Feasibility of Colon Cancer Detection in Confocal Laser Microscopy Images Using Convolution Neural Networks

Nils Gessert; Lukas Wittig; Daniel Drömann; Tobias Keck; Alexander Schlaefer; David B. Ellebrecht

doi:10.1007/978-3-658-25326-4_72

Feasibility of Colon Cancer Detection in Confocal Laser Microscopy Images Using Convolution Neural Networks

Nils Gessert^*, Lukas Wittig, Daniel Drömann, Tobias Keck, Alexander Schlaefer, David B. Ellebrecht

^*Corresponding author for this work

Hamburg University of Technology

Abstract

Histological evaluation of tissue samples is a typical approach to identify colorectal cancer metastases in the peritoneum. For immediate assessment, reliable and real-time in-vivo imaging would be required. For example, intraoperative confocal laser microscopy has been shown to be suitable for distinguishing organs and also malignant and benign tissue. So far, the analysis is done by human experts. We investigate the feasibility of automatic colon cancer classification from confocal laser microscopy images using deep learning models. We overcome very small dataset sizes through transfer learning with state-of-the-art architectures. We achieve an accuracy of 89.1% for cancer detection in the peritoneum which indicates viability as an intraoperative decision support system.

Original language	English
Title of host publication	Bildverarbeitung für die Medizin 2019
Editors	Heinz Handels, Thomas M. Deserno, Andreas Maier, Klaus Hermann Maier-Hein, Christoph Palm, Thomas Tolxdorff
Number of pages	6
Publisher	Springer Vieweg, Wiesbaden
Publication date	07.02.2019
Pages	327-332
ISBN (Print)	978-3-658-25325-7
ISBN (Electronic)	978-3-658-25326-4
DOIs	https://doi.org/10.1007/978-3-658-25326-4_72
Publication status	Published - 07.02.2019
Event	Workshop on Bildverarbeitung fur die Medizin 2019 - Lübeck, Germany Duration: 17.03.2019 → 19.03.2019 Conference number: 224899

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-3-658-25326-4_72

Cite this

Gessert, N., Wittig, L., Drömann, D., Keck, T., Schlaefer, A., & Ellebrecht, D. B. (2019). Feasibility of Colon Cancer Detection in Confocal Laser Microscopy Images Using Convolution Neural Networks. In H. Handels, T. M. Deserno, A. Maier, K. Hermann Maier-Hein, C. Palm, & T. Tolxdorff (Eds.), Bildverarbeitung für die Medizin 2019 (pp. 327-332). (Informatik aktuell). Springer Vieweg, Wiesbaden. https://doi.org/10.1007/978-3-658-25326-4_72

Gessert, Nils ; Wittig, Lukas ; Drömann, Daniel et al. / Feasibility of Colon Cancer Detection in Confocal Laser Microscopy Images Using Convolution Neural Networks. Bildverarbeitung für die Medizin 2019 . editor / Heinz Handels ; Thomas M. Deserno ; Andreas Maier ; Klaus Hermann Maier-Hein ; Christoph Palm ; Thomas Tolxdorff. Springer Vieweg, Wiesbaden, 2019. pp. 327-332 (Informatik aktuell).

@inproceedings{7ea8563f56b24b378fe8819d2b96bf73,

title = "Feasibility of Colon Cancer Detection in Confocal Laser Microscopy Images Using Convolution Neural Networks",

abstract = "Histological evaluation of tissue samples is a typical approach to identify colorectal cancer metastases in the peritoneum. For immediate assessment, reliable and real-time in-vivo imaging would be required. For example, intraoperative confocal laser microscopy has been shown to be suitable for distinguishing organs and also malignant and benign tissue. So far, the analysis is done by human experts. We investigate the feasibility of automatic colon cancer classification from confocal laser microscopy images using deep learning models. We overcome very small dataset sizes through transfer learning with state-of-the-art architectures. We achieve an accuracy of 89.1% for cancer detection in the peritoneum which indicates viability as an intraoperative decision support system.",

author = "Nils Gessert and Lukas Wittig and Daniel Dr{\"o}mann and Tobias Keck and Alexander Schlaefer and Ellebrecht, {David B.}",

note = "Publisher Copyright: {\textcopyright} 2019, Springer Berlin Heidelberg. All rights reserved. Copyright: Copyright 2019 Elsevier B.V., All rights reserved.; Workshop on Bildverarbeitung fur die Medizin 2019 ; Conference date: 17-03-2019 Through 19-03-2019",

year = "2019",

month = feb,

day = "7",

doi = "10.1007/978-3-658-25326-4_72",

language = "English",

isbn = "978-3-658-25325-7",

series = "Informatik aktuell",

publisher = "Springer Vieweg, Wiesbaden",

pages = "327--332",

editor = "Handels, {Heinz } and { M. Deserno}, Thomas and Andreas Maier and {Hermann Maier-Hein}, {Klaus } and Christoph Palm and Tolxdorff, {Thomas }",

booktitle = "Bildverarbeitung f{\"u}r die Medizin 2019",

}

Gessert, N, Wittig, L, Drömann, D , Keck, T, Schlaefer, A & Ellebrecht, DB 2019, Feasibility of Colon Cancer Detection in Confocal Laser Microscopy Images Using Convolution Neural Networks. in H Handels, T M. Deserno, A Maier, K Hermann Maier-Hein, C Palm & T Tolxdorff (eds), Bildverarbeitung für die Medizin 2019 . Informatik aktuell, Springer Vieweg, Wiesbaden, pp. 327-332, Workshop on Bildverarbeitung fur die Medizin 2019 , Lübeck, Schleswig-Holstein, Germany, 17.03.19. https://doi.org/10.1007/978-3-658-25326-4_72

Feasibility of Colon Cancer Detection in Confocal Laser Microscopy Images Using Convolution Neural Networks. / Gessert, Nils; Wittig, Lukas; Drömann, Daniel et al.
Bildverarbeitung für die Medizin 2019 . ed. / Heinz Handels; Thomas M. Deserno; Andreas Maier; Klaus Hermann Maier-Hein; Christoph Palm; Thomas Tolxdorff. Springer Vieweg, Wiesbaden, 2019. p. 327-332 (Informatik aktuell).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Feasibility of Colon Cancer Detection in Confocal Laser Microscopy Images Using Convolution Neural Networks

AU - Gessert, Nils

AU - Wittig, Lukas

AU - Drömann, Daniel

AU - Keck, Tobias

AU - Schlaefer, Alexander

AU - Ellebrecht, David B.

N1 - Conference code: 224899

PY - 2019/2/7

Y1 - 2019/2/7

N2 - Histological evaluation of tissue samples is a typical approach to identify colorectal cancer metastases in the peritoneum. For immediate assessment, reliable and real-time in-vivo imaging would be required. For example, intraoperative confocal laser microscopy has been shown to be suitable for distinguishing organs and also malignant and benign tissue. So far, the analysis is done by human experts. We investigate the feasibility of automatic colon cancer classification from confocal laser microscopy images using deep learning models. We overcome very small dataset sizes through transfer learning with state-of-the-art architectures. We achieve an accuracy of 89.1% for cancer detection in the peritoneum which indicates viability as an intraoperative decision support system.

AB - Histological evaluation of tissue samples is a typical approach to identify colorectal cancer metastases in the peritoneum. For immediate assessment, reliable and real-time in-vivo imaging would be required. For example, intraoperative confocal laser microscopy has been shown to be suitable for distinguishing organs and also malignant and benign tissue. So far, the analysis is done by human experts. We investigate the feasibility of automatic colon cancer classification from confocal laser microscopy images using deep learning models. We overcome very small dataset sizes through transfer learning with state-of-the-art architectures. We achieve an accuracy of 89.1% for cancer detection in the peritoneum which indicates viability as an intraoperative decision support system.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85065090790&origin=inward&txGid=2df48ce73eafbc6113a3ac23f68ac223

U2 - 10.1007/978-3-658-25326-4_72

DO - 10.1007/978-3-658-25326-4_72

M3 - Conference contribution

SN - 978-3-658-25325-7

T3 - Informatik aktuell

SP - 327

EP - 332

BT - Bildverarbeitung für die Medizin 2019

A2 - Handels, Heinz

A2 - M. Deserno, Thomas

A2 - Maier, Andreas

A2 - Hermann Maier-Hein, Klaus

A2 - Palm, Christoph

A2 - Tolxdorff, Thomas

PB - Springer Vieweg, Wiesbaden

T2 - Workshop on Bildverarbeitung fur die Medizin 2019

Y2 - 17 March 2019 through 19 March 2019

ER -

Gessert N, Wittig L, Drömann D , Keck T, Schlaefer A, Ellebrecht DB. Feasibility of Colon Cancer Detection in Confocal Laser Microscopy Images Using Convolution Neural Networks. In Handels H, M. Deserno T, Maier A, Hermann Maier-Hein K, Palm C, Tolxdorff T, editors, Bildverarbeitung für die Medizin 2019 . Springer Vieweg, Wiesbaden. 2019. p. 327-332. (Informatik aktuell). doi: 10.1007/978-3-658-25326-4_72

Feasibility of Colon Cancer Detection in Confocal Laser Microscopy Images Using Convolution Neural Networks

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this