Multiplex computational pathology for treatment response predication

Ming Y Lu; Houssein A Sater; Faisal Mahmood

doi:10.1016/j.ccell.2021.07.014

Multiplex computational pathology for treatment response predication

Cancer Cell. 2021 Aug 9;39(8):1053-1055. doi: 10.1016/j.ccell.2021.07.014.

Authors

Ming Y Lu¹, Houssein A Sater², Faisal Mahmood³

Affiliations

¹ Department of Pathology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA 02115, USA; Cancer Program, Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA; Cancer Data Science Program, Dana-Farber Cancer Institute, Boston, MA 02115, USA.
² Cleveland Clinic Martin Health Center for Clinical Research, Stuart, FL 34994, USA.
³ Department of Pathology, Brigham and Women's Hospital, Harvard Medical School, Boston, MA 02115, USA; Cancer Program, Broad Institute of Harvard and MIT, Cambridge, MA 02142, USA; Cancer Data Science Program, Dana-Farber Cancer Institute, Boston, MA 02115, USA. Electronic address: [email protected].

PMID: 34375608
DOI: 10.1016/j.ccell.2021.07.014

Abstract

Recently published in Science, AstroPath outlines a standardized workflow for multiplex immunofluorescence (mIF) panel development, imaging, and analysis; showcases its potential in biomarker discovery for predicting response to anti-PD-1 treatment; and paves the way for large-scale computational pathology studies on high-quality mIF datasets using data-driven machine-learning techniques.

Publication types

Research Support, N.I.H., Extramural
Research Support, Non-U.S. Gov't
Comment

MeSH terms

Fluorescent Antibody Technique
Humans
Machine Learning*
Workflow