You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+11-10Lines changed: 11 additions & 10 deletions
Original file line number
Diff line number
Diff line change
@@ -22,7 +22,7 @@
22
22
23
23
## Introduction
24
24
25
-
Contains multi-task encoder-decoder architectures (U-Net-like) along with dedicated post-processing methods for segmenting cell/nuclei instances. As the name suggests, this library is heavily inspired by [segmentation_models.pytorch](https://github.com/qubvel/segmentation_models.pytorch) library for semantic segmentation.
25
+
Contains multi-task encoder-decoder architectures along with dedicated post-processing methods for segmenting cell/nuclei instances. As the name suggests, this library is heavily inspired by [segmentation_models.pytorch](https://github.com/qubvel/segmentation_models.pytorch) library for semantic segmentation.
-[Training Stardist with Pannuke](https://github.com/okunator/cellseg_models.pytorch/blob/main/examples/pannuke_nuclei_segmentation_stardist.ipynb). Uses in-built training utilities and Pytorch-Lightning
75
+
-[Training Stardist with Pannuke](https://github.com/okunator/cellseg_models.pytorch/blob/main/examples/pannuke_nuclei_segmentation_stardist.ipynb). Train the Stardist model with constant sized Pannuke patches.
76
+
-[Training Cellpose with Lizard](https://github.com/okunator/cellseg_models.pytorch/blob/main/examples/lizard_nuclei_segmentation_cellpose.ipynb). Train the Cellpose model with Lizard dataset that is composed of varying sized images.
75
77
76
78
## Code Examples
77
79
@@ -207,11 +209,9 @@ model(x)
207
209
# }
208
210
```
209
211
210
-
This model would give 5 outputs with names that should describe their prediction task. The names are arbitrary and there are no restrictions for them, however, during training and post-processing, these names need to match to the input names of the training or post-processing pipelines. Here, for example during training, the `"cellpose"`-head would predict x- and -y flow gradients, given that during training there would be x- and- y- gradient ground truth inputs with the same name. Similarly, `"type"`-head would predict semantic cell type masks, `"dist"`-head would predict a distance transform from the center of cell/nuclei instances, `"contour"`-head would predict cell/nuclei contours, and `"sem"`-head would predict semantic area segmentation masks. Check out the training notebooks in the `examples`-folder for more detailed info.
211
-
212
212
### Function API
213
213
214
-
With the function API, you can build models with low effort by calling the below listed functions. Under the hood, the function API simply calls the above classes with pre-defined decoder- and head names. The training- and post-processing tools of this library are built around these names, thus, it is recommended to use the function API, although, it is a bit more rigid than the class API. Basically, the function API only lacks the ability to define the output-tasks of the model, but allows for all the rest as the class API.
214
+
With the function API, you can build models with low effort by calling the below listed functions. Under the hood, the function API simply calls the above classes with pre-defined decoder and head names. The training and post-processing tools of this library are built around these names, thus, it is recommended to use the function API, although, it is a bit more rigid than the class API. Basically, the function API only lacks the ability to define the output-tasks of the model, but allows for all the rest as the class API.
@@ -235,6 +235,7 @@ With the function API, you can build models with low effort by calling the below
235
235
-[4] Uwe Schmidt, Martin Weigert, Coleman Broaddus, & Gene Myers (2018). Cell Detection with Star-Convex Polygons. In Medical Image Computing and Computer Assisted Intervention - MICCAI 2018 - 21st International Conference, Granada, Spain, September 16-20, 2018, Proceedings, Part II (pp. 265–273).
236
236
-[5] Gamper, J., Koohbanani, N., Benet, K., Khuram, A., & Rajpoot, N. (2019) PanNuke: an open pan-cancer histology dataset for nuclei instance segmentation and classification. In European Congress on Digital Pathology (pp. 11-19).
237
237
-[6] Gamper, J., Koohbanani, N., Graham, S., Jahanifar, M., Khurram, S., Azam, A.,Hewitt, K., & Rajpoot, N. (2020). PanNuke Dataset Extension, Insights and Baselines. arXiv preprint arXiv:2003.10778.
238
+
-[7] Graham, S., Jahanifar, M., Azam, A., Nimir, M., Tsang, Y.W., Dodd, K., Hero, E., Sahota, H., Tank, A., Benes, K., & others (2021). Lizard: A Large-Scale Dataset for Colonic Nuclear Instance Segmentation and Classification. In Proceedings of the IEEE/CVF International Conference on Computer Vision (pp. 684-693).
0 commit comments