The development of CRISPR-Cas9 genome editing technology has led to the emergence of a new generation of novel life sciences applications. In drug discovery, researchers have harnessed the precision of selective gene knockouts by CRISPR to enable genome-wide drug screening. By mapping genotypes to phenotypes, CRISPR-based phenotypic screens can enable a better understanding of drug mechanism of actions (MOAs) and identification of novel druggable targets. However, current phenotypic CRISPR screening approaches rely heavily on microscopic imaging of target phenotypes, a process that imposes throughput limitations and restricts screening to only a handful of simple phenotypes based on binary fluorescence signals. To fully realize the potential of CRISPRbased phenotypic screening, here show application of the VisionSort platform to a pooled high throughput, labelfree CRISPR screening methodology targeting morphological phenotypes. As a proof-of-concept, we used this methodology to screen for genes involved in macrophage polarization.