Article

Interpretable deep learning of label-free live cell images uncovers functional hallmarks of highly-metastatic melanoma

2020-05-15

Abstract excerpt

Deep convolutional neural networks have emerged as a powerful technique to identify hidden patterns in complex cell imaging data. However, these machine learning techniques are often criticized as uninterpretable “black-boxes” - lacking the ability to provide meaningful explanations for the cell properties that drive the machine’s prediction. Here, we demonstrate that the latent features extracted from label-free...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: a6c768bf-54c2-5027-99f2-897d4693933a
DOI: 10.1101/2020.05.15.096628

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Interpretable deep learning of label-free live cell images uncovers functional hallmarks of highly-metastatic melanomaDOI 10.1101/2020.05.15.096628Read

High accuracy label-free classification of kinetic cell states from holographic cytometrySemantic proximity Read

Unambiguous signatures of malignancies extracted from images of growing cellsSemantic proximity Read

Information-Distilled Generative Label-Free Morphological Profiling Encodes Cellular HeterogeneitySemantic proximity Read

3D single-cell shape analysis using geometric deep learningSemantic proximity Read

Biophysical informatics reveals distinctive phenotypic signatures and functional diversity of single-cell lineages.Semantic proximity Read

Label-Free Melanoma Phenotype Classification Using Artificial Intelligence-Based Morphological ProfilingSemantic proximity Read

Image-based cell phenotyping with deep learning.Semantic proximity Read

Deep learning-driven morphology analysis enables label-free classification of therapeutic agentnaive versus resistant cancer cellsSemantic proximity Read

Microenvironmental information significantly improves the recognition of cell types in human lung cancer patientsSemantic proximity Read

Generalizable Morphological Profiling of Cells by Interpretable Unsupervised LearningSemantic proximity Read

Generative machine learning unlocks the first proteome-wide image of human cellsSemantic proximity Read

Multi-view deep learning of highly multiplexed imaging data improves association of cell states with clinical outcomesSemantic proximity Read