Cargando…

Generative adversarial network based digital stain conversion for generating RGB EVG stained image from hyperspectral H&E stained image

SIGNIFICANCE: Quantification of elastic fiber in the tissue specimen is an important aspect of diagnosing different diseases. Though hematoxylin and eosin (H&E) staining is a routinely used and less expensive tissue staining technique, elastic and collagen fibers cannot be differentiated using i...

Descripción completa

Detalles Bibliográficos
Autores principales: Biswas, Tanwi, Suzuki, Hiroyuki, Ishikawa, Masahiro, Kobayashi, Naoki, Obi, Takashi
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Society of Photo-Optical Instrumentation Engineers 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10231830/
https://www.ncbi.nlm.nih.gov/pubmed/37265876
http://dx.doi.org/10.1117/1.JBO.28.5.056501
_version_ 1785051823503048704
author Biswas, Tanwi
Suzuki, Hiroyuki
Ishikawa, Masahiro
Kobayashi, Naoki
Obi, Takashi
author_facet Biswas, Tanwi
Suzuki, Hiroyuki
Ishikawa, Masahiro
Kobayashi, Naoki
Obi, Takashi
author_sort Biswas, Tanwi
collection PubMed
description SIGNIFICANCE: Quantification of elastic fiber in the tissue specimen is an important aspect of diagnosing different diseases. Though hematoxylin and eosin (H&E) staining is a routinely used and less expensive tissue staining technique, elastic and collagen fibers cannot be differentiated using it. So, in conventional pathology, special staining technique, such as Verhoeff’s van Gieson (EVG), is applied physically for this purpose. However, the procedure of EVG staining is very expensive and time-consuming. AIM: The goal of our study is to propose a deep-learning-based computerized method for the generation of RGB EVG stained tissue from hyperspectral H&E stained one to save the time and cost of conventional EVG staining procedure. APPROACH: H&E stained hyperspectral image and EVG stained RGB whole slide image of human pancreatic tissue have been leveraged for this experiment. CycleGAN-based deep learning model has been proposed for digital stain conversion while images from source and target domains are of different modalities (hyperspectral and RGB) with different channel dimensions. A set of three basis functions have been introduced for calculating one of the losses of the proposed method, which retains the relevant features of EVG stained image within the reduced channel dimension of the H&E stained one. RESULTS: The experimental results showed that a set of three basis functions including linear discriminant function and transmittance spectrum of eosin and hematoxylin better retained the essential properties of the elastic fiber to be discriminated from collagen fiber within the reduced dimension of the hyperspectral H&E stained image. Also, only a smaller number of paired training data with our proposed training method contributed significantly to the generation of more realistic EVG stained image with more precise identification of elastic fiber. CONCLUSIONS: RGB EVG stained image is generated from hyperspectral H&E stained image for which our model has performed two types of image conversion simultaneously: hyperspectral to RGB and H&E to EVG. The experimental results show that the intentionally designed set of three basis functions contains more relevant information and prove the effectiveness of our proposed method in generating realistic RGB EVG stained image from hyperspectral H&E stained one.
format Online
Article
Text
id pubmed-10231830
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher Society of Photo-Optical Instrumentation Engineers
record_format MEDLINE/PubMed
spelling pubmed-102318302023-06-01 Generative adversarial network based digital stain conversion for generating RGB EVG stained image from hyperspectral H&E stained image Biswas, Tanwi Suzuki, Hiroyuki Ishikawa, Masahiro Kobayashi, Naoki Obi, Takashi J Biomed Opt Microscopy SIGNIFICANCE: Quantification of elastic fiber in the tissue specimen is an important aspect of diagnosing different diseases. Though hematoxylin and eosin (H&E) staining is a routinely used and less expensive tissue staining technique, elastic and collagen fibers cannot be differentiated using it. So, in conventional pathology, special staining technique, such as Verhoeff’s van Gieson (EVG), is applied physically for this purpose. However, the procedure of EVG staining is very expensive and time-consuming. AIM: The goal of our study is to propose a deep-learning-based computerized method for the generation of RGB EVG stained tissue from hyperspectral H&E stained one to save the time and cost of conventional EVG staining procedure. APPROACH: H&E stained hyperspectral image and EVG stained RGB whole slide image of human pancreatic tissue have been leveraged for this experiment. CycleGAN-based deep learning model has been proposed for digital stain conversion while images from source and target domains are of different modalities (hyperspectral and RGB) with different channel dimensions. A set of three basis functions have been introduced for calculating one of the losses of the proposed method, which retains the relevant features of EVG stained image within the reduced channel dimension of the H&E stained one. RESULTS: The experimental results showed that a set of three basis functions including linear discriminant function and transmittance spectrum of eosin and hematoxylin better retained the essential properties of the elastic fiber to be discriminated from collagen fiber within the reduced dimension of the hyperspectral H&E stained image. Also, only a smaller number of paired training data with our proposed training method contributed significantly to the generation of more realistic EVG stained image with more precise identification of elastic fiber. CONCLUSIONS: RGB EVG stained image is generated from hyperspectral H&E stained image for which our model has performed two types of image conversion simultaneously: hyperspectral to RGB and H&E to EVG. The experimental results show that the intentionally designed set of three basis functions contains more relevant information and prove the effectiveness of our proposed method in generating realistic RGB EVG stained image from hyperspectral H&E stained one. Society of Photo-Optical Instrumentation Engineers 2023-05-31 2023-05 /pmc/articles/PMC10231830/ /pubmed/37265876 http://dx.doi.org/10.1117/1.JBO.28.5.056501 Text en © 2023 The Authors https://creativecommons.org/licenses/by/4.0/Published by SPIE under a Creative Commons Attribution 4.0 International License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.
spellingShingle Microscopy
Biswas, Tanwi
Suzuki, Hiroyuki
Ishikawa, Masahiro
Kobayashi, Naoki
Obi, Takashi
Generative adversarial network based digital stain conversion for generating RGB EVG stained image from hyperspectral H&E stained image
title Generative adversarial network based digital stain conversion for generating RGB EVG stained image from hyperspectral H&E stained image
title_full Generative adversarial network based digital stain conversion for generating RGB EVG stained image from hyperspectral H&E stained image
title_fullStr Generative adversarial network based digital stain conversion for generating RGB EVG stained image from hyperspectral H&E stained image
title_full_unstemmed Generative adversarial network based digital stain conversion for generating RGB EVG stained image from hyperspectral H&E stained image
title_short Generative adversarial network based digital stain conversion for generating RGB EVG stained image from hyperspectral H&E stained image
title_sort generative adversarial network based digital stain conversion for generating rgb evg stained image from hyperspectral h&e stained image
topic Microscopy
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10231830/
https://www.ncbi.nlm.nih.gov/pubmed/37265876
http://dx.doi.org/10.1117/1.JBO.28.5.056501
work_keys_str_mv AT biswastanwi generativeadversarialnetworkbaseddigitalstainconversionforgeneratingrgbevgstainedimagefromhyperspectralhestainedimage
AT suzukihiroyuki generativeadversarialnetworkbaseddigitalstainconversionforgeneratingrgbevgstainedimagefromhyperspectralhestainedimage
AT ishikawamasahiro generativeadversarialnetworkbaseddigitalstainconversionforgeneratingrgbevgstainedimagefromhyperspectralhestainedimage
AT kobayashinaoki generativeadversarialnetworkbaseddigitalstainconversionforgeneratingrgbevgstainedimagefromhyperspectralhestainedimage
AT obitakashi generativeadversarialnetworkbaseddigitalstainconversionforgeneratingrgbevgstainedimagefromhyperspectralhestainedimage