1
|
Ternes L, Dane M, Gross S, Labrie M, Mills G, Gray J, Heiser L, Chang YH. A multi-encoder variational autoencoder controls multiple transformational features in single-cell image analysis. Commun Biol 2022; 5:255. [PMID: 35322205 PMCID: PMC8943013 DOI: 10.1038/s42003-022-03218-x] [Citation(s) in RCA: 16] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2021] [Accepted: 03/07/2022] [Indexed: 01/02/2023] Open
Abstract
Image-based cell phenotyping relies on quantitative measurements as encoded representations of cells; however, defining suitable representations that capture complex imaging features is challenged by the lack of robust methods to segment cells, identify subcellular compartments, and extract relevant features. Variational autoencoder (VAE) approaches produce encouraging results by mapping an image to a representative descriptor, and outperform classical hand-crafted features for morphology, intensity, and texture at differentiating data. Although VAEs show promising results for capturing morphological and organizational features in tissue, single cell image analyses based on VAEs often fail to identify biologically informative features due to uninformative technical variation. Here we propose a multi-encoder VAE (ME-VAE) in single cell image analysis using transformed images as a self-supervised signal to extract transform-invariant biologically meaningful features, including emergent features not obvious from prior knowledge. We show that the proposed architecture improves analysis by making distinct cell populations more separable compared to traditional and recent extensions of VAE architectures and intensity measurements by enhancing phenotypic differences between cells and by improving correlations to other analytic modalities. Better feature extraction and image analysis methods enabled by the ME-VAE will advance our understanding of complex cell biology and enable discoveries previously hidden behind image complexity ultimately improving medical outcomes and drug discovery.
Collapse
Affiliation(s)
- Luke Ternes
- Biomedical Engineering Department, Oregon Health & Science University, Portland, OR, 97239, USA
| | - Mark Dane
- Biomedical Engineering Department, Oregon Health & Science University, Portland, OR, 97239, USA
| | - Sean Gross
- Biomedical Engineering Department, Oregon Health & Science University, Portland, OR, 97239, USA
| | - Marilyne Labrie
- Cell, Developmental and Cancer Biology Department, Oregon Health & Science University, Portland, OR, 97239, USA
| | - Gordon Mills
- Cell, Developmental and Cancer Biology Department, Oregon Health & Science University, Portland, OR, 97239, USA
| | - Joe Gray
- Biomedical Engineering Department, Oregon Health & Science University, Portland, OR, 97239, USA
| | - Laura Heiser
- Biomedical Engineering Department, Oregon Health & Science University, Portland, OR, 97239, USA.
| | - Young Hwan Chang
- Biomedical Engineering Department, Oregon Health & Science University, Portland, OR, 97239, USA.
| |
Collapse
|