“…The remainder describe differences in descriptors in glomeruli from normal and pathologic populations, rather than isolating and labeling different glomeruli within the same wide image field. The current study [27] WSI, anti-desmin, fixed rat segmentation (normal, diabetic) [28] field, anti-nestin, fixed rat segmentation, characterization (normal, renal failure) [23] WSI, PAS, fixed mouse segmentation (normal) [25] WSI, Jones H&E/PAS/other, fixed human segmentation (normal) [22] WSI, H&E/PAS/others human, mouse, rat segmentation, characterization (normal, diabetic) [29] WSI, H&E primate segmentation, characterization (normal, diseased) [30] WSI, Masson's trichrome human segmentation - [31] field, H&E mouse segmentation - [24] patch, PAS human segmentation - [32] patch rat segmentation, characterization (normal, hypertrophy) [33] patch, H&E/PAS, fixed human segmentation, characterization (normal, proliferating) [34], [35] patch, H&E/PAS, fixed mouse, rat segmentation, characterization (normal) [36]- [38] patch -segmentation demonstrates the novel use of CNNs applied to frozen H&E sections to detect non-sclerotic and sclerotic glomeruli to assist pathologists in intra-operative interpretation of percent global glomerulosclerosis.…”