domains / families / science / image-analysis
Segments cells/nuclei and extracts image features from imaging spatial transcriptomics (Xenium, MERFISH/MERSCOPE, CosMx) and H&E/IF tissue images using Cellpose, StarDist, Baysor, and Squidpy. Use when choosing a segmentation strategy (DAPI nucleus + expansion vs membrane-stain whole-cell vs transcript-aware Baysor/proseg vs segmentation-free SSAM) given the available stain; judging whether transcript spillover is fabricating false co-expression and short-range cell-cell signal; and deciding whether the derived cell-by-gene matrix is trustworthy before downstream typing, DE, or ligand-receptor analysis.
The two skills cover the same domain but diverge on scope and method. The first copy is a procedural recipe for Squidpy-based feature extraction and basic segmentation on Visium/H&E data. The second copy is a strategic guide for imaging spatial transcriptomics (Xenium/MERFISH/CosMx) that prioritizes segmentation strategy selection (Cellpose, StarDist, Baysor, proseg) and includes critical warnings about segmentation artifacts and spillover. The first copy lacks the strategic decision-making and artifact warnings, while the second copy lacks the specific Visium feature extraction code and H&E deconvolution steps found in the first. Combining them provides both the strategic framework for choosing a segmentation method and the concrete code for feature extraction.