Tampere University of Technology

TUTCRIS Research Portal

Multiphoton microscopy of the dermoepidermal junction and automated identification of dysplastic tissues with deep learning

Research output: Contribution to journalArticleScientificpeer-review

Standard

Multiphoton microscopy of the dermoepidermal junction and automated identification of dysplastic tissues with deep learning. / Huttunen, Mikko J.; Hristu, Radu; Dumitru, Adrian; Floroiu, Iustin; Costache, Mariana; Stanciu, Stefan G.

In: Biomedical Optics Express, Vol. 11, No. 1, 2020, p. 186-199.

Research output: Contribution to journalArticleScientificpeer-review

Harvard

Huttunen, MJ, Hristu, R, Dumitru, A, Floroiu, I, Costache, M & Stanciu, SG 2020, 'Multiphoton microscopy of the dermoepidermal junction and automated identification of dysplastic tissues with deep learning', Biomedical Optics Express, vol. 11, no. 1, pp. 186-199. https://doi.org/10.1364/BOE.11.000186

APA

Huttunen, M. J., Hristu, R., Dumitru, A., Floroiu, I., Costache, M., & Stanciu, S. G. (2020). Multiphoton microscopy of the dermoepidermal junction and automated identification of dysplastic tissues with deep learning. Biomedical Optics Express, 11(1), 186-199. https://doi.org/10.1364/BOE.11.000186

Vancouver

Author

Huttunen, Mikko J. ; Hristu, Radu ; Dumitru, Adrian ; Floroiu, Iustin ; Costache, Mariana ; Stanciu, Stefan G. / Multiphoton microscopy of the dermoepidermal junction and automated identification of dysplastic tissues with deep learning. In: Biomedical Optics Express. 2020 ; Vol. 11, No. 1. pp. 186-199.

Bibtex - Download

@article{6b0ce1301fed467a9b1ede203ccd39cb,
title = "Multiphoton microscopy of the dermoepidermal junction and automated identification of dysplastic tissues with deep learning",
abstract = "Histopathological image analysis performed by a trained expert is currently regarded as the gold-standard for the diagnostics of many pathologies, including cancers. However, such approaches are laborious, time consuming and contain a risk for bias or human error. There is thus a clear need for faster, less intrusive and more accurate diagnostic solutions, requiring also minimal human intervention. Multiphoton microscopy (MPM) can alleviate some of the drawbacks specific to traditional histopathology by exploiting various endogenous optical signals to provide virtual biopsies that reflect the architecture and composition of tissues, both in-vivo or ex-vivo. Here we show that MPM imaging of the dermoepidermal junction (DEJ) in unstained fixed tissues provides useful cues for a histopathologist to identify the onset of non-melanoma skin cancers. Furthermore, we show that MPM images collected on the DEJ, besides being easy to interpret by a trained specialist, can be automatically classified into healthy and dysplastic classes with high precision using a Deep Learning method and existing pre-trained convolutional neural networks. Our results suggest that deep learning enhanced MPM for in-vivo skin cancer screening could facilitate timely diagnosis and intervention, enabling thus more optimal therapeutic approaches.",
author = "Huttunen, {Mikko J.} and Radu Hristu and Adrian Dumitru and Iustin Floroiu and Mariana Costache and Stanciu, {Stefan G.}",
year = "2020",
doi = "10.1364/BOE.11.000186",
language = "English",
volume = "11",
pages = "186--199",
journal = "Biomedical Optics Express",
issn = "2156-7085",
publisher = "Optical Society of America",
number = "1",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Multiphoton microscopy of the dermoepidermal junction and automated identification of dysplastic tissues with deep learning

AU - Huttunen, Mikko J.

AU - Hristu, Radu

AU - Dumitru, Adrian

AU - Floroiu, Iustin

AU - Costache, Mariana

AU - Stanciu, Stefan G.

PY - 2020

Y1 - 2020

N2 - Histopathological image analysis performed by a trained expert is currently regarded as the gold-standard for the diagnostics of many pathologies, including cancers. However, such approaches are laborious, time consuming and contain a risk for bias or human error. There is thus a clear need for faster, less intrusive and more accurate diagnostic solutions, requiring also minimal human intervention. Multiphoton microscopy (MPM) can alleviate some of the drawbacks specific to traditional histopathology by exploiting various endogenous optical signals to provide virtual biopsies that reflect the architecture and composition of tissues, both in-vivo or ex-vivo. Here we show that MPM imaging of the dermoepidermal junction (DEJ) in unstained fixed tissues provides useful cues for a histopathologist to identify the onset of non-melanoma skin cancers. Furthermore, we show that MPM images collected on the DEJ, besides being easy to interpret by a trained specialist, can be automatically classified into healthy and dysplastic classes with high precision using a Deep Learning method and existing pre-trained convolutional neural networks. Our results suggest that deep learning enhanced MPM for in-vivo skin cancer screening could facilitate timely diagnosis and intervention, enabling thus more optimal therapeutic approaches.

AB - Histopathological image analysis performed by a trained expert is currently regarded as the gold-standard for the diagnostics of many pathologies, including cancers. However, such approaches are laborious, time consuming and contain a risk for bias or human error. There is thus a clear need for faster, less intrusive and more accurate diagnostic solutions, requiring also minimal human intervention. Multiphoton microscopy (MPM) can alleviate some of the drawbacks specific to traditional histopathology by exploiting various endogenous optical signals to provide virtual biopsies that reflect the architecture and composition of tissues, both in-vivo or ex-vivo. Here we show that MPM imaging of the dermoepidermal junction (DEJ) in unstained fixed tissues provides useful cues for a histopathologist to identify the onset of non-melanoma skin cancers. Furthermore, we show that MPM images collected on the DEJ, besides being easy to interpret by a trained specialist, can be automatically classified into healthy and dysplastic classes with high precision using a Deep Learning method and existing pre-trained convolutional neural networks. Our results suggest that deep learning enhanced MPM for in-vivo skin cancer screening could facilitate timely diagnosis and intervention, enabling thus more optimal therapeutic approaches.

U2 - 10.1364/BOE.11.000186

DO - 10.1364/BOE.11.000186

M3 - Article

VL - 11

SP - 186

EP - 199

JO - Biomedical Optics Express

JF - Biomedical Optics Express

SN - 2156-7085

IS - 1

ER -