Digital Pathology Pipeline

Tools for automatic glomerulus identification and histological quantification from scanned PAS slides

Histological scores could be used, in combination with other physiological measures, to significantly advance renal research. However, the available methods to score histological samples, specifically glomeruli, do not allow for collection of this necessary data in a high-throughput and consistent manner. Neither untrained individuals nor computers are presently capable of identifying glomerular features, thus expert pathologists must do the identification by eye and score the result in a categorical matrix, complicating statistical analysis. We have developed a method, utilizing free existing software, that can automatically identify and score glomeruli. This method is usable without extensive image analysis training, can be applied to many varying data sets, and allows for fast glomerular identification and quantitative measurements of glomerular features. The GitHub directory below contains the instructions and scripts to set up the pipeline

Download Digital Pathology Pipeline



          Read the full manuscript          

Faculty & Staff

Ron Korstanje, Ph.D. Professor

Ron Korstanje, Ph.D.