MIM-CyCIF: masked imaging modeling for enhancing cyclic immunofluorescence (CyCIF) with panel reduction and imputation
Year: 2024
Type: article
Abstract: CyCIF quantifies multiple biomarkers, but panel capacity is compromised by technical challenges including tissue loss. We propose a computational panel reduction, inferring surrogate CyCIF data from a subset of biomarkers. Our model reconstructs the information content from 25 markers using only 9 markers, learning co-expression and morphological patterns. We demonstrate strong correlations in predictions and generalizability across breast and colorectal cancer tissue microarrays, illustrating broader applicability to diverse tissue types.
Source: Communications Biology
Language: English
Subfield: Molecular Biology
Domain: Life Sciences
Open Access status: gold
Estimated APC paid: $3,890
Awards: G1037864568, Omic and Multidimensional Spatial Atlas of Metastatic Breast and Prostate Cancers, Measuring, Modeling and Controlling Heterogeneity, G575840262, Integrative single cell analyses of inflammation-derived circulating hybrid cells to identify aggressive disease, OHSU Knight Cancer Institute
OpenAlex ID: W4393862047