Are you looking for a fully integrated approach for detecting, segmenting, and classifying tissue biopsies? NCI-funded researchers have a new model, called “CelloType,” that merges machine learning technologies to give you an end-to-end approach for automatically analyzing cancer cells and tissues. Read on to learn more about this model and to gain access to its software on GitHub.

In a recent study, the researchers found CelloType excelled in identifying both cell and non-cell characteristics. For example, using CelloType, the researchers were able to capture noncellular components (e.g., vasculature and bone matrix) as well as cells with varying shapes (e.g., macrophages and fat cells), which often are difficult to decipher. The model not only helps you annotate cell types, but also lets you segment and classify these structures.

Corresponding author, Dr. Kai Tan, of the Children’s Hospital of Philadelphia and the University of Pennsylvania, said, “Today’s spatial omics technologies rely on accurate cell segmentation. We can apply CelloType to a wide variety of images and classify highly diverse cell types. This information enables us to better understand gene and protein expression and other cancer causing events linked to those specific cells.”

He noted, “We are just beginning to unlock the potential of spatial omics technologies. CelloType advances spatial omics by providing a robust, scalable tool for analyzing complex tissue architectures, thereby expediting discoveries in cellular interactions, tissue function, and disease mechanisms.”

NCI’s Program Officer, Dr. Miguel Ossandron, added, “Spatial transcriptomic technologies can generate enormous amount of data (e.g., profiling hundreds of thousands of genes at the single cell level), challenging current methods for analysis. Deep learning tools like CelloType facilitate the annotation of omics data and streamline the way we profile the genes and gene products that drive cancer. Different from traditional methods, CelloType implements a multi-task learning approach, improving performance and offering a unified framework for detecting, segmenting, and classifying cellular components. These technologies are poised to revolutionize the way we diagnose, treat, and track cancer’s progression.”