New Window [code] [issues] [dir] [json] [YouTube (demo)] loading ...

Tumor Infitrating Lynphocytes (TILs)

Tumor formation requires evading the surveillance of the patient's own immune system. As such, the visualization of the immune response mediated by Lymphocytes has an important prognostic value for the understanding and treatment of cancer. To that end, large collaboratory initiatives like tilsinbreastcancer.org bring together distributed efforts to analyse and classify histopathology slides, each with up to a million individual cells.

Deep Learning (AI)

Deep Learning, an Artificial Intelligence (AI) technique, was used here to scale and automate the laborious TIL and cancer cell classification by Pathologists. This web-based tool provides an interface with tissue images synthesized from the AI predictions, which can be interactivelly mapped to the raw images they classify. The result is a collection of 1015 breast cancer whole slide images and their respective synthetic AI maps. The slide images come from the public The Cancer Genome Atlas (TCGA), and the AI calssification image maps are similarly made publicly available with this tool. To use the interactive tool where AI classifications are mapped to whole slides of breast tumors


For more information and methodological detail see published manuscript:

Han Le, Rajarsi Gupta, Le Hou, Shahira Abousamra, Danielle Fassler, Tahsin Kurc, Dimitris Samaras, Rebecca Batiste, Tianhao Zhao, Alison L. Van Dyke, Ashish Sharma, Erich Bremer, Jonas S Almeida, Joel Saltz (2020) Utilizing Automated Breast Cancer Detection to Identify Spatial Distributions of Tumor Infiltrating Lymphocytes in Invasive Breast Cancer. Am J. Pathol. (20)30188-7. [PMID:32277893].