Login / Signup

MIM-CyCIF: masked imaging modeling for enhancing cyclic immunofluorescence (CyCIF) with panel reduction and imputation.

Zachary SimsGordon B MillsYoung Hwan Chang
Published in: Communications biology (2024)
Cyclic Immunofluorescence (CyCIF) can quantify multiple biomarkers, but panel capacity is limited by technical challenges. We propose a computational panel reduction approach that can impute the information content from 25 markers using only 9 markers, learning co-expression and morphological patterns while concurrently increasing speed and panel content and decreasing cost. We demonstrate strong correlations in predictions and generalizability across breast and colorectal cancer, illustrating applicability of our approach to diverse tissue types.
Keyphrases
  • poor prognosis
  • high resolution
  • healthcare
  • health information
  • long non coding rna
  • binding protein
  • social media
  • photodynamic therapy