Investigating human skin using deep learning enhanced multiphoton microscopy

Mikko J. Huttunen, Radu Hristu, Adrian Dumitru, Mariana Costache, Stefan G. Stanciu

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review


Histopathological image analysis of stained tissue slides is routinely performed by a pathologist to diagnose diseases, such as cancers. Although the approach is effective, it is labor-intensive, time-consuming and risks being biased. Therefore, it would be beneficial to develop faster and more cost-effective approaches. Multiphoton microscopy can alleviate these problems by allowing label-free imaging with high contrast. When label-free multiphoton microscopy is combined with deep learning based image analysis, a wide variety of possibilities arise for the real-time characterization and diagnosis of tissues. Here, we overview our recent work on this topic focusing on automated classification of tissue images taken from human skin near the dermoepidermal junction.

Original languageEnglish
Title of host publication21st International Conference on Transparent Optical Networks, ICTON 2019
ISBN (Electronic)9781728127798
Publication statusPublished - 1 Jul 2019
Publication typeA4 Article in conference proceedings
EventInternational Conference on Transparent Optical Networks - Angers, France
Duration: 9 Jul 201913 Jul 2019

Publication series

NameInternational Conference on Transparent Optical Networks
ISSN (Electronic)2161-2064


ConferenceInternational Conference on Transparent Optical Networks


  • Deep learning
  • Label-free
  • Machine learning
  • Nonlinear microscopy
  • Tissue characterization

Publication forum classification

  • Publication forum level 1

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Electrical and Electronic Engineering
  • Electronic, Optical and Magnetic Materials


Dive into the research topics of 'Investigating human skin using deep learning enhanced multiphoton microscopy'. Together they form a unique fingerprint.

Cite this