Back

Breast Cancer Reaction-Diffusion from Spectral-Spatial Analysis in Immunohistochemistry

Pasetto, S.; Zahid, M. U.; Diaz, R.; Montejo, M.; Rosa, M.; Gatenby, R.; Enderling, H.

2022-07-11 cancer biology
10.1101/2022.07.10.499460 bioRxiv
Show abstract

Cancer is a prevalent disease, and while many significant advances have been made, the ability to accurately predict how an individual tumor will grow - and ultimately respond to therapy - remains limited. We use spatial-spectral analysis of 20 patients accrued to a phase II study of preoperative SABR with 9.5 x 3 Gy for early-stage breast cancer whose tissues were stained with multiplex immunofluorescence. We employ the reaction-diffusion framework to compare the data-deduced two-point correlation function and the corresponding spatial power spectral distribution with the theoretically predicted ones. A single histopathological slice suffices to characterize the reaction-diffusion equation dynamics through its power spectral density giving us an interpretative key in terms of infiltration and diffusion of cancer on a per-patient basis. This novel approach tackles model-parameter-inference problems for tumor infiltration and can immediately inform clinical treatments.

Matching journals

The top 6 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.