Are you sure you want to leave this community? Leaving the community will revoke any permissions you have been granted in this community.
URL: https://github.com/HMS-IDAC/UnMicst
Proper Citation: UnMICST (RRID:SCR_021050)
Description: Software tool as set of deep learning nuclei instance and semantic segmentation models that have been trained on 6 human tissue types: tonsil, small intestine, ovary, and cancers of brain, colon, prostate, and lung stained with Hoechst 33342 and combination of lamin B2 and nucleoporin98. Includes manually curated annotations as well as novel concept of introducing intentionally defocused and saturated images for robustness.
Synonyms: , Universal Models for Identifying Cells and Segmenting Tissue, UNet Model for Identifying Cells and Segmenting Tissue, UnMicst
Resource Type: segmentation software, data processing software, software application, image analysis software, software resource, image processing software
Keywords: segmentation, identifying cells, segmenting tissue, universal models, tissue image, cell segmentation
Expand AllWe found {{ ctrl2.mentions.all_count }} mentions in open access literature.
We have not found any literature mentions for this resource.
We are searching literature mentions for this resource.
Most recent articles:
{{ mention._source.dc.creators[0].familyName }} {{ mention._source.dc.creators[0].initials }}, et al. ({{ mention._source.dc.publicationYear }}) {{ mention._source.dc.title }} {{ mention._source.dc.publishers[0].name }}, {{ mention._source.dc.publishers[0].volume }}({{ mention._source.dc.publishers[0].issue }}), {{ mention._source.dc.publishers[0].pagination }}. (PMID:{{ mention._id.replace('PMID:', '') }})
A list of researchers who have used the resource and an author search tool
A list of researchers who have used the resource and an author search tool. This is available for resources that have literature mentions.
No rating or validation information has been found for UnMICST.
No alerts have been found for UnMICST.
Source: SciCrunch Registry