Interpretable deep learning uncovers cellular properties in label-free live cell images that are predictive of highly metastatic melanoma

Assaf Zaritsky, Andrew R. Jamieson, Erik S. Welf, Andres Nevarez, Justin Cillay, Ugur Eskiocak, Brandi L. Cantarel, Gaudenz Danuser

Research output: Contribution to journalArticlepeer-review

6 Scopus citations

Abstract

Deep learning has emerged as the technique of choice for identifying hidden patterns in cell imaging data but is often criticized as “black box.” Here, we employ a generative neural network in combination with supervised machine learning to classify patient-derived melanoma xenografts as “efficient” or “inefficient” metastatic, validate predictions regarding melanoma cell lines with unknown metastatic efficiency in mouse xenografts, and use the network to generate in silico cell images that amplify the critical predictive cell properties. These exaggerated images unveiled pseudopodial extensions and increased light scattering as hallmark properties of metastatic cells. We validated this interpretation using live cells spontaneously transitioning between states indicative of low and high metastatic efficiency. This study illustrates how the application of artificial intelligence can support the identification of cellular properties that are predictive of complex phenotypes and integrated cell functions but are too subtle to be identified in the raw imagery by a human expert. A record of this paper's transparent peer review process is included in the supplemental information. Video Abstract: [Figure presented]

Original languageEnglish (US)
Pages (from-to)733-747.e6
JournalCell Systems
Volume12
Issue number7
DOIs
StatePublished - Jul 21 2021

Keywords

  • interpretable deep learning
  • live cell imaging
  • melanoma metastasis

ASJC Scopus subject areas

  • Pathology and Forensic Medicine
  • Histology
  • Cell Biology

Fingerprint

Dive into the research topics of 'Interpretable deep learning uncovers cellular properties in label-free live cell images that are predictive of highly metastatic melanoma'. Together they form a unique fingerprint.

Cite this