OCT A-Scan based lung tumor tissue classification with Bidirectional Long Short Term Memory networks

S. Otte; Christoph Otte; A. Schlaefer; L. Wittig; G. Huttmann; D. Dromann; A. Zeli

doi:10.1109/MLSP.2013.6661944

OCT A-Scan based lung tumor tissue classification with Bidirectional Long Short Term Memory networks

S. Otte^*, Christoph Otte, A. Schlaefer, L. Wittig, G. Huttmann, D. Dromann, A. Zeli

^*Corresponding author for this work

University of Tubingen

17 Citations (Scopus)

Abstract

This paper presents a novel method for lung tumor tissue classification using Bidirectional Long Short Term Memory networks (BLSTMs). Samples are obtained through Optical Coherence Tomography (OCT) from real soft tissue specimen and represented as data sequences. Such sequences are learned with BLSTMs, which are able to recognize even non-uniformly compressed temporal encoded patterns in sequential data in both forward and backward time-direction. Our experiments indicate that BLSTMs are a suitable choice for this classification task, since they outperform other recurrent architectures. Furthermore, the presented findings lead to promising future investigations in the field of OCT based tissue analysis.

Original language	English
Title of host publication	2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)
Publisher	IEEE
Publication date	2013
Article number	6661944
ISBN (Print)	978-147991180-6
DOIs	https://doi.org/10.1109/MLSP.2013.6661944
Publication status	Published - 2013
Event	2013 16th IEEE International Workshop on Machine Learning for Signal Processing - Southampton, United Kingdom Duration: 22.09.2013 → 25.09.2013 Conference number: 102379

UN SDGs

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

SDG 3 Good Health and Well-being
SDG 9 Industry, Innovation, and Infrastructure

Research Areas and Centers

Academic Focus: Biomedical Engineering
Research Area: Luebeck Integrated Oncology Network (LION)
Centers: University Cancer Center Schleswig-Holstein (UCCSH)

Access to Document

10.1109/MLSP.2013.6661944

Cite this

Otte, S., Otte, C., Schlaefer, A., Wittig, L., Huttmann, G., Dromann, D., & Zeli, A. (2013). OCT A-Scan based lung tumor tissue classification with Bidirectional Long Short Term Memory networks. In 2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP) Article 6661944 (IEEE International Workshop on Machine Learning for Signal Processing, MLSP). IEEE. https://doi.org/10.1109/MLSP.2013.6661944

@inproceedings{51283578db6c412a932e9c118615cd50,

title = "OCT A-Scan based lung tumor tissue classification with Bidirectional Long Short Term Memory networks",

abstract = "This paper presents a novel method for lung tumor tissue classification using Bidirectional Long Short Term Memory networks (BLSTMs). Samples are obtained through Optical Coherence Tomography (OCT) from real soft tissue specimen and represented as data sequences. Such sequences are learned with BLSTMs, which are able to recognize even non-uniformly compressed temporal encoded patterns in sequential data in both forward and backward time-direction. Our experiments indicate that BLSTMs are a suitable choice for this classification task, since they outperform other recurrent architectures. Furthermore, the presented findings lead to promising future investigations in the field of OCT based tissue analysis.",

author = "S. Otte and Christoph Otte and A. Schlaefer and L. Wittig and G. Huttmann and D. Dromann and A. Zeli",

note = "Copyright: Copyright 2014 Elsevier B.V., All rights reserved.; 2013 16th IEEE International Workshop on Machine Learning for Signal Processing , MLSP 2013 ; Conference date: 22-09-2013 Through 25-09-2013",

year = "2013",

doi = "10.1109/MLSP.2013.6661944",

language = "English",

isbn = "978-147991180-6",

series = "IEEE International Workshop on Machine Learning for Signal Processing, MLSP",

publisher = "IEEE",

booktitle = "2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)",

}

Otte, S, Otte, C, Schlaefer, A, Wittig, L, Huttmann, G , Dromann, D & Zeli, A 2013, OCT A-Scan based lung tumor tissue classification with Bidirectional Long Short Term Memory networks. in 2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)., 6661944, IEEE International Workshop on Machine Learning for Signal Processing, MLSP, IEEE, 2013 16th IEEE International Workshop on Machine Learning for Signal Processing , Southampton, United Kingdom, 22.09.13. https://doi.org/10.1109/MLSP.2013.6661944

OCT A-Scan based lung tumor tissue classification with Bidirectional Long Short Term Memory networks. / Otte, S.; Otte, Christoph; Schlaefer, A. et al.
2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP). IEEE, 2013. 6661944 (IEEE International Workshop on Machine Learning for Signal Processing, MLSP).

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

TY - GEN

T1 - OCT A-Scan based lung tumor tissue classification with Bidirectional Long Short Term Memory networks

AU - Otte, S.

AU - Otte, Christoph

AU - Schlaefer, A.

AU - Wittig, L.

AU - Huttmann, G.

AU - Dromann, D.

AU - Zeli, A.

N1 - Conference code: 102379

PY - 2013

Y1 - 2013

N2 - This paper presents a novel method for lung tumor tissue classification using Bidirectional Long Short Term Memory networks (BLSTMs). Samples are obtained through Optical Coherence Tomography (OCT) from real soft tissue specimen and represented as data sequences. Such sequences are learned with BLSTMs, which are able to recognize even non-uniformly compressed temporal encoded patterns in sequential data in both forward and backward time-direction. Our experiments indicate that BLSTMs are a suitable choice for this classification task, since they outperform other recurrent architectures. Furthermore, the presented findings lead to promising future investigations in the field of OCT based tissue analysis.

AB - This paper presents a novel method for lung tumor tissue classification using Bidirectional Long Short Term Memory networks (BLSTMs). Samples are obtained through Optical Coherence Tomography (OCT) from real soft tissue specimen and represented as data sequences. Such sequences are learned with BLSTMs, which are able to recognize even non-uniformly compressed temporal encoded patterns in sequential data in both forward and backward time-direction. Our experiments indicate that BLSTMs are a suitable choice for this classification task, since they outperform other recurrent architectures. Furthermore, the presented findings lead to promising future investigations in the field of OCT based tissue analysis.

UR - https://www.scopus.com/pages/publications/84893226563

U2 - 10.1109/MLSP.2013.6661944

DO - 10.1109/MLSP.2013.6661944

M3 - Conference contribution

SN - 978-147991180-6

T3 - IEEE International Workshop on Machine Learning for Signal Processing, MLSP

BT - 2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP)

PB - IEEE

T2 - 2013 16th IEEE International Workshop on Machine Learning for Signal Processing

Y2 - 22 September 2013 through 25 September 2013

ER -

Otte S, Otte C, Schlaefer A, Wittig L, Huttmann G , Dromann D et al. OCT A-Scan based lung tumor tissue classification with Bidirectional Long Short Term Memory networks. In 2013 IEEE International Workshop on Machine Learning for Signal Processing (MLSP). IEEE. 2013. 6661944. (IEEE International Workshop on Machine Learning for Signal Processing, MLSP). doi: 10.1109/MLSP.2013.6661944

OCT A-Scan based lung tumor tissue classification with Bidirectional Long Short Term Memory networks

Abstract

UN SDGs

Research Areas and Centers

Access to Document

Other files and links

Fingerprint

Cite this