Software tool analyzes cancer cells in biopsy slides

An innovative software tool could advance cancer pathology by providing diagnostic information from tissue biopsies. The tool, called METI (Morphology-Enhanced Spatial Transcriptome Analysis Integrator), was developed by researchers at MD Anderson and Emory.

METI provides a platform for integrating data based on the appearance and organization of cells in a biopsy sample (histology), as well as the active genes within them. It allows the identification of both cancer cells and other cells, such as healthy cells or immune cells that have migrated into a tumor. The presence of immune cells and the spatial organization of cells in a biopsy sample are often critical to diagnosis.

“The main contribution of METI is its ability to accurately identify tumor cells and other components of the tumor microenvironment, integrating both molecular and morphological information,” said co-senior author Jian Hu, Ph.D., assistant professor of human genetics at Emory School of Medicine and director of the AI ​​in Genomics Laboratory.

To create METI, Hu worked with Linghua Wang, MD, PhD, and her lab at MD Anderson Cancer Center, as well as a team of experienced pathologists. They describe the software’s performance in a paper published in Nature CommunicationsThe software is available, with a user-friendly interface for data visualization, on GitHub.

The researchers evaluated METI’s performance on biopsy samples from lung and bladder cancers at MD Anderson and gastric cancers from Zhejiang Cancer Hospital in China. According to Hu, the software can be applied to many types of cancer because it relies on gene expression and morphological signatures common to various cancers.

METI is an unsupervised method that incorporates domain knowledge from previous publications on cancer genomics to guide its machine learning model.