Determining the scale of image patches using a deep learning approach

Sebastian Otalora; Oscar Perdomo; Manfredo Atzori; Mats Andersson; Ludwig Jacobsson; Martin Hedlund; Henning Muller

doi:10.1109/ISBI.2018.8363703

Determining the scale of image patches using a deep learning approach

Sebastian Otalora, Oscar Perdomo, Manfredo Atzori, Mats Andersson, Ludwig Jacobsson, Martin Hedlund, Henning Muller

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

4 Scopus citations

Abstract

Detecting the scale of histopathology images is important because it allows to exploit various sources of information to train deep learning (DL) models to recognise biological structures of interest. Large open access databases with images exist, such as The Cancer Genome Atlas (TCGA) and PubMed Central but very few models can use such datasets because of the variability of the data in color and scale and a lack of metadata. In this article, we present and compare two deep learning architectures, to detect the scale of histopathology image patches. The approach is evaluated on a patch dataset from whole slide images of the prostate, obtaining a Cohen's kappa coefficient of 0.9897 in the classification of patches with a scale of 5×, 10× and 20×. The good results represent a first step towards magnification detection in histopathology images that can help to solve the problem on more heterogeneous data sources.

Original language	English (US)
Title of host publication	2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018
Publisher	IEEE Computer Society
Pages	843-846
Number of pages	4
ISBN (Electronic)	9781538636367
DOIs	https://doi.org/10.1109/ISBI.2018.8363703
State	Published - May 23 2018
Externally published	Yes
Event	15th IEEE International Symposium on Biomedical Imaging, ISBI 2018 - Washington, United States Duration: Apr 4 2018 → Apr 7 2018

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
Volume	2018-April
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	15th IEEE International Symposium on Biomedical Imaging, ISBI 2018
Country	United States
City	Washington
Period	4/4/18 → 4/7/18

All Science Journal Classification (ASJC) codes

Biomedical Engineering
Radiology Nuclear Medicine and imaging

UN SDGs

This output contributes to the following Sustainable Development Goal(s)

Access to Document

10.1109/ISBI.2018.8363703

Fingerprint Dive into the research topics of 'Determining the scale of image patches using a deep learning approach'. Together they form a unique fingerprint.

Cite this

Otalora, S., Perdomo, O., Atzori, M., Andersson, M., Jacobsson, L., Hedlund, M., & Muller, H. (2018). Determining the scale of image patches using a deep learning approach. In 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018 (pp. 843-846). (Proceedings - International Symposium on Biomedical Imaging; Vol. 2018-April). IEEE Computer Society. https://doi.org/10.1109/ISBI.2018.8363703

Otalora, Sebastian ; Perdomo, Oscar ; Atzori, Manfredo ; Andersson, Mats ; Jacobsson, Ludwig ; Hedlund, Martin ; Muller, Henning. / Determining the scale of image patches using a deep learning approach. 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. IEEE Computer Society, 2018. pp. 843-846 (Proceedings - International Symposium on Biomedical Imaging).

@inproceedings{c49339b8c0124f40ac0de2702a2580d4,

title = "Determining the scale of image patches using a deep learning approach",

abstract = "Detecting the scale of histopathology images is important because it allows to exploit various sources of information to train deep learning (DL) models to recognise biological structures of interest. Large open access databases with images exist, such as The Cancer Genome Atlas (TCGA) and PubMed Central but very few models can use such datasets because of the variability of the data in color and scale and a lack of metadata. In this article, we present and compare two deep learning architectures, to detect the scale of histopathology image patches. The approach is evaluated on a patch dataset from whole slide images of the prostate, obtaining a Cohen's kappa coefficient of 0.9897 in the classification of patches with a scale of 5×, 10× and 20×. The good results represent a first step towards magnification detection in histopathology images that can help to solve the problem on more heterogeneous data sources.",

author = "Sebastian Otalora and Oscar Perdomo and Manfredo Atzori and Mats Andersson and Ludwig Jacobsson and Martin Hedlund and Henning Muller",

note = "Funding Information: This work was partially supported by the Eurostars project E! 9653 SLDESUTO-BOX and by Nvidia. Publisher Copyright: {\textcopyright} 2018 IEEE. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.; 15th IEEE International Symposium on Biomedical Imaging, ISBI 2018 ; Conference date: 04-04-2018 Through 07-04-2018",

year = "2018",

month = may,

day = "23",

doi = "10.1109/ISBI.2018.8363703",

language = "English (US)",

series = "Proceedings - International Symposium on Biomedical Imaging",

publisher = "IEEE Computer Society",

pages = "843--846",

booktitle = "2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018",

address = "United States",

}

Otalora, S, Perdomo, O, Atzori, M, Andersson, M, Jacobsson, L, Hedlund, M & Muller, H 2018, Determining the scale of image patches using a deep learning approach. in 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Proceedings - International Symposium on Biomedical Imaging, vol. 2018-April, IEEE Computer Society, pp. 843-846, 15th IEEE International Symposium on Biomedical Imaging, ISBI 2018, Washington, United States, 4/4/18. https://doi.org/10.1109/ISBI.2018.8363703

Determining the scale of image patches using a deep learning approach. / Otalora, Sebastian; Perdomo, Oscar; Atzori, Manfredo; Andersson, Mats; Jacobsson, Ludwig; Hedlund, Martin; Muller, Henning.

2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. IEEE Computer Society, 2018. p. 843-846 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2018-April).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - Determining the scale of image patches using a deep learning approach

AU - Otalora, Sebastian

AU - Perdomo, Oscar

AU - Atzori, Manfredo

AU - Andersson, Mats

AU - Jacobsson, Ludwig

AU - Hedlund, Martin

AU - Muller, Henning

N1 - Funding Information: This work was partially supported by the Eurostars project E! 9653 SLDESUTO-BOX and by Nvidia. Publisher Copyright: © 2018 IEEE. Copyright: Copyright 2018 Elsevier B.V., All rights reserved.

PY - 2018/5/23

Y1 - 2018/5/23

N2 - Detecting the scale of histopathology images is important because it allows to exploit various sources of information to train deep learning (DL) models to recognise biological structures of interest. Large open access databases with images exist, such as The Cancer Genome Atlas (TCGA) and PubMed Central but very few models can use such datasets because of the variability of the data in color and scale and a lack of metadata. In this article, we present and compare two deep learning architectures, to detect the scale of histopathology image patches. The approach is evaluated on a patch dataset from whole slide images of the prostate, obtaining a Cohen's kappa coefficient of 0.9897 in the classification of patches with a scale of 5×, 10× and 20×. The good results represent a first step towards magnification detection in histopathology images that can help to solve the problem on more heterogeneous data sources.

AB - Detecting the scale of histopathology images is important because it allows to exploit various sources of information to train deep learning (DL) models to recognise biological structures of interest. Large open access databases with images exist, such as The Cancer Genome Atlas (TCGA) and PubMed Central but very few models can use such datasets because of the variability of the data in color and scale and a lack of metadata. In this article, we present and compare two deep learning architectures, to detect the scale of histopathology image patches. The approach is evaluated on a patch dataset from whole slide images of the prostate, obtaining a Cohen's kappa coefficient of 0.9897 in the classification of patches with a scale of 5×, 10× and 20×. The good results represent a first step towards magnification detection in histopathology images that can help to solve the problem on more heterogeneous data sources.

UR - http://www.scopus.com/inward/record.url?scp=85048099378&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048099378&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2018.8363703

DO - 10.1109/ISBI.2018.8363703

M3 - Conference contribution

AN - SCOPUS:85048099378

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 843

EP - 846

BT - 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018

PB - IEEE Computer Society

T2 - 15th IEEE International Symposium on Biomedical Imaging, ISBI 2018

Y2 - 4 April 2018 through 7 April 2018

ER -

Determining the scale of image patches using a deep learning approach

Abstract

Publication series

Conference

All Science Journal Classification (ASJC) codes

UN SDGs

Access to Document

Other files and links

Cite this