Skip to main content
Fig. 3 | BMC Bioinformatics

Fig. 3

From: CellSeg: a robust, pre-trained nucleus segmentation and pixel quantification software for highly multiplexed fluorescence images

Fig. 3

CellSeg performance on diverse human FFPE tissues. CellSeg performance on representative tissue images from a multi-tumor tissue microarray imaged with CODEX, all stains are DRAQ5 nuclear stain. A. Healthy spleen shows small cells. B. Dermatofibrosarcoma protuberans (DFSP) shows spindly nuclei. C. Glioblastoma multiforme (GBM) shows large, misshapen cells. D. Hepatocellular carcinoma (HCC) shows large, round cells. E. Seminoma shows a blend of large tumor cell nuclei and small nuclei from tumor-infiltrating lymphocytes. F. T-cell acute lymphoblastic leukemia (T-ALL) shows densely packed cells. Scale bar, 20 μm. Fluorescence intensity increased in original images for visualization purposes

Back to article page

BMC Bioinformatics

ISSN: 1471-2105

Contact us