Theia: Bleed-Through Estimation with Interaction Terms and Convolutional Kernels

Le résumé fourni par la source

Advances in multiplexed fluorescent microscopy have significantly increased the quality and utility of multi-channel biomedical images. With these advances, the problem of bleed-through across channels has become increasingly prevalent. Bleed-through negatively impacts analyses such as fluorescent marker correlation and cellular and subcellular segmentation. We present Theia, a novel convolutional kernal LASSO model for bleed-through estimation. Theia intelligently and automatically identifies regions of interest in images, uses interaction terms to account for objects tagged with multiple fluorophores, accounts for pixel-scale spatial uncertainties with convolutional kernels, requires minimal a priori knowledge of emission spectra, and is highly performant even on inexpensive hardware. Theia also exhibits excellent performance as measured by the Pearson Correlation Coefficient.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.