loading page

SPECHT: Self-tuning Plausibility Based Object Detection Enables Quantification of Conflict in Heterogeneous Multi-scale Microscopy
  • +4
  • Ben Cardoen ,
  • Timothy Wong ,
  • Parsa Alan ,
  • Sieun Lee ,
  • Joanne Aiko Matsubara ,
  • Ivan Robert Nabi ,
  • Ghassan Hamarneh
Ben Cardoen
Simon Fraser University, Simon Fraser University, Simon Fraser University

Corresponding Author:[email protected]

Author Profile
Timothy Wong
Author Profile
Parsa Alan
Author Profile
Sieun Lee
Author Profile
Joanne Aiko Matsubara
Author Profile
Ivan Robert Nabi
Author Profile
Ghassan Hamarneh
Author Profile


We introduce a novel method that is able to localize fluorescent labelled objects in multi-scale 2D microscopy, and is robust to highly variable imaging conditions. Localized objects are then classified in a novel way using belief theory, requiring only the image level label. Each object is assigned a ‘belief’ that describes how likely it is to appear in an image with a given set of labels. We apply our method successfully to identify amyloid-beta deposits, associated with Alzheimer’s disease, and to discover caveolae and their modular components in superresolution microscpy. We illustrate how our approach allows the fusion or combination of models learned across markedly different datasets. We show how we can compute the ‘conflict’, or disagreement between the models, an insight that can allow the domain expert to interpret the composite model.
29 Dec 2022Published in PLOS ONE volume 17 issue 12 on pages e0276726. 10.1371/journal.pone.0276726