkAbdolreza Rashno, Marinko Sarunic, Saad Shaikh, Jayanthi Sivaswamy, Ruwan Tennakoon, Shivin Yadav, Sandro De Zanet, Sebastian M. Waldstein, Bianca S. Gerendas, Caroline Klaver, Clara I. Sanchez, Ursula Schmidt-Erfurth

Research output: Contribution to journal › Article › peer-review

35 Scopus citations

Abstract

Retinal swelling due to the accumulation of fluid is associated with the most vision-threatening retinal diseases. Optical coherence tomography (OCT) is the current standard of care in assessing the presence and quantity of retinal fluid and image-guided treatment management. Deep learning methods have made their impact across medical imaging, and many retinal OCT analysis methods have been proposed. However, it is currently not clear how successful they are in interpreting the retinal fluid on OCT, which is due to the lack of standardized benchmarks. To address this, we organized a challenge RETOUCH in conjunction with MICCAI 2017, with eight teams participating. The challenge consisted of two tasks: fluid detection and fluid segmentation. It featured for the first time: all three retinal fluid types, with annotated images provided by two clinical centers, which were acquired with the three most common OCT device vendors from patients with two different retinal diseases. The analysis revealed that in the detection task, the performance on the automated fluid detection was within the inter-grader variability. However, in the segmentation task, fusing the automated methods produced segmentations that were superior to all individual methods, indicating the need for further improvements in the segmentation performance.

Original language	English (US)
Article number	8653407
Pages (from-to)	1858-1874
Number of pages	17
Journal	IEEE Transactions on Medical Imaging
Volume	38
Issue number	8
DOIs	https://doi.org/10.1109/TMI.2019.2901398
State	Published - Aug 2019

Bibliographical note

Funding Information:
Manuscript received November 13, 2018; revised February 13, 2019; accepted February 17, 2019. Date of publication February 26, 2019; date of current version July 31, 2019. The work of H. Bogunović, S. Klimscha, S. M. Waldstein, B. S. Gerendas, and U. Schmidt-Erfurth was supported in part by the Christian Doppler Research Association, in part by the Austrian Federal Ministry for Digital and Economic Affairs, and in part by the National Foundation for Research, Technology and Development. The work of F. Venhuizen and C. I. Sánchez was supported in part by the MD fonds, in part by the LSBS fonds, and in part by the OOG fonds through UitZicht. The work of K. Jeon, S. H. Kang, and H. S. Park was supported by the Korean Government through the National Institute for Mathematical Sciences under Grant B18130000. (Corresponding author: Hrvoje Bogunović) H. Bogunović, S. Klimscha, S. M. Waldstein, B. S. Gerendas, and U. Schmidt-Erfurth are with the Christian Doppler Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology, Medical University of Vienna, 1090 Vienna, Austria (e-mail: hrvoje.bogunovic@ meduniwien.ac.at).

Funding Information:
The work of H. Bogunovi?, S. Klimscha, S. M. Waldstein, B. S. Gerendas, and U. Schmidt-Erfurth was supported in part by the Christian Doppler Research Association, in part by the Austrian Federal Ministry for Digital and Economic Affairs, and in part by the National Foundation for Research, Technology and Development. The work of F. Venhuizen and C. I. S?nchez was supported in part by the MD fonds, in part by the LSBS fonds, and in part by the OOG fonds through UitZicht. The work of K. Jeon, S. H. Kang, and H. S. Park was supported by the Korean Government through the National Institute for Mathematical Sciences under Grant B18130000.

Publisher Copyright:
© 1982-2012 IEEE.

Keywords

Evaluation
image classification
image segmentation
optical coherence tomography
retina

Access

10.1109/TMI.2019.2901398

Fingerprint Dive into the research topics of 'RETOUCH: The Retinal OCT Fluid Detection and Segmentation Benchmark and Challenge'. Together they form a unique fingerprint.

Cite this

Bogunovic, H., Venhuizen, F., Klimscha, S., Apostolopoulos, S., Bab-Hadiashar, A., Bagci, U., Beg, M. F., Bekalo, L., Chen, Q., Ciller, C., Gopinath, K., Gostar, A. K., Jeon, K., Ji, Z., Kang, S. H., Koozekanani, D. D., Lu, D., Morley, D., Parhi, K. K., ... Schmidt-Erfurth, U. (2019). RETOUCH: The Retinal OCT Fluid Detection and Segmentation Benchmark and Challenge. IEEE Transactions on Medical Imaging, 38(8), 1858-1874. [8653407]. https://doi.org/10.1109/TMI.2019.2901398

RETOUCH : The Retinal OCT Fluid Detection and Segmentation Benchmark and Challenge. / Bogunovic, Hrvoje; Venhuizen, Freerk; Klimscha, Sophie; Apostolopoulos, Stefanos; Bab-Hadiashar, Alireza; Bagci, Ulas; Beg, Mirza Faisal; Bekalo, Loza; Chen, Qiang; Ciller, Carlos; Gopinath, Karthik; Gostar, Amirali K.; Jeon, Kiwan; Ji, Zexuan; Kang, Sung Ho; Koozekanani, Dara D.; Lu, Donghuan; Morley, Dustin; Parhi, Keshab K.; Park, Hyoung Suk; Rashno, Abdolreza; Sarunic, Marinko; Shaikh, Saad; Sivaswamy, Jayanthi; Tennakoon, Ruwan; Yadav, Shivin; De Zanet, Sandro; Waldstein, Sebastian M.; Gerendas, Bianca S.; Klaver, Caroline; Sanchez, Clara I.; Schmidt-Erfurth, Ursula.

In: IEEE Transactions on Medical Imaging, Vol. 38, No. 8, 8653407, 08.2019, p. 1858-1874.

Research output: Contribution to journal › Article › peer-review

Bogunovic, H, Venhuizen, F, Klimscha, S, Apostolopoulos, S, Bab-Hadiashar, A, Bagci, U, Beg, MF, Bekalo, L, Chen, Q, Ciller, C, Gopinath, K, Gostar, AK, Jeon, K, Ji, Z, Kang, SH, Koozekanani, DD, Lu, D, Morley, D, Parhi, KK, Park, HS, Rashno, A, Sarunic, M, Shaikh, S, Sivaswamy, J, Tennakoon, R, Yadav, S, De Zanet, S, Waldstein, SM, Gerendas, BS, Klaver, C, Sanchez, CI & Schmidt-Erfurth, U 2019, 'RETOUCH: The Retinal OCT Fluid Detection and Segmentation Benchmark and Challenge', IEEE Transactions on Medical Imaging, vol. 38, no. 8, 8653407, pp. 1858-1874. https://doi.org/10.1109/TMI.2019.2901398

Bogunovic, Hrvoje ; Venhuizen, Freerk ; Klimscha, Sophie ; Apostolopoulos, Stefanos ; Bab-Hadiashar, Alireza ; Bagci, Ulas ; Beg, Mirza Faisal ; Bekalo, Loza ; Chen, Qiang ; Ciller, Carlos ; Gopinath, Karthik ; Gostar, Amirali K. ; Jeon, Kiwan ; Ji, Zexuan ; Kang, Sung Ho ; Koozekanani, Dara D. ; Lu, Donghuan ; Morley, Dustin ; Parhi, Keshab K. ; Park, Hyoung Suk ; Rashno, Abdolreza ; Sarunic, Marinko ; Shaikh, Saad ; Sivaswamy, Jayanthi ; Tennakoon, Ruwan ; Yadav, Shivin ; De Zanet, Sandro ; Waldstein, Sebastian M. ; Gerendas, Bianca S. ; Klaver, Caroline ; Sanchez, Clara I. ; Schmidt-Erfurth, Ursula. / RETOUCH : The Retinal OCT Fluid Detection and Segmentation Benchmark and Challenge. In: IEEE Transactions on Medical Imaging. 2019 ; Vol. 38, No. 8. pp. 1858-1874.

@article{979cc362adfe4c2d918039be0b14e5cd,

title = "RETOUCH: The Retinal OCT Fluid Detection and Segmentation Benchmark and Challenge",

abstract = "Retinal swelling due to the accumulation of fluid is associated with the most vision-threatening retinal diseases. Optical coherence tomography (OCT) is the current standard of care in assessing the presence and quantity of retinal fluid and image-guided treatment management. Deep learning methods have made their impact across medical imaging, and many retinal OCT analysis methods have been proposed. However, it is currently not clear how successful they are in interpreting the retinal fluid on OCT, which is due to the lack of standardized benchmarks. To address this, we organized a challenge RETOUCH in conjunction with MICCAI 2017, with eight teams participating. The challenge consisted of two tasks: fluid detection and fluid segmentation. It featured for the first time: all three retinal fluid types, with annotated images provided by two clinical centers, which were acquired with the three most common OCT device vendors from patients with two different retinal diseases. The analysis revealed that in the detection task, the performance on the automated fluid detection was within the inter-grader variability. However, in the segmentation task, fusing the automated methods produced segmentations that were superior to all individual methods, indicating the need for further improvements in the segmentation performance.",

keywords = "Evaluation, image classification, image segmentation, optical coherence tomography, retina",

author = "Hrvoje Bogunovic and Freerk Venhuizen and Sophie Klimscha and Stefanos Apostolopoulos and Alireza Bab-Hadiashar and Ulas Bagci and Beg, {Mirza Faisal} and Loza Bekalo and Qiang Chen and Carlos Ciller and Karthik Gopinath and Gostar, {Amirali K.} and Kiwan Jeon and Zexuan Ji and Kang, {Sung Ho} and Koozekanani, {Dara D.} and Donghuan Lu and Dustin Morley and Parhi, {Keshab K.} and Park, {Hyoung Suk} and Abdolreza Rashno and Marinko Sarunic and Saad Shaikh and Jayanthi Sivaswamy and Ruwan Tennakoon and Shivin Yadav and {De Zanet}, Sandro and Waldstein, {Sebastian M.} and Gerendas, {Bianca S.} and Caroline Klaver and Sanchez, {Clara I.} and Ursula Schmidt-Erfurth",

note = "Funding Information: Manuscript received November 13, 2018; revised February 13, 2019; accepted February 17, 2019. Date of publication February 26, 2019; date of current version July 31, 2019. The work of H. Bogunovi{\'c}, S. Klimscha, S. M. Waldstein, B. S. Gerendas, and U. Schmidt-Erfurth was supported in part by the Christian Doppler Research Association, in part by the Austrian Federal Ministry for Digital and Economic Affairs, and in part by the National Foundation for Research, Technology and Development. The work of F. Venhuizen and C. I. S{\'a}nchez was supported in part by the MD fonds, in part by the LSBS fonds, and in part by the OOG fonds through UitZicht. The work of K. Jeon, S. H. Kang, and H. S. Park was supported by the Korean Government through the National Institute for Mathematical Sciences under Grant B18130000. (Corresponding author: Hrvoje Bogunovi{\'c}) H. Bogunovi{\'c}, S. Klimscha, S. M. Waldstein, B. S. Gerendas, and U. Schmidt-Erfurth are with the Christian Doppler Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology, Medical University of Vienna, 1090 Vienna, Austria (e-mail: hrvoje.bogunovic@ meduniwien.ac.at). Funding Information: The work of H. Bogunovi?, S. Klimscha, S. M. Waldstein, B. S. Gerendas, and U. Schmidt-Erfurth was supported in part by the Christian Doppler Research Association, in part by the Austrian Federal Ministry for Digital and Economic Affairs, and in part by the National Foundation for Research, Technology and Development. The work of F. Venhuizen and C. I. S?nchez was supported in part by the MD fonds, in part by the LSBS fonds, and in part by the OOG fonds through UitZicht. The work of K. Jeon, S. H. Kang, and H. S. Park was supported by the Korean Government through the National Institute for Mathematical Sciences under Grant B18130000. Publisher Copyright: {\textcopyright} 1982-2012 IEEE.",

year = "2019",

month = aug,

doi = "10.1109/TMI.2019.2901398",

language = "English (US)",

volume = "38",

pages = "1858--1874",

journal = "IEEE Transactions on Medical Imaging",

issn = "0278-0062",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

number = "8",

}

TY - JOUR

T1 - RETOUCH

T2 - The Retinal OCT Fluid Detection and Segmentation Benchmark and Challenge

AU - Bogunovic, Hrvoje

AU - Venhuizen, Freerk

AU - Klimscha, Sophie

AU - Apostolopoulos, Stefanos

AU - Bab-Hadiashar, Alireza

AU - Bagci, Ulas

AU - Beg, Mirza Faisal

AU - Bekalo, Loza

AU - Chen, Qiang

AU - Ciller, Carlos

AU - Gopinath, Karthik

AU - Gostar, Amirali K.

AU - Jeon, Kiwan

AU - Ji, Zexuan

AU - Kang, Sung Ho

AU - Koozekanani, Dara D.

AU - Lu, Donghuan

AU - Morley, Dustin

AU - Parhi, Keshab K.

AU - Park, Hyoung Suk

AU - Rashno, Abdolreza

AU - Sarunic, Marinko

AU - Shaikh, Saad

AU - Sivaswamy, Jayanthi

AU - Tennakoon, Ruwan

AU - Yadav, Shivin

AU - De Zanet, Sandro

AU - Waldstein, Sebastian M.

AU - Gerendas, Bianca S.

AU - Klaver, Caroline

AU - Sanchez, Clara I.

AU - Schmidt-Erfurth, Ursula

N1 - Funding Information: Manuscript received November 13, 2018; revised February 13, 2019; accepted February 17, 2019. Date of publication February 26, 2019; date of current version July 31, 2019. The work of H. Bogunović, S. Klimscha, S. M. Waldstein, B. S. Gerendas, and U. Schmidt-Erfurth was supported in part by the Christian Doppler Research Association, in part by the Austrian Federal Ministry for Digital and Economic Affairs, and in part by the National Foundation for Research, Technology and Development. The work of F. Venhuizen and C. I. Sánchez was supported in part by the MD fonds, in part by the LSBS fonds, and in part by the OOG fonds through UitZicht. The work of K. Jeon, S. H. Kang, and H. S. Park was supported by the Korean Government through the National Institute for Mathematical Sciences under Grant B18130000. (Corresponding author: Hrvoje Bogunović) H. Bogunović, S. Klimscha, S. M. Waldstein, B. S. Gerendas, and U. Schmidt-Erfurth are with the Christian Doppler Laboratory for Ophthalmic Image Analysis, Department of Ophthalmology, Medical University of Vienna, 1090 Vienna, Austria (e-mail: hrvoje.bogunovic@ meduniwien.ac.at). Funding Information: The work of H. Bogunovi?, S. Klimscha, S. M. Waldstein, B. S. Gerendas, and U. Schmidt-Erfurth was supported in part by the Christian Doppler Research Association, in part by the Austrian Federal Ministry for Digital and Economic Affairs, and in part by the National Foundation for Research, Technology and Development. The work of F. Venhuizen and C. I. S?nchez was supported in part by the MD fonds, in part by the LSBS fonds, and in part by the OOG fonds through UitZicht. The work of K. Jeon, S. H. Kang, and H. S. Park was supported by the Korean Government through the National Institute for Mathematical Sciences under Grant B18130000. Publisher Copyright: © 1982-2012 IEEE.

PY - 2019/8

Y1 - 2019/8

N2 - Retinal swelling due to the accumulation of fluid is associated with the most vision-threatening retinal diseases. Optical coherence tomography (OCT) is the current standard of care in assessing the presence and quantity of retinal fluid and image-guided treatment management. Deep learning methods have made their impact across medical imaging, and many retinal OCT analysis methods have been proposed. However, it is currently not clear how successful they are in interpreting the retinal fluid on OCT, which is due to the lack of standardized benchmarks. To address this, we organized a challenge RETOUCH in conjunction with MICCAI 2017, with eight teams participating. The challenge consisted of two tasks: fluid detection and fluid segmentation. It featured for the first time: all three retinal fluid types, with annotated images provided by two clinical centers, which were acquired with the three most common OCT device vendors from patients with two different retinal diseases. The analysis revealed that in the detection task, the performance on the automated fluid detection was within the inter-grader variability. However, in the segmentation task, fusing the automated methods produced segmentations that were superior to all individual methods, indicating the need for further improvements in the segmentation performance.

AB - Retinal swelling due to the accumulation of fluid is associated with the most vision-threatening retinal diseases. Optical coherence tomography (OCT) is the current standard of care in assessing the presence and quantity of retinal fluid and image-guided treatment management. Deep learning methods have made their impact across medical imaging, and many retinal OCT analysis methods have been proposed. However, it is currently not clear how successful they are in interpreting the retinal fluid on OCT, which is due to the lack of standardized benchmarks. To address this, we organized a challenge RETOUCH in conjunction with MICCAI 2017, with eight teams participating. The challenge consisted of two tasks: fluid detection and fluid segmentation. It featured for the first time: all three retinal fluid types, with annotated images provided by two clinical centers, which were acquired with the three most common OCT device vendors from patients with two different retinal diseases. The analysis revealed that in the detection task, the performance on the automated fluid detection was within the inter-grader variability. However, in the segmentation task, fusing the automated methods produced segmentations that were superior to all individual methods, indicating the need for further improvements in the segmentation performance.

KW - Evaluation

KW - image classification

KW - image segmentation

KW - optical coherence tomography

KW - retina

UR - http://www.scopus.com/inward/record.url?scp=85070239796&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070239796&partnerID=8YFLogxK

U2 - 10.1109/TMI.2019.2901398

DO - 10.1109/TMI.2019.2901398

M3 - Article

C2 - 30835214

AN - SCOPUS:85070239796

VL - 38

SP - 1858

EP - 1874

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 8

M1 - 8653407

ER -

RETOUCH: The Retinal OCT Fluid Detection and Segmentation Benchmark and Challenge

Abstract

Bibliographical note

Keywords

Access

Other files and links

Cite this