Open AccessUnsupervised hyperspectral stimulated Raman microscopy image enhancement: denoising and segmentation via one-shot deep learning
Author(s) -
Pedram Abdolghader,
Andrew Ridsdale,
Tassos Grammatikopoulos,
Gavin Resch,
François Légaré,
Albert Stolow,
Adrian F. Pegoraro,
Isaac Tamblyn
Publication year - 2021
Publication title -
optics express
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.394
H-Index - 271
ISSN - 1094-4087
DOI - 10.1364/oe.439662
Subject(s) - hyperspectral imaging , artificial intelligence , noise reduction , pattern recognition (psychology) , computer science , cluster analysis , unsupervised learning , microscopy , segmentation , sample (material) , noise (video) , deep learning , chemical imaging , computer vision , optics , image (mathematics) , physics , thermodynamics
Hyperspectral stimulated Raman scattering (SRS) microscopy is a label-free technique for biomedical and mineralogical imaging which can suffer from low signal-to-noise ratios. Here we demonstrate the use of an unsupervised deep learning neural network for rapid and automatic denoising of SRS images: UHRED (Unsupervised Hyperspectral Resolution Enhancement and Denoising). UHRED is capable of "one-shot" learning; only one hyperspectral image is needed, with no requirements for training on previously labelled datasets or images. Furthermore, by applying a k-means clustering algorithm to the processed data, we demonstrate automatic, unsupervised image segmentation, yielding, without prior knowledge of the sample, intuitive chemical species maps, as shown here for a lithium ore sample.