# PhenDiff: Revealing Subtle Phenotypes with Diffusion Models in Real Images

arXiv: https://arxiv.org/abs/2312.08290 · HTML: https://mlsanity.com/paper/2312.08290/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Medical imaging and segmentation, one of 14 directions in Diffusion models.
- Builds on 10 of its 20 references that are in the map.
- First posted on arXiv 13 Dec 2023.

## Placed in

- Diffusion models / [Medical imaging and segmentation](https://mlsanity.com/diffusion/medical-imaging-and-segmentation/)

## Builds on (most cited first, 10 of 10)

- [Denoising Diffusion Probabilistic Models](https://mlsanity.com/paper/2006.11239/) (2020)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Diffusion Models Beat GANs on Image Synthesis](https://mlsanity.com/paper/2105.05233/) (2021)
- [Image-to-Image Translation with Conditional Adversarial Networks](https://mlsanity.com/paper/1611.07004/) (2016)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [StarGAN: Unified Generative Adversarial Networks for Multi-Domain Image-to-Image Translation](https://mlsanity.com/paper/1711.09020/) (2017)
- [Dual Diffusion Implicit Bridges for Image-to-Image Translation](https://mlsanity.com/paper/2203.08382/) (2022)
- [Predicting Cellular Responses to Novel Drug Perturbations at a Single-Cell Resolution](https://mlsanity.com/paper/2204.13545/) (2022)
- [Improving Inversion and Generation Diversity in StyleGAN using a Gaussianized Latent Space](https://mlsanity.com/paper/2009.06529/) (2020)
- [Unpaired Image-to-Image Translation with Limited Data to Reveal Subtle Phenotypes](https://mlsanity.com/paper/2302.08503/) (2023)

## Built on by (most cited first, 11 of 11)

- [CellFlux: Simulating Cellular Morphology Changes via Flow Matching](https://mlsanity.com/paper/2502.09775/) (2025)
- [CellFluxRL: Biologically-Constrained Virtual Cell Modeling via Reinforcement Learning](https://mlsanity.com/paper/2603.21743/) (2026)
- [Compressing Biology: Evaluating the Stable Diffusion VAE for Phenotypic Drug Discovery](https://mlsanity.com/paper/2510.19887/) (2025)
- [Elucidating the Design Space of Flow Matching for Cellular Microscopy](https://mlsanity.com/paper/2603.26790/) (2026)
- [DiffEx: Explaining a Classifier with Diffusion Models to Identify Microscopic Cellular Variations](https://mlsanity.com/paper/2502.09663/) (2025)
- [Revealing Subtle Phenotypes in Small Microscopy Datasets Using Latent Diffusion Models](https://mlsanity.com/paper/2502.09665/) (2025)
- [Morphologically Intelligent Perturbation Prediction with FORM](https://mlsanity.com/paper/2510.21337/) (2025)
- [FreeBridge: Variational Schr"odinger Bridges for Cellular Transition Dynamics](https://mlsanity.com/paper/2606.11286/) (2026)
- [Conditional Neural Optimal Transport for Predicting Cellular Phenotypes from Molecular Structure](https://mlsanity.com/paper/2608.14293/) (2026)
- [Joint Flow Matching Enables Continuous Dose-Conditioned Cell Morphing](https://mlsanity.com/paper/2608.16424/) (2026)
- [PerturbBridge: Direct Phenotypic Supervision for Cellular Perturbation Generation](https://mlsanity.com/paper/2610.17066/) (2026)

## Abstract (arXiv)

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.