Inferring a third spatial dimension from 2D histological images

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-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.

LanguageEnglish
Title of host publication2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018
Place of PublicationPiscataway
PublisherIEEE Computer Society
Pages586-589
Number of pages4
Volume2018-April
ISBN (Electronic)978-1-5386-3636-7
ISBN (Print)978-1-5386-3637-4
DOIs
StatePublished - 10 Jan 2018
Event15th IEEE International Symposium on Biomedical Imaging (ISBI 2018) - Omni Shoreham Hotel, Washington, United States
Duration: 4 Apr 20187 Apr 2018
Conference number: 15
https://biomedicalimaging.org/2018/

Conference

Conference15th IEEE International Symposium on Biomedical Imaging (ISBI 2018)
Abbreviated titleISBI18
CountryUnited States
CityWashington
Period4/04/187/04/18
Internet address

Fingerprint

Tissue
Decomposition
Coloring Agents
Learning
Staining and Labeling
Light
Direction compound
Deep learning

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. DOI: 10.1109/ISBI.2018.8363644
Lafarge, Maxime W. ; Pluim, Josien P.W. ; Eppenhof, Koen A.J. ; Moeskops, Pim ; Veta, Mitko. / Inferring a third spatial dimension from 2D histological images. 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Vol. 2018-April Piscataway : IEEE Computer Society, 2018. pp. 586-589
@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 = "1",
day = "10",
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. DOI: 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 proceedingConference contributionAcademicpeer-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 - 2018/1/10

Y1 - 2018/1/10

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 -

Lafarge MW, Pluim JPW, Eppenhof KAJ, Moeskops P, Veta M. Inferring a third spatial dimension from 2D histological images. In 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Vol. 2018-April. Piscataway: IEEE Computer Society. 2018. p. 586-589. Available from, DOI: 10.1109/ISBI.2018.8363644