DLBCL-Morph

A publicly available dataset containing 42 digitally scanned high-resolution tissue microarrays (TMAs) from 209 DLBCL cases at Stanford Hospital. Each TMA was stained for H&E as well as for BCL2, BCL6, MYC, CD10 and MUM1 gene expression. All of the TMAs are accompanied by pathologist-annotated regions-of-interest (ROIs) that indicate areas representative of DLBCL. For each patient in the dataset, we provide survival data, follow-up status, and a wide range of clinical and molecular variables such as age and MYC/BCL2/BCL6 gene translocations. We also segmented out tumor nuclei from ROIs inside the H&E stained TMAs, and provide several geometric features for each tumor nucleus.