Agreement of two pre-trained deep-learning neural networks built with transfer learning with six pathologists on 6000 patches of prostate cancer from Gleason2019 Challenge.
Journal:
Romanian journal of morphology and embryology = Revue roumaine de morphologie et embryologie
Published Date:
Jan 1, 2020
Abstract
INTRODUCTION: While the visual inspection of histopathology images by expert pathologists remains the golden standard method for grading of prostate cancer the quest for developing automated algorithms for the job is set and deep-learning techniques have emerged on top of other approaches.