|
--- |
|
license: gpl-3.0 |
|
language: |
|
- en |
|
pipeline_tag: image-segmentation |
|
--- |
|
|
|
# 3DL_NuCount model |
|
|
|
|
|
__Model author__: Fabrice Daian |
|
|
|
|
|
#### Model description |
|
|
|
__3DL_NuCount__ model has been designed by fine tuning a pretrained Stardist3D model [1,2] using a home made dataset [3] in order to assess the number of cells present in a given 3D image stack acquired using an optical microscope. Training and Inference Notebooks are hosted on our Github repo [4]. |
|
|
|
#### Stardist Training parameters |
|
|
|
- patch size: (48,96,96) |
|
- batch size: 32 |
|
- epochs : 100 |
|
- data augmentation : flip/rotation/intensity |
|
- image normalization: normalize channel independantly |
|
- anisotropy: empirical |
|
- rays : 96 |
|
|
|
#### Training dataset parameters |
|
- tile size : (4,63,128,128) |
|
- split : Train 0.8 / Val 0.2 |
|
|
|
#### Inference |
|
- patch size : (784,784,:) |
|
- image size : (2048,2048,:) |
|
- model name : __weights_best_1.h5__ |
|
- config file : __config.json__ |
|
- threshold file : __thresholds.json__ |
|
|
|
|
|
#### References |
|
- [1] Stardist Project: [Github](https://github.com/stardist/stardist) |
|
- [2] Stardist Paper : [ArXiv](https://arxiv.org/abs/1908.03636) |
|
- [3] NuCount Training Dataset : [Zenodo](https://) |
|
- [4] NuCount Github Project: [Github](https://github.com/andysaurin/3DL_NuCount/) |
