A Pathologist-Annotated Dataset for Validating Artificial Intelligence: A Project Description and Pilot Study.

Purpose: Validating artificial intelligence algorithms for clinical use in medical images is a challenging endeavor due to a lack of standard reference data (ground truth). This topic typically occupies a small portion of the discussion in research papers since most of the efforts are focused on developing novel algorithms. In this work, we present a collaboration to create a validation dataset of pathologist annotations for algorithms that process whole slide images.

Leveraging advances in immunopathology and artificial intelligence to analyze in vitro tumor models in composition and space.

Cancer is the leading cause of death worldwide. Unfortunately, efforts to understand this disease are confounded by the complex, heterogenous tumor microenvironment (TME). Better understanding of the TME could lead to novel diagnostic, prognostic, and therapeutic discoveries.

Factual accuracy and the cultural context of science in popular media: Perspectives of media makers, middle school students, and university students on an entertainment television program.

Popular media influences ideas about science constructed by the public. To sway media productions, public policy organizations have increasingly promoted use of science consultants. This study contributes to understanding the connection from science consultants to popular media to public outcomes.

An interactive Web site providing major histocompatibility ligand predictions: application to HIV research.

EpiMatrix/HIV, a tool that is currently available on the World Wide Web, enables researchers to screen HIV proteins for potential MHC ligands. We have performed a comparison of EpiMatrix predictions to 158 published allotype-specific HLA-associated peptides (MHC ligands) derived from 133 proteins. The top 10 ranked EpiMatrix predictions for each of the 158 HLA allotype-protein pairs were selected for comparison with these published ligands.