Inferring a third spatial dimension from 2D histological images

Maxime W. Lafarge; Josien P.W. Pluim; Koen A.J. Eppenhof; Pim Moeskops; Mitko Veta

doi:10.1109/ISBI.2018.8363644

Inferring a third spatial dimension from 2D histological images

Maxime W. Lafarge, Josien P.W. Pluim, Koen A.J. Eppenhof, Pim Moeskops, Mitko Veta

Medical Image Analysis

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

Abstract

Histological images are obtained by transmitting light through a tissue specimen that has been stained in order to produce contrast. This process results in 2D images of the specimen that has a three-dimensional structure. In this paper, we propose a method to infer how the stains are distributed in the direction perpendicular to the surface of the slide for a given 2D image in order to obtain a 3D representation of the tissue. This inference is achieved by decomposition of the staining concentration maps under constraints that ensure realistic decomposition and reconstruction of the original 2D images. Our study shows that it is possible to generate realistic 3D images making this method a potential tool for data augmentation when training deep learning models.

Original language	English
Title of host publication	2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018
Place of Publication	Piscataway
Publisher	IEEE Computer Society
Pages	586-589
Number of pages	4
Volume	2018-April
ISBN (Electronic)	978-1-5386-3636-7
ISBN (Print)	978-1-5386-3637-4
DOIs	https://doi.org/10.1109/ISBI.2018.8363644
Publication status	Published - 23 May 2018
Event	15th IEEE International Symposium on Biomedical Imaging (ISBI 2018) - Omni Shoreham Hotel, Washington, United States Duration: 4 Apr 2018 → 7 Apr 2018 Conference number: 15 https://biomedicalimaging.org/2018/

Conference

Conference	15th IEEE International Symposium on Biomedical Imaging (ISBI 2018)
Abbreviated title	ISBI18
Country	United States
City	Washington
Period	4/04/18 → 7/04/18
Internet address	https://biomedicalimaging.org/2018/

Fingerprint

Keywords

3D Inference
Adversarial Training
Histopathology Image Analysis
Image Synthesis

Cite this

Lafarge, M. W., Pluim, J. P. W., Eppenhof, K. A. J., Moeskops, P., & Veta, M. (2018). Inferring a third spatial dimension from 2D histological images. In 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018 (Vol. 2018-April, pp. 586-589). Piscataway: IEEE Computer Society. https://doi.org/10.1109/ISBI.2018.8363644

@inproceedings{492a79759551482eb6f140faced4c310,

title = "Inferring a third spatial dimension from 2D histological images",

abstract = "Histological images are obtained by transmitting light through a tissue specimen that has been stained in order to produce contrast. This process results in 2D images of the specimen that has a three-dimensional structure. In this paper, we propose a method to infer how the stains are distributed in the direction perpendicular to the surface of the slide for a given 2D image in order to obtain a 3D representation of the tissue. This inference is achieved by decomposition of the staining concentration maps under constraints that ensure realistic decomposition and reconstruction of the original 2D images. Our study shows that it is possible to generate realistic 3D images making this method a potential tool for data augmentation when training deep learning models.",

keywords = "3D Inference, Adversarial Training, Histopathology Image Analysis, Image Synthesis",

author = "Lafarge, {Maxime W.} and Pluim, {Josien P.W.} and Eppenhof, {Koen A.J.} and Pim Moeskops and Mitko Veta",

year = "2018",

month = "5",

day = "23",

doi = "10.1109/ISBI.2018.8363644",

language = "English",

isbn = "978-1-5386-3637-4",

volume = "2018-April",

pages = "586--589",

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

publisher = "IEEE Computer Society",

address = "United States",

}

Lafarge, MW , Pluim, JPW , Eppenhof, KAJ, Moeskops, P & Veta, M 2018, Inferring a third spatial dimension from 2D histological images. in 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. vol. 2018-April, IEEE Computer Society, Piscataway, pp. 586-589, 15th IEEE International Symposium on Biomedical Imaging (ISBI 2018), Washington, United States, 4/04/18. https://doi.org/10.1109/ISBI.2018.8363644

Inferring a third spatial dimension from 2D histological images. / Lafarge, Maxime W.; Pluim, Josien P.W.; Eppenhof, Koen A.J.; Moeskops, Pim; Veta, Mitko.

2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Vol. 2018-April Piscataway : IEEE Computer Society, 2018. p. 586-589.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review

TY - GEN

T1 - Inferring a third spatial dimension from 2D histological images

AU - Lafarge, Maxime W.

AU - Pluim, Josien P.W.

AU - Eppenhof, Koen A.J.

AU - Moeskops, Pim

AU - Veta, Mitko

PY - 2018/5/23

Y1 - 2018/5/23

N2 - Histological images are obtained by transmitting light through a tissue specimen that has been stained in order to produce contrast. This process results in 2D images of the specimen that has a three-dimensional structure. In this paper, we propose a method to infer how the stains are distributed in the direction perpendicular to the surface of the slide for a given 2D image in order to obtain a 3D representation of the tissue. This inference is achieved by decomposition of the staining concentration maps under constraints that ensure realistic decomposition and reconstruction of the original 2D images. Our study shows that it is possible to generate realistic 3D images making this method a potential tool for data augmentation when training deep learning models.

AB - Histological images are obtained by transmitting light through a tissue specimen that has been stained in order to produce contrast. This process results in 2D images of the specimen that has a three-dimensional structure. In this paper, we propose a method to infer how the stains are distributed in the direction perpendicular to the surface of the slide for a given 2D image in order to obtain a 3D representation of the tissue. This inference is achieved by decomposition of the staining concentration maps under constraints that ensure realistic decomposition and reconstruction of the original 2D images. Our study shows that it is possible to generate realistic 3D images making this method a potential tool for data augmentation when training deep learning models.

KW - 3D Inference

KW - Adversarial Training

KW - Histopathology Image Analysis

KW - Image Synthesis

UR - http://www.scopus.com/inward/record.url?scp=85048139365&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2018.8363644

DO - 10.1109/ISBI.2018.8363644

M3 - Conference contribution

SN - 978-1-5386-3637-4

VL - 2018-April

SP - 586

EP - 589

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

PB - IEEE Computer Society

CY - Piscataway

ER -

Access to Document

10.1109/ISBI.2018.8363644

Link to publication in Scopus