Assessing the Performance of Deep Learning for Automated Gleason Grading in Prostate Cancer.

Journal: Studies in health technology and informatics
Published Date:

Abstract

Prostate cancer is a dominant health concern calling for advanced diagnostic tools. Utilizing digital pathology and artificial intelligence, this study explores the potential of 11 deep neural network architectures for automated Gleason grading in prostate carcinoma focusing on comparing traditional and recent architectures. A standardized image classification pipeline, based on the AUCMEDI framework, facilitated robust evaluation using an in-house dataset consisting of 34,264 annotated tissue tiles. The results indicated varying sensitivity across architectures, with ConvNeXt demonstrating the strongest performance. Notably, newer architectures achieved superior performance, even though with challenges in differentiating closely related Gleason grades. The ConvNeXt model was capable of learning a balance between complexity and generalizability. Overall, this study lays the groundwork for enhanced Gleason grading systems, potentially improving diagnostic efficiency for prostate cancer.

Authors

  • Dominik Müller
    IT-Infrastructure for Translational Medical Research, University of Augsburg, 86159 Augsburg, Germany.
  • Philip Meyer
    IT-Infrastructure for Translational Medical Research, University of Augsburg.
  • Lukas Rentschler
    Institute for Digital Medicine, University Hospital Augsburg, Germany.
  • Robin Manz
    Institute for Digital Medicine, University Hospital Augsburg, Germany.
  • Daniel Hieber
    Institute for Pathology, University Hospital Augsburg, Germany.
  • Jonas Bäcker
    Institute for Digital Medicine, University Hospital Augsburg, Germany.
  • Samantha Cramer
    Institute for Digital Medicine, University Hospital Augsburg, Germany.
  • Christoph Wengenmayr
    Institute for Digital Medicine, University Hospital Augsburg, Germany.
  • Bruno Märkl
    Department of Pathology, University Hospital of Augsburg, Augsburg, Germany.
  • Ralf Huss
    Institute of Pathology and Molecular Diagnostics, University Hospital Augsburg, Augsburg, Germany.
  • Frank Kramer
    IT-Infrastructure for Translational Medical Research, Faculty of Applied Computer Science, Faculty of Medicine, University of Augsburg, Augsburg, Germany.
  • Iñaki Soto-Rey
    IT-Infrastructure for Translational Medical Research, University of Augsburg.
  • Johannes Raffler
    Institute for Digital Medicine, University Hospital Augsburg, Augsburg, Germany.