Poster Abstract 024

DigiPathLondon 2023

Counting in the Name of Nuclei Quantification of Pathologists Vs. Conventional Thresholding Algorithm Vs. Deep Learning Algorithm

Christopher Günther, Nickels Winkler, Jan N. Peters, Cora Lohse, Bernd Gromoll
Crown Bioscience Germany, Hamburg, Germany

The detection and segmentation of cell nuclei is a crucial step in most digital image analysis workflows. The accuracy of the recognition results is of utmost importance, especially when advancing to more sophisticated target recognition and quantification. As deep neural network algorithms are increasingly used to recognize nuclei of different shapes, sizes, and staining intensities, it is of interest to compare the detection result of a Deep Learning (DL) algorithm with a conventional threshold (TH) approach and to see how a pathologist would evaluate the same region of interest.

Download this Poster to Discover:

• How the factors of the DL algorithm produced more favorable results, showing more precise, sensitive results producing fewer false events
  
  
• Insights into both algorithms and how each amount of TPs higher than the initial pathologist’s count for all cases, with a variation of +31 % for TH and +40 % for DL

Download Now

Download Now!