Open Jwong684 opened 5 months ago
@Jwong684 sorry for delay in response. Baysor is too slow to run for a reasonable size of spatial dataset and it's known to have tendency of over-segmentation in the area with no strong evidence of cells in IF images. The default CosMx segmentations use all 5 channels of IF staining, including CD68 if it's in the morphology kit. So I'm not sure what do you mean by no way to integrating all IF stains. FastReseg is designed to perform transcription-informed refinement upon image-based cell segmentation, so it would also be able to take advantage of all IF stains if you have included them in initial cell segmentation.
Hi Nanostring team,
I came upon this repo while looking through your available modules. I am currently working with CosMx data and have opted to using Baysor at the moment for resegmentation. I was wondering if you guys have tried to test this tool as a benchmark against other more widely known tools.
I guess one outstanding issue with the CosMx data at the moment is that there is no way to integrate all the different IF staining as additional information to inform on segmentation (i.e. CD68 markers for macrophages). Do you think that would be something that could be integrated eventually?
Thank you!