Bookmark Saya

arXiv Open Access 2021

Unsupervised Hyperspectral Stimulated Raman Microscopy Image Enhancement: Denoising and Segmentation via One-Shot Deep Learning

Pedram Abdolghader Andrew Ridsdale Tassos Grammatikopoulos Gavin Resch Francois Legare +3 lainnya
Lihat Sumber

Abstrak

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.

Topik & Kata Kunci

eess.SP physics.app-ph physics.optics

Penulis (8)

P

Pedram Abdolghader

A

Andrew Ridsdale

T

Tassos Grammatikopoulos

G

Gavin Resch

F

Francois Legare

A

Albert Stolow

A

Adrian F. Pegoraro

I

Isaac Tamblyn

Format Sitasi

APA MLA BibTeX
Abdolghader, P., Ridsdale, A., Grammatikopoulos, T., Resch, G., Legare, F., Stolow, A. et al. (2021). Unsupervised Hyperspectral Stimulated Raman Microscopy Image Enhancement: Denoising and Segmentation via One-Shot Deep Learning. https://arxiv.org/abs/2104.08338

Akses Cepat

Lihat di Sumber
Informasi Jurnal
Tahun Terbit
2021
Bahasa
en
Sumber Database
arXiv
Akses
Open Access ✓