Marker-specific pixel attribution for single-cell protein quantification with PixAQ

PixAQ improves single-cell protein quantification in imaging mass cytometry by using marker-specific probabilistic pixel attribution, yielding cohort-median patient-paired gains of 1.99–4.83 percentage points in expected-marker share.

• Why it matters: Shared cell-mask quantification can miss marker signals with distinct spatial patterns or mistakenly include neighboring-cell signals, limiting accuracy for single-cell protein measurements.
• What they did: PixAQ assigns each pixel to neighboring cells for each marker using spatial proximity plus anchor-group intensity models with an explicit residual, then averages original intensities over marker-specific supports.
• The result: In 366 patients across three cohorts (680 regions), PixAQ increased agreement with predefined population-marker relationships, and ablations showed both spatial and intensity evidence contributed to the gains.

AI summary of the abstract · may contain errors · not medical advice · read the paper.