Spatial features in NMF components align strikingly well with anatomical features in H&E-stained images.

<p>a) Example alignment for a CPH dataset showing H&E image, original NMF spatial components, and the aligned images which enhance identification of tissue structure. b) Alignment for a naïve dataset. Similar features are apparent in the raw and H&E images. However, the correlation is...

Full description

Saved in:

Bibliographic Details
Main Author:	Kasun Pathirage (19832012) (author)
Other Authors:	Aman Virmani (19832015) (author), Alison J. Scott (9428011) (author), Richard J. Traub (12553162) (author), Robert K. Ernst (127237) (author), Reza Ghodssi (705823) (author), Behtash Babadi (5156105) (author), Pamela Ann Abshire (19832018) (author)
Published:	2024
Subjects:	Biotechnology Immunology Space Science Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Chemical Sciences not elsewhere classified Information Systems not elsewhere classified powerful scientific tool negative matrix factorization large file sizes interpretable dimensionality reduction additional clustering steps second challenge unaddressed readily interpretable features different tissue types stained tissue images msi data processing components may also 20 &# 215 msi data analysis spectral components generate images first challenge features according data augmentation &# 8764 tissue structures tissue structure enhance tissue msi datasets msi dataset yielding spatial three orders support training spatial distribution small patches resolve two nmf data necessarily result meaningful correlation image registration female sprague enhanced specificity dawley rats cph ). correlate well control subjects biochemical compounds biggest challenges animal model 20 pixels
Tags:	Add Tag No Tags, Be the first to tag this record!

Spatial features in NMF components align strikingly well with anatomical features in H&E-stained images.

Similar Items