Quality control of immunofluorescence images using artificial intelligence

Fluorescent imaging has revolutionized biomedical research, enabling the study of intricate cellular processes. Multiplex immunofluorescent imaging has extended this capability, permitting the simultaneous detection of multiple markers within a single tissue section. However, these images are susceptible to a myriad of undesired artifacts, which compromise the accuracy of downstream analyses. Manual artifact removal is impractical given the large number of images generated in these experiments, necessitating automated solutions. Here, we report the development of QUALIFAI (quality control of immunofluorescence images using artificial intelligence), a deep-learning-based tool designed to automate the identification of common artifacts in fluorescent imaging. We demonstrate the utility of QUALIFAI in detecting five of the most common types of artifacts in fluorescent imaging, achieving over 90% classification accuracy and a more than 0.6 intersection over union score across all artifact types in a variety of multiplexing platforms. Finally, we show how the implementation of QUALIFAI leads to more reliable results in downstream analysis. [Display omitted] •A deep-learning-based tool, QUALIFAI, is developed and demonstrated•QUALIFAI automates artifact detection in fluorescent imaging•QUALIFAI excels in classification and segmentation across multiplexing platforms•QUALIFAI improves reliability in spatial proteomics multiplexing analysis Andhari et al. introduce QUALIFAI, an advanced AI-driven tool designed for the automated detection of common artifacts in fluorescent imaging across various multiplexing platforms. This innovative tool significantly enhances the accuracy and reliability of spatial proteomics analysis, offering a valuable asset for researchers in diverse scientific fields.