Abstract

Convolutional neural networks were used to accurately segment both H&E-stained tissue sections and in vivo autofluorescence images of skin wounds, which enabled automated, quantitative analysis of a variety of wound features.

© 2020 The Author(s)

PDF Article
More Like This
Deep Learning-Based Virtual Staining of Unlabeled Tissue Samples

Kevin de Haan, Yair Rivenson, Zhensong Wei, Hongda Wang, Tairan Liu, W. Dean Wallace, and Aydogan Ozcan
MM3A.3 Microscopy Histopathology and Analytics (Microscopy) 2020

Longitudinal Monitoring of Skin Wounds In Vivo Using Label-free Multiphoton Microscopy

Jake D. Jones, Hallie E. Ramser, Alan Woessner, and Kyle P. Quinn
CTh4B.3 Clinical and Translational Biophotonics (Translational) 2018

Machine Learning Methods for Barret’s and Dysplasia classification from In Vivo Optical Coherence Tomography Images of Human Esophagus

Christos Photiou, George Plastiras, Guillermo Tearney, and Costas Pitris
OW2E.4 Optical Coherence Tomography (OCT) 2020

References

You do not have subscription access to this journal. Citation lists with outbound citation links are available to subscribers only. You may subscribe either as an OSA member, or as an authorized user of your institution.

Contact your librarian or system administrator
or
Login to access OSA Member Subscription