External site

By following this link, you are leaving Medically and entering a website that is not owned or controlled by Roche. Roche does not take any responsibility for access to or use of this website, nor for any content therein.

Leave site
Roche and Genentech at

TUCSON Symposium 2023

-
Coming soon

Sign up or login to unlock the full suite of MEDICALLY features

May 2 / Roche
Synthetic Singleplex Image Generation for Multiplex-Brightfield Immunohistochemistry using Image-to-image Translation Methods
Multiplex-brightfield immunohistochemistry imaging(MPx) enables quantification of various biomarkers in tissue while retaining morphological and spatial information. Manual scoring of MPx is challenging, especially with co-localized biomarkers. Consequently, it requires unmixing methods to separate multiple-staining intensities and remix individual-staining intensity together with counterstain to become singleplex images(SPx). Pathologists confidently can read and score staining intensity on SPx. Nevertheless, to unmix MPx is challenging, especially when more than two-biomarkers co-localized. Conventional unmixing methods e.g.,color-deconvolution or Nonnegative-Matrix-Factorization remain limited and error prone to separate staining intensities of co-localized biomarkers in membrane or nuclear-subcellular compartments. Here, we exploit advances in generative-adversarial networks(GANs), especially of unpaired image-to-image translation using CycleGAN to generate synthetic SPx from MPx for pathologists’ read and scores.

Sign up or login to unlock the full suite of MEDICALLY features

May 2 / Roche

Sign up or login to unlock the full suite of MEDICALLY features

May 2 / Roche
An observational cohort study investigating the association between artificial intelligence- (AI) assisted tumor AREG and EREG immunohistochemistry (IHC) and outcomes from anti-EGFR therapy during the routine management of metastatic colorectal cancer (mCRC)
AREG and EREG are ligands of EGFR overexpressed by a subset of colorectal cancers (CRCs). Tumor AREG/EREG expression predicted benefit from anti-EGFR therapy in a previous retrospective analysis of the PICCOLO trial (second-line irinotecan ± panitumumab). This study sought to validate these findings in metastatic CRC patients who received anti-EGFR therapy during routine care.