Autofluorescence image reconstruction and virtual staining for in-vivo optical biopsying

Simple item page
dc.contributor.authorPicon, Artzai
dc.contributor.authorMedela, Alfonso
dc.contributor.authorSanchez-Peralta, Luisa F.
dc.contributor.authorCicchi, Riccardo
dc.contributor.authorBilbao, Roberto
dc.contributor.authorAlfieri, Domenico
dc.contributor.authorElola, Andoni
dc.contributor.authorGlover, Ben
dc.contributor.authorSaratxaga, Cristina L.
dc.contributor.institutionCOMPUTER_VISION
dc.contributor.institutionVISUAL
dc.date.issued2021-02
dc.descriptionPublisher Copyright: © 2013 IEEE.
dc.description.abstractModern photonic technologies are emerging, allowing the acquisition of in-vivo endoscopic tissue imaging at a microscopic scale, with characteristics comparable to traditional histological slides, and with a label-free modality. This raises the possibility of an ‘optical biopsy’ to aid clinical decision making. This approach faces barriers for being incorporated into clinical practice, including the lack of existing images for training, unfamiliarity of clinicians with the novel image domains and the uncertainty of trusting ‘black-box’ machine learned image analysis, where the decision making remains inscrutable. In this paper, we propose a new method to transform images from novel photonics techniques (e.g. autofluorescence microscopy) into already established domains such as Hematoxilyn-Eosin (H-E) microscopy through virtual reconstruction and staining. We introduce three main innovations: 1) we propose a transformation method based on a Siamese structure that simultaneously learns the direct and inverse transformation ensuring domain back-transformation quality of the transformed data. 2) We also introduced an embedding loss term that ensures similarity not only at pixel level, but also at the image embedding description level. This drastically reduces the perception distortion trade-off problem existing in common domain transfer based on generative adversarial networks. These virtually stained images can serve as reference standard images for comparison with the already known H-E images. 3) We also incorporate an uncertainty margin concept that allows the network to measure its own confidence, and demonstrate that these reconstructed and virtually stained images can be used on previously-studied classification models of H-E images that have been computationally degraded and de-stained. The three proposed methods can be seamlessly incorporated on any existing architectures. We obtained balanced accuracies of 0.95 and negative predictive values of 1.00 over the reconstructed and virtually stained image-set on the detection of color-rectal tumoral tissue. This is of great importance as we reduce the need for extensive labeled datasets for training, which are normally not available on the early studies of a new imaging technology.en
dc.description.statusPeer reviewed
dc.format.extent13
dc.format.extent3644160
dc.identifier.citationPicon , A , Medela , A , Sanchez-Peralta , L F , Cicchi , R , Bilbao , R , Alfieri , D , Elola , A , Glover , B & Saratxaga , C L 2021 , ' Autofluorescence image reconstruction and virtual staining for in-vivo optical biopsying ' , IEEE Access , vol. 9 , 2425 , pp. 32081-32093 . https://doi.org/10.1109/access.2021.3060926
dc.identifier.doi10.1109/access.2021.3060926
dc.identifier.issn2169-3536
dc.identifier.otherresearchoutputwizard: 11556/1087
dc.identifier.urlhttp://www.scopus.com/inward/record.url?scp=85111948809&partnerID=8YFLogxK
dc.language.isoeng
dc.relation.ispartofIEEE Access
dc.rightsinfo:eu-repo/semantics/openAccess
dc.subject.keywordsHistopathology analysis
dc.subject.keywordsConvolutional neural network
dc.subject.keywordsDomain adaptation
dc.subject.keywordsOptical biopsy
dc.subject.keywordsVirtual staining
dc.subject.keywordsSiamese semantic regression networks
dc.subject.keywordsHistopathology analysis
dc.subject.keywordsConvolutional neural network
dc.subject.keywordsDomain adaptation
dc.subject.keywordsOptical biopsy
dc.subject.keywordsVirtual staining
dc.subject.keywordsSiamese semantic regression networks
dc.subject.keywordsGeneral Computer Science
dc.subject.keywordsGeneral Materials Science
dc.subject.keywordsGeneral Engineering
dc.subject.keywordsProject ID
dc.subject.keywordsinfo:eu-repo/grantAgreement/EC/FP7/296162/EU/SERVICES ASSOCIATED TO DIGITALISED CONTENTS OF TISSUES IN BIOBANKS ACROSS EUROPE/BIOPOOL
dc.subject.keywordsinfo:eu-repo/grantAgreement/EC/FP7/296162/EU/SERVICES ASSOCIATED TO DIGITALISED CONTENTS OF TISSUES IN BIOBANKS ACROSS EUROPE/BIOPOOL
dc.subject.keywordsFunding Info
dc.subject.keywordsThe authors would like to thank all pathologists that generated the BIOPOOL dataset (FP7-ICT-296162) that has been used for this work and specially to M. Saiz, A. Gaafar, S. Fernandez, A. Saiz, E. de Miguel, B. Catón, J. J. Aguirre, R. Ruiz, Ma A. Viguri, and R. Rezola.
dc.subject.keywordsThe authors would like to thank all pathologists that generated the BIOPOOL dataset (FP7-ICT-296162) that has been used for this work and specially to M. Saiz, A. Gaafar, S. Fernandez, A. Saiz, E. de Miguel, B. Catón, J. J. Aguirre, R. Ruiz, Ma A. Viguri, and R. Rezola.
dc.titleAutofluorescence image reconstruction and virtual staining for in-vivo optical biopsyingen
dc.typejournal article
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
09359782.pdf
Size:
3.48 MB
Format:
Adobe Portable Document Format
Download