ST-MKSC: The FF-FFPE Stain Transfer Based on Multiple Key Structure Constraint

Zexin Li; Yiyang Lin; Yifeng Wang; Zijie Fang; Hao Bian; Runze Hu; Xiu Li; Yongbing Zhang

doi:10.1109/ISBI53787.2023.10230499

ST-MKSC: The FF-FFPE Stain Transfer Based on Multiple Key Structure Constraint

Zexin Li, Yiyang Lin, Yifeng Wang, Zijie Fang, Hao Bian, Runze Hu, Xiu Li^*, Yongbing Zhang^*

^*Corresponding author for this work

School of Information and Electronics

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

Abstract

The common computational pathology tissue slides mainly include Fresh Frozen (FF) slides and Formalin-Fixed Paraffin-Embedded (FFPE) slides. The FF slide has low quality but is easy to prepare, while the FFPE one is the opposite, which is widely used in pathological slide preservation and high-precision diagnosis. Our goal is to generate FFPE images based on FF patches in order to quickly obtain high-quality slides in a short time and to provide doctors with convenient and accurate diagnostic evidence. We propose ST-MKSC, an FF2FFPE image translation network, which contains a Multi-frequency Domain Hierarchical Constraint (MDHC) network based on key consistent information constraints to keep the content information from the FF domain being preserved in the FFPE domain and Released Constraint loss (RC loss) to weaken the existing constraints, so as to reduce the impact of source domain (FF) style information on the appearance of the target domain (FFPE). We conduct FF2FFPE translation experiments on the TCGA-KIRC Dataset and our method is the best among the existing methods. Our model can effectively eliminate or weaken the cavity, artifacts, and other unreasonable structures in FF slides, and generate high-quality FFPE images.

Original language	English
Title of host publication	2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023
Publisher	IEEE Computer Society
ISBN (Electronic)	9781665473583
DOIs	https://doi.org/10.1109/ISBI53787.2023.10230499
Publication status	Published - 2023
Event	20th IEEE International Symposium on Biomedical Imaging, ISBI 2023 - Cartagena, Colombia Duration: 18 Apr 2023 → 21 Apr 2023

Publication series

Name	Proceedings - International Symposium on Biomedical Imaging
Volume	2023-April
ISSN (Print)	1945-7928
ISSN (Electronic)	1945-8452

Conference

Conference	20th IEEE International Symposium on Biomedical Imaging, ISBI 2023
Country/Territory	Colombia
City	Cartagena
Period	18/04/23 → 21/04/23

Keywords

FF2FFPE
Image translation
Stain transfer

Access to Document

10.1109/ISBI53787.2023.10230499

Cite this

Li, Z., Lin, Y., Wang, Y., Fang, Z., Bian, H., Hu, R., Li, X., & Zhang, Y. (2023). ST-MKSC: The FF-FFPE Stain Transfer Based on Multiple Key Structure Constraint. In 2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2023-April). IEEE Computer Society. https://doi.org/10.1109/ISBI53787.2023.10230499

@inproceedings{1783ed3c8361487585042a4d421123ff,

title = "ST-MKSC: The FF-FFPE Stain Transfer Based on Multiple Key Structure Constraint",

abstract = "The common computational pathology tissue slides mainly include Fresh Frozen (FF) slides and Formalin-Fixed Paraffin-Embedded (FFPE) slides. The FF slide has low quality but is easy to prepare, while the FFPE one is the opposite, which is widely used in pathological slide preservation and high-precision diagnosis. Our goal is to generate FFPE images based on FF patches in order to quickly obtain high-quality slides in a short time and to provide doctors with convenient and accurate diagnostic evidence. We propose ST-MKSC, an FF2FFPE image translation network, which contains a Multi-frequency Domain Hierarchical Constraint (MDHC) network based on key consistent information constraints to keep the content information from the FF domain being preserved in the FFPE domain and Released Constraint loss (RC loss) to weaken the existing constraints, so as to reduce the impact of source domain (FF) style information on the appearance of the target domain (FFPE). We conduct FF2FFPE translation experiments on the TCGA-KIRC Dataset and our method is the best among the existing methods. Our model can effectively eliminate or weaken the cavity, artifacts, and other unreasonable structures in FF slides, and generate high-quality FFPE images.",

keywords = "FF2FFPE, Image translation, Stain transfer",

author = "Zexin Li and Yiyang Lin and Yifeng Wang and Zijie Fang and Hao Bian and Runze Hu and Xiu Li and Yongbing Zhang",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 20th IEEE International Symposium on Biomedical Imaging, ISBI 2023 ; Conference date: 18-04-2023 Through 21-04-2023",

year = "2023",

doi = "10.1109/ISBI53787.2023.10230499",

language = "English",

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

publisher = "IEEE Computer Society",

booktitle = "2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023",

address = "United States",

}

Li, Z, Lin, Y, Wang, Y, Fang, Z, Bian, H, Hu, R, Li, X & Zhang, Y 2023, ST-MKSC: The FF-FFPE Stain Transfer Based on Multiple Key Structure Constraint. in 2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023. Proceedings - International Symposium on Biomedical Imaging, vol. 2023-April, IEEE Computer Society, 20th IEEE International Symposium on Biomedical Imaging, ISBI 2023, Cartagena, Colombia, 18/04/23. https://doi.org/10.1109/ISBI53787.2023.10230499

ST-MKSC: The FF-FFPE Stain Transfer Based on Multiple Key Structure Constraint. / Li, Zexin; Lin, Yiyang; Wang, Yifeng et al.
2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023. IEEE Computer Society, 2023. (Proceedings - International Symposium on Biomedical Imaging; Vol. 2023-April).

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

TY - GEN

T1 - ST-MKSC

T2 - 20th IEEE International Symposium on Biomedical Imaging, ISBI 2023

AU - Li, Zexin

AU - Lin, Yiyang

AU - Wang, Yifeng

AU - Fang, Zijie

AU - Bian, Hao

AU - Hu, Runze

AU - Li, Xiu

AU - Zhang, Yongbing

PY - 2023

Y1 - 2023

N2 - The common computational pathology tissue slides mainly include Fresh Frozen (FF) slides and Formalin-Fixed Paraffin-Embedded (FFPE) slides. The FF slide has low quality but is easy to prepare, while the FFPE one is the opposite, which is widely used in pathological slide preservation and high-precision diagnosis. Our goal is to generate FFPE images based on FF patches in order to quickly obtain high-quality slides in a short time and to provide doctors with convenient and accurate diagnostic evidence. We propose ST-MKSC, an FF2FFPE image translation network, which contains a Multi-frequency Domain Hierarchical Constraint (MDHC) network based on key consistent information constraints to keep the content information from the FF domain being preserved in the FFPE domain and Released Constraint loss (RC loss) to weaken the existing constraints, so as to reduce the impact of source domain (FF) style information on the appearance of the target domain (FFPE). We conduct FF2FFPE translation experiments on the TCGA-KIRC Dataset and our method is the best among the existing methods. Our model can effectively eliminate or weaken the cavity, artifacts, and other unreasonable structures in FF slides, and generate high-quality FFPE images.

AB - The common computational pathology tissue slides mainly include Fresh Frozen (FF) slides and Formalin-Fixed Paraffin-Embedded (FFPE) slides. The FF slide has low quality but is easy to prepare, while the FFPE one is the opposite, which is widely used in pathological slide preservation and high-precision diagnosis. Our goal is to generate FFPE images based on FF patches in order to quickly obtain high-quality slides in a short time and to provide doctors with convenient and accurate diagnostic evidence. We propose ST-MKSC, an FF2FFPE image translation network, which contains a Multi-frequency Domain Hierarchical Constraint (MDHC) network based on key consistent information constraints to keep the content information from the FF domain being preserved in the FFPE domain and Released Constraint loss (RC loss) to weaken the existing constraints, so as to reduce the impact of source domain (FF) style information on the appearance of the target domain (FFPE). We conduct FF2FFPE translation experiments on the TCGA-KIRC Dataset and our method is the best among the existing methods. Our model can effectively eliminate or weaken the cavity, artifacts, and other unreasonable structures in FF slides, and generate high-quality FFPE images.

KW - FF2FFPE

KW - Image translation

KW - Stain transfer

UR - http://www.scopus.com/inward/record.url?scp=85172125664&partnerID=8YFLogxK

U2 - 10.1109/ISBI53787.2023.10230499

DO - 10.1109/ISBI53787.2023.10230499

M3 - Conference contribution

AN - SCOPUS:85172125664

T3 - Proceedings - International Symposium on Biomedical Imaging

BT - 2023 IEEE International Symposium on Biomedical Imaging, ISBI 2023

PB - IEEE Computer Society

Y2 - 18 April 2023 through 21 April 2023

ER -

ST-MKSC: The FF-FFPE Stain Transfer Based on Multiple Key Structure Constraint

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this