Unraveling the deep learning gearbox in optical coherence tomography image segmentation towards explainable artificial intelligence.

Journal: Communications biology
Published Date: Feb 5, 2021

Abstract

Machine learning has greatly facilitated the analysis of medical data, while the internal operations usually remain intransparent. To better comprehend these opaque procedures, a convolutional neural network for optical coherence tomography image segmentation was enhanced with a Traceable Relevance Explainability (T-REX) technique. The proposed application was based on three components: ground truth generation by multiple graders, calculation of Hamming distances among graders and the machine learning algorithm, as well as a smart data visualization ('neural recording'). An overall average variability of 1.75% between the human graders and the algorithm was found, slightly minor to 2.02% among human graders. The ambiguity in ground truth had noteworthy impact on machine learning results, which could be visualized. The convolutional neural network balanced between graders and allowed for modifiable predictions dependent on the compartment. Using the proposed T-REX setup, machine learning processes could be rendered more transparent and understandable, possibly leading to optimized applications.

Authors

  • Peter M Maloca
    OCTlab, Department of Ophthalmology, University of Basel, Basel, Switzerland.
  • Philipp L Müller
    Universitäts-Augenklinik Bonn, Bonn, Deutschland.
  • Aaron Y Lee
    Department of Ophthalmology, University of Washington, Seattle, Washington.
  • Adnan Tufail
    London, United Kingdom. Electronic address: Adnan.Tufail@moorfields.nhs.uk.
  • Konstantinos Balaskas
    School of Pharmacy and Optometry, Faculty of Biology, Medicine and Health, The University of Manchester, Manchester, United Kingdom; Manchester Royal Eye Hospital, NHS Central Manchester University Hospitals, Manchester, United Kingdom.
  • Stephanie Niklaus
    Pharma Research and Early Development (pRED), Pharmaceutical Sciences (PS), Roche, Innovation Center Basel, Basel, Switzerland.
  • Pascal Kaiser
    Biotechnologie & Physik, Supercomputing Systems, Zürich, Switzerland.
  • Susanne Suter
    Supercomputing Systems, Zurich, Switzerland.
  • Javier Zarranz-Ventura
    Institut Clínic d'Oftalmologia, Hospital Clínic de Barcelona, Barcelona, Spain.
  • Catherine Egan
    NIHR Biomedical Research Centre at Moorfields Eye Hospital and UCL Institute of Ophthalmology, London, UK.
  • Hendrik P N Scholl
    Department of Ophthalmology, University of Basel, Basel, Switzerland.
  • Tobias K Schnitzer
    Pharma Research and Early Development (pRED), Pharmaceutical Sciences (PS), Roche, Innovation Center Basel, Basel, Switzerland.
  • Thomas Singer
    Pharma Research and Early Development (pRED), Pharmaceutical Sciences (PS), Roche, Innovation Center Basel, Basel, Switzerland.
  • Pascal W Hasler
    OCTlab, Department of Ophthalmology, University of Basel, Basel, Switzerland.
  • Nora Denk
    Department of Ophthalmology, University of Basel, Basel, Switzerland.

Keywords

External Resources

Popular Topics
Recent Journals