DARE2d

# DARE 2DCreation of README file: 27/10/2025 This repository contains the data and pretrained models associated with the paper: Romain Karpinski†, Marc Karnat*, Qazi Saaheelur Rahaman*◊, Mehdi Saadaoui◊, Sham Tlili◊, Jean-François Rupprecht** Aix Marseille Univ, CNRS, LAI (UMR 7333), Turing Centre for Living systems, Marseille, France† LORIA, CNRS, Nancy, France◊ Aix Marseille Univ, CNRS, IBDM (UMR 7288), Turing Centre for Living systems, Marseille, France Contact: [e-mail], [e-mail], [e-mail]; --- ## Description We propose a two-stage deep learning method to characterize cell divisions in time-lapse microscopy sequences. 1. **Stage 1 – Division Detection:** A semantic segmentation network (U-Net) identifies potential division events within image sequences. 2. **Stage 2 – Regression of Division Geometry:** A convolutional regression model estimates the orientation and separation of daughter cells. The method was applied to confocal image sequences of neural tube formation in chicken embryos. Optimization of the networks was performed through systematic hyperparameter exploration. --- ## Repository contents - **DARE2d.zip (490 MB):** Dataset used for training and testing. - **regression_checkpoints.zip (366 MB):** Pretrained weights for the regression network. - **segmentation_checkpoints.zip (1.27 GB):** Pretrained weights for the segmentation (U-Net) network. --- ## Citation If you use this dataset or pretrained models, please cite: Romain Karpinski, Alice Gros, Marc Karnat, Qazi Saaheelur Rahaman, Jules Vanaret, Mehdi Saadaoui, Sham Tlili, and Jean-François Rupprecht, “DARE: Division Axis REcognition from time-lapse image sequences in 2D and 3D.” --- ## License This work is distributed under the **CC BY 4.0 License**. You are free to use, share, and adapt with attribution.