Deep Learning on Oral Squamous Cell Carcinoma Ex Vivo Fluorescent Confocal Microscopy Data: A Feasibility Study

Background: Ex vivo fluorescent confocal microscopy (FCM) is a novel and effective method for a fast-automatized histological tissue examination. In contrast, conventional diagnostic methods are primarily based on the skills of the histopathologist. In this study, we investigated the potential of co...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Veronika Shavlokhova, Sameena Sandhu, Christa Flechtenmacher, Istvan Koveshazi, Florian Neumeier, Víctor Padrón-Laso, Žan Jonke, Babak Saravi, Michael Vollmer, Andreas Vollmer, Jürgen Hoffmann, Michael Engel, Oliver Ristow, Christian Freudlsperger
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	confocal microscopy deep learning CNN OSCC SCC intraoperative microscopy Medicine R
Acceso en línea:	https://doaj.org/article/47c4d08d37934315a81cbcd5f2d6a157
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:47c4d08d37934315a81cbcd5f2d6a157
record_format	dspace
spelling	oai:doaj.org-article:47c4d08d37934315a81cbcd5f2d6a1572021-11-25T18:01:47ZDeep Learning on Oral Squamous Cell Carcinoma Ex Vivo Fluorescent Confocal Microscopy Data: A Feasibility Study10.3390/jcm102253262077-0383https://doaj.org/article/47c4d08d37934315a81cbcd5f2d6a1572021-11-01T00:00:00Zhttps://www.mdpi.com/2077-0383/10/22/5326https://doaj.org/toc/2077-0383Background: Ex vivo fluorescent confocal microscopy (FCM) is a novel and effective method for a fast-automatized histological tissue examination. In contrast, conventional diagnostic methods are primarily based on the skills of the histopathologist. In this study, we investigated the potential of convolutional neural networks (CNNs) for automatized classification of oral squamous cell carcinoma via ex vivo FCM imaging for the first time. Material and Methods: Tissue samples from 20 patients were collected, scanned with an ex vivo confocal microscope immediately after resection, and investigated histopathologically. A CNN architecture (MobileNet) was trained and tested for accuracy. Results: The model achieved a sensitivity of 0.47 and specificity of 0.96 in the automated classification of cancerous tissue in our study. Conclusion: In this preliminary work, we trained a CNN model on a limited number of ex vivo FCM images and obtained promising results in the automated classification of cancerous tissue. Further studies using large sample sizes are warranted to introduce this technology into clinics.Veronika ShavlokhovaSameena SandhuChrista FlechtenmacherIstvan KoveshaziFlorian NeumeierVíctor Padrón-LasoŽan JonkeBabak SaraviMichael VollmerAndreas VollmerJürgen HoffmannMichael EngelOliver RistowChristian FreudlspergerMDPI AGarticleconfocal microscopydeep learningCNNOSCCSCCintraoperative microscopyMedicineRENJournal of Clinical Medicine, Vol 10, Iss 5326, p 5326 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	confocal microscopy deep learning CNN OSCC SCC intraoperative microscopy Medicine R
spellingShingle	confocal microscopy deep learning CNN OSCC SCC intraoperative microscopy Medicine R Veronika Shavlokhova Sameena Sandhu Christa Flechtenmacher Istvan Koveshazi Florian Neumeier Víctor Padrón-Laso Žan Jonke Babak Saravi Michael Vollmer Andreas Vollmer Jürgen Hoffmann Michael Engel Oliver Ristow Christian Freudlsperger Deep Learning on Oral Squamous Cell Carcinoma Ex Vivo Fluorescent Confocal Microscopy Data: A Feasibility Study
description	Background: Ex vivo fluorescent confocal microscopy (FCM) is a novel and effective method for a fast-automatized histological tissue examination. In contrast, conventional diagnostic methods are primarily based on the skills of the histopathologist. In this study, we investigated the potential of convolutional neural networks (CNNs) for automatized classification of oral squamous cell carcinoma via ex vivo FCM imaging for the first time. Material and Methods: Tissue samples from 20 patients were collected, scanned with an ex vivo confocal microscope immediately after resection, and investigated histopathologically. A CNN architecture (MobileNet) was trained and tested for accuracy. Results: The model achieved a sensitivity of 0.47 and specificity of 0.96 in the automated classification of cancerous tissue in our study. Conclusion: In this preliminary work, we trained a CNN model on a limited number of ex vivo FCM images and obtained promising results in the automated classification of cancerous tissue. Further studies using large sample sizes are warranted to introduce this technology into clinics.
format	article
author	Veronika Shavlokhova Sameena Sandhu Christa Flechtenmacher Istvan Koveshazi Florian Neumeier Víctor Padrón-Laso Žan Jonke Babak Saravi Michael Vollmer Andreas Vollmer Jürgen Hoffmann Michael Engel Oliver Ristow Christian Freudlsperger
author_facet	Veronika Shavlokhova Sameena Sandhu Christa Flechtenmacher Istvan Koveshazi Florian Neumeier Víctor Padrón-Laso Žan Jonke Babak Saravi Michael Vollmer Andreas Vollmer Jürgen Hoffmann Michael Engel Oliver Ristow Christian Freudlsperger
author_sort	Veronika Shavlokhova
title	Deep Learning on Oral Squamous Cell Carcinoma Ex Vivo Fluorescent Confocal Microscopy Data: A Feasibility Study
title_short	Deep Learning on Oral Squamous Cell Carcinoma Ex Vivo Fluorescent Confocal Microscopy Data: A Feasibility Study
title_full	Deep Learning on Oral Squamous Cell Carcinoma Ex Vivo Fluorescent Confocal Microscopy Data: A Feasibility Study
title_fullStr	Deep Learning on Oral Squamous Cell Carcinoma Ex Vivo Fluorescent Confocal Microscopy Data: A Feasibility Study
title_full_unstemmed	Deep Learning on Oral Squamous Cell Carcinoma Ex Vivo Fluorescent Confocal Microscopy Data: A Feasibility Study
title_sort	deep learning on oral squamous cell carcinoma ex vivo fluorescent confocal microscopy data: a feasibility study
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/47c4d08d37934315a81cbcd5f2d6a157
work_keys_str_mv	AT veronikashavlokhova deeplearningonoralsquamouscellcarcinomaexvivofluorescentconfocalmicroscopydataafeasibilitystudy AT sameenasandhu deeplearningonoralsquamouscellcarcinomaexvivofluorescentconfocalmicroscopydataafeasibilitystudy AT christaflechtenmacher deeplearningonoralsquamouscellcarcinomaexvivofluorescentconfocalmicroscopydataafeasibilitystudy AT istvankoveshazi deeplearningonoralsquamouscellcarcinomaexvivofluorescentconfocalmicroscopydataafeasibilitystudy AT florianneumeier deeplearningonoralsquamouscellcarcinomaexvivofluorescentconfocalmicroscopydataafeasibilitystudy AT victorpadronlaso deeplearningonoralsquamouscellcarcinomaexvivofluorescentconfocalmicroscopydataafeasibilitystudy AT zanjonke deeplearningonoralsquamouscellcarcinomaexvivofluorescentconfocalmicroscopydataafeasibilitystudy AT babaksaravi deeplearningonoralsquamouscellcarcinomaexvivofluorescentconfocalmicroscopydataafeasibilitystudy AT michaelvollmer deeplearningonoralsquamouscellcarcinomaexvivofluorescentconfocalmicroscopydataafeasibilitystudy AT andreasvollmer deeplearningonoralsquamouscellcarcinomaexvivofluorescentconfocalmicroscopydataafeasibilitystudy AT jurgenhoffmann deeplearningonoralsquamouscellcarcinomaexvivofluorescentconfocalmicroscopydataafeasibilitystudy AT michaelengel deeplearningonoralsquamouscellcarcinomaexvivofluorescentconfocalmicroscopydataafeasibilitystudy AT oliverristow deeplearningonoralsquamouscellcarcinomaexvivofluorescentconfocalmicroscopydataafeasibilitystudy AT christianfreudlsperger deeplearningonoralsquamouscellcarcinomaexvivofluorescentconfocalmicroscopydataafeasibilitystudy
_version_	1718411676260237312

Deep Learning on Oral Squamous Cell Carcinoma Ex Vivo Fluorescent Confocal Microscopy Data: A Feasibility Study

Ejemplares similares