Study Background
- Fluorescent imaging technologies now allow for multiplex immunofluorescence (mIF) of up to 100 targets on a single slide. However, the ability to quantitatively analyze the resulting data, especially on whole-slide images (WSI), is limited by scalability and reproducibility.
- Currently used platforms for segmenting cancer cells and nuclei involve segmentation algorithms that are hand-tuned on individual fields of view, making these methods subjective and difficult to replicate.
- To this end, we sought to develop an end-to-end workflow for WSI mIF data in cancer, from raw images to cell-level features (Fig. 1), using stateof-the-art deep learning models for tissue, cell, and nuclei segmentation.
Waleed Tahir 1,*, Emma Krause 1,*, Judy Shen 1, Vignesh Valaboju 1, Jin Li 1, Howard Mak 1, Mohammad Mirzadeh 1, Kevin Rose 1, Guillaume Chhor 1, Joseph Lee 1, Jun Zhang 1, Jacqueline Brosnan-Cashman 1, Michael G. Drage 1, Justin Lee 1, Carlee Hemphill 2, Saumya Pant 2, Robert Egger 1
1PathAI, Boston, Massachusetts
2PathAI Biopharma Lab, Memphis, Tennessee
*Contributed equally to this study.