PhenDiff: Revealing Subtle Phenotypes with Diffusion Models in Real Images (2312.08290v2)
Abstract: For the past few years, deep generative models have increasingly been used in biological research for a variety of tasks. Recently, they have proven to be valuable for uncovering subtle cell phenotypic differences that are not directly discernible to the human eye. However, current methods employed to achieve this goal mainly rely on Generative Adversarial Networks (GANs). While effective, GANs encompass issues such as training instability and mode collapse, and they do not accurately map images back to the model's latent space, which is necessary to synthesize, manipulate, and thus interpret outputs based on real images. In this work, we introduce PhenDiff: a multi-class conditional method leveraging Diffusion Models (DMs) designed to identify shifts in cellular phenotypes by translating a real image from one condition to another. We qualitatively and quantitatively validate this method on cases where the phenotypic changes are visible or invisible, such as in low concentrations of drug treatments. Overall, PhenDiff represents a valuable tool for identifying cellular variations in real microscopy images. We anticipate that it could facilitate the understanding of diseases and advance drug discovery through the identification of novel biomarkers.
- Alexis Lamiable et al., “Revealing invisible cell phenotypes with conditional generative modeling,” Nature Communications, vol. 14, 2022.
- “Unpaired image-to-image translation with limited data to reveal subtle phenotypes,” 2023.
- “Unpaired image-to-image translation using cycle-consistent adversarial networks,” 2020.
- Thomas Boyer, “Phendiff,” github.com/ WarmongeringBeaver/PhenDiff, 2023.
- “Generative adversarial networks,” 2014.
- “Image-to-image translation with conditional adversarial networks,” 2018.
- “Learning to discover cross-domain relations with generative adversarial networks,” 2017.
- “Dualgan: Unsupervised dual learning for image-to-image translation,” 2018.
- “Bbdm: Image-to-image translation with brownian bridge diffusion models,” 2023.
- “Dual diffusion implicit bridges for image-to-image translation,” in The Eleventh International Conference on Learning Representations, 2023.
- “Denoising diffusion probabilistic models,” 2020.
- “Denoising diffusion implicit models,” 2022.
- “Generative modeling by estimating gradients of the data distribution,” 2020.
- “Score-based generative modeling through stochastic differential equations,” 2021.
- Anne Carpenter et al, “Cellprofiler: Image analysis software for identifying and quantifying cell phenotypes,” Genome biology, vol. 7, pp. R100, 02 2006.
- “A survey of convolutional neural networks: Analysis, applications, and prospects,” 2020.
- “No free lunch in self supervised representation learning,” 2023.
- “Comparison of semi-supervised learning methods for high content screening quality control,” 2022.
- “U-net: Convolutional networks for biomedical image segmentation,” CoRR, vol. abs/1505.04597, 2015.
- “Null-text inversion for editing real images using guided diffusion models,” 2022.
- “Gan inversion: A survey,” 2022.
- Peter D. Caie et al., “High-Content Phenotypic Profiling of Drug Response Signatures across Distinct Cancer Cells,” Molecular Cancer Therapeutics, vol. 9, no. 6, pp. 1913–1926, 06 2010.
- Daupin K. et al. de Thonel A., Ahlskog J.K., “CBP-HSF2 structural and functional interplay in Rubinstein-Taybi neurodevelopmental disorder,” Nat Commun 13, 7002 (2022), 2022.
- Gaelle Boncompain et al., “Targeting ccr5 trafficking to inhibit hiv-1 infection,” Science Advances, vol. 5, no. 10, pp. eaax0821, 2019.