Re-staining pathology images by FCNN

Masayuki Fujitani, Yoshihiko Mochizuki, Satoshi Iizuka, Edgar Simo-Serra, Hirokazu Kobayashi, Chika Iwamoto, Kenoki Ouchida, Makoto Hashizume, Hidekata Hontani, Hiroshi Ishikawa

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In histopathology, pathologic tissue samples are stained using one of various techniques according to the desired features to be observed in microscopic examination. One problem is that staining is irreversible. Once a tissue slice is stained using a technique, it cannot be re-stained using another. In this work, we propose a method for simulated re-staining using a Fully Convolutional Neural Network (FCNN). We convert a digitally scanned pathology image of a sample, stained using one technique, into another image with a different simulated stain. The challenge is that the ground truth cannot be obtained: The network needs training data, which in this case would be pairs of images of a sample stained in two different techniques. We overcome this problem by using the images of consecutive slices that are stained using the two distinct techniques, screening for morphological similarity by comparing their density components in the HSD color space. We demonstrate the effectiveness of the method in the case of converting hematoxylin and eosin-stained images into Masson's trichrome-stained images.

Original languageEnglish
Title of host publicationProceedings of the 16th International Conference on Machine Vision Applications, MVA 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9784901122184
DOIs
Publication statusPublished - May 1 2019
Event16th International Conference on Machine Vision Applications, MVA 2019 - Tokyo, Japan
Duration: May 27 2019May 31 2019

Publication series

NameProceedings of the 16th International Conference on Machine Vision Applications, MVA 2019

Conference

Conference16th International Conference on Machine Vision Applications, MVA 2019
CountryJapan
CityTokyo
Period5/27/195/31/19

Fingerprint

Pathology
Tissue
Neural networks
Microscopic examination
Screening
Color

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Signal Processing
  • Computer Vision and Pattern Recognition

Cite this

Fujitani, M., Mochizuki, Y., Iizuka, S., Simo-Serra, E., Kobayashi, H., Iwamoto, C., ... Ishikawa, H. (2019). Re-staining pathology images by FCNN. In Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019 [8757875] (Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/MVA.2019.8757875

Re-staining pathology images by FCNN. / Fujitani, Masayuki; Mochizuki, Yoshihiko; Iizuka, Satoshi; Simo-Serra, Edgar; Kobayashi, Hirokazu; Iwamoto, Chika; Ouchida, Kenoki; Hashizume, Makoto; Hontani, Hidekata; Ishikawa, Hiroshi.

Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8757875 (Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Fujitani, M, Mochizuki, Y, Iizuka, S, Simo-Serra, E, Kobayashi, H, Iwamoto, C, Ouchida, K, Hashizume, M, Hontani, H & Ishikawa, H 2019, Re-staining pathology images by FCNN. in Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019., 8757875, Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019, Institute of Electrical and Electronics Engineers Inc., 16th International Conference on Machine Vision Applications, MVA 2019, Tokyo, Japan, 5/27/19. https://doi.org/10.23919/MVA.2019.8757875
Fujitani M, Mochizuki Y, Iizuka S, Simo-Serra E, Kobayashi H, Iwamoto C et al. Re-staining pathology images by FCNN. In Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019. Institute of Electrical and Electronics Engineers Inc. 2019. 8757875. (Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019). https://doi.org/10.23919/MVA.2019.8757875
Fujitani, Masayuki ; Mochizuki, Yoshihiko ; Iizuka, Satoshi ; Simo-Serra, Edgar ; Kobayashi, Hirokazu ; Iwamoto, Chika ; Ouchida, Kenoki ; Hashizume, Makoto ; Hontani, Hidekata ; Ishikawa, Hiroshi. / Re-staining pathology images by FCNN. Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019. Institute of Electrical and Electronics Engineers Inc., 2019. (Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019).
@inproceedings{65eb904832244153adf4d755384a1a63,
title = "Re-staining pathology images by FCNN",
abstract = "In histopathology, pathologic tissue samples are stained using one of various techniques according to the desired features to be observed in microscopic examination. One problem is that staining is irreversible. Once a tissue slice is stained using a technique, it cannot be re-stained using another. In this work, we propose a method for simulated re-staining using a Fully Convolutional Neural Network (FCNN). We convert a digitally scanned pathology image of a sample, stained using one technique, into another image with a different simulated stain. The challenge is that the ground truth cannot be obtained: The network needs training data, which in this case would be pairs of images of a sample stained in two different techniques. We overcome this problem by using the images of consecutive slices that are stained using the two distinct techniques, screening for morphological similarity by comparing their density components in the HSD color space. We demonstrate the effectiveness of the method in the case of converting hematoxylin and eosin-stained images into Masson's trichrome-stained images.",
author = "Masayuki Fujitani and Yoshihiko Mochizuki and Satoshi Iizuka and Edgar Simo-Serra and Hirokazu Kobayashi and Chika Iwamoto and Kenoki Ouchida and Makoto Hashizume and Hidekata Hontani and Hiroshi Ishikawa",
year = "2019",
month = "5",
day = "1",
doi = "10.23919/MVA.2019.8757875",
language = "English",
series = "Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019",
address = "United States",

}

TY - GEN

T1 - Re-staining pathology images by FCNN

AU - Fujitani, Masayuki

AU - Mochizuki, Yoshihiko

AU - Iizuka, Satoshi

AU - Simo-Serra, Edgar

AU - Kobayashi, Hirokazu

AU - Iwamoto, Chika

AU - Ouchida, Kenoki

AU - Hashizume, Makoto

AU - Hontani, Hidekata

AU - Ishikawa, Hiroshi

PY - 2019/5/1

Y1 - 2019/5/1

N2 - In histopathology, pathologic tissue samples are stained using one of various techniques according to the desired features to be observed in microscopic examination. One problem is that staining is irreversible. Once a tissue slice is stained using a technique, it cannot be re-stained using another. In this work, we propose a method for simulated re-staining using a Fully Convolutional Neural Network (FCNN). We convert a digitally scanned pathology image of a sample, stained using one technique, into another image with a different simulated stain. The challenge is that the ground truth cannot be obtained: The network needs training data, which in this case would be pairs of images of a sample stained in two different techniques. We overcome this problem by using the images of consecutive slices that are stained using the two distinct techniques, screening for morphological similarity by comparing their density components in the HSD color space. We demonstrate the effectiveness of the method in the case of converting hematoxylin and eosin-stained images into Masson's trichrome-stained images.

AB - In histopathology, pathologic tissue samples are stained using one of various techniques according to the desired features to be observed in microscopic examination. One problem is that staining is irreversible. Once a tissue slice is stained using a technique, it cannot be re-stained using another. In this work, we propose a method for simulated re-staining using a Fully Convolutional Neural Network (FCNN). We convert a digitally scanned pathology image of a sample, stained using one technique, into another image with a different simulated stain. The challenge is that the ground truth cannot be obtained: The network needs training data, which in this case would be pairs of images of a sample stained in two different techniques. We overcome this problem by using the images of consecutive slices that are stained using the two distinct techniques, screening for morphological similarity by comparing their density components in the HSD color space. We demonstrate the effectiveness of the method in the case of converting hematoxylin and eosin-stained images into Masson's trichrome-stained images.

UR - http://www.scopus.com/inward/record.url?scp=85070456994&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85070456994&partnerID=8YFLogxK

U2 - 10.23919/MVA.2019.8757875

DO - 10.23919/MVA.2019.8757875

M3 - Conference contribution

AN - SCOPUS:85070456994

T3 - Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019

BT - Proceedings of the 16th International Conference on Machine Vision Applications, MVA 2019

PB - Institute of Electrical and Electronics Engineers Inc.

ER -