Hugging Face's logo

monai-test
/
pathology_nuclick_annotation

monai
medical
Model card Files
xet
Community
katielink commited on
Commit
6ecf3f0
·
1 Parent(s): 8008a76

Update with figure links

Browse files
Files changed (3) hide show
  1. README.md +7 -7
  2. configs/metadata.json +2 -1
  3. docs/README.md +7 -7
README.md CHANGED
@@ -21,7 +21,7 @@ The training dataset is from https://warwick.ac.uk/fac/cross_fac/tia/data/hovern
21
  wget https://warwick.ac.uk/fac/cross_fac/tia/data/hovernet/consep_dataset.zip
22
  unzip -q consep_dataset.zip
23
  ```
24
- ![](images/dataset.jpeg)<br/>
25
 
26
  ## Training configuration
27
  The training was performed with the following:
@@ -58,8 +58,8 @@ As part of pre-processing, the following steps are executed.
58
 
59
  - Crop and Extract each nuclei Image + Label (128x128) based on the centroid given in the dataset.
60
  - Combine classes 3 & 4 into the epithelial class and 5,6 & 7 into the spindle-shaped class.
61
- - Update the label index for the target nuclie based on the class value
62
- - Other cells which are part of the patch are modified to have label idex = 255
63
 
64
  Example dataset.json
65
  ```json
@@ -102,7 +102,7 @@ Example dataset.json
102
  - 0 = Background
103
  - 1 = Nuclei
104
 
105
- ![](images/train_in_out.jpeg)
106
 
107
  ## Scores
108
  This model achieves the following Dice score on the validation data provided as part of the dataset:
@@ -114,13 +114,13 @@ This model achieves the following Dice score on the validation data provided as
114
  ## Training Performance
115
  A graph showing the training Loss and Dice over 50 epochs.
116
 
117
- ![](images/train_loss.jpeg) <br>
118
- ![](images/train_dice.jpeg) <br>
119
 
120
  ## Validation Performance
121
  A graph showing the validation mean Dice over 50 epochs.
122
 
123
- ![](images/val_dice.jpeg) <br>
124
 
125
 
126
  ## commands example
 
21
  wget https://warwick.ac.uk/fac/cross_fac/tia/data/hovernet/consep_dataset.zip
22
  unzip -q consep_dataset.zip
23
  ```
24
+ ![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_dataset.jpeg)<br/>
25
 
26
  ## Training configuration
27
  The training was performed with the following:
 
58
 
59
  - Crop and Extract each nuclei Image + Label (128x128) based on the centroid given in the dataset.
60
  - Combine classes 3 & 4 into the epithelial class and 5,6 & 7 into the spindle-shaped class.
61
+ - Update the label index for the target nuclei based on the class value
62
+ - Other cells which are part of the patch are modified to have label idx = 255
63
 
64
  Example dataset.json
65
  ```json
 
102
  - 0 = Background
103
  - 1 = Nuclei
104
 
105
+ ![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_train_in_out.jpeg)
106
 
107
  ## Scores
108
  This model achieves the following Dice score on the validation data provided as part of the dataset:
 
114
  ## Training Performance
115
  A graph showing the training Loss and Dice over 50 epochs.
116
 
117
+ ![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_train_loss.jpeg) <br>
118
+ ![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_train_dice.jpeg) <br>
119
 
120
  ## Validation Performance
121
  A graph showing the validation mean Dice over 50 epochs.
122
 
123
+ ![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_val_dice.jpeg) <br>
124
 
125
 
126
  ## commands example
configs/metadata.json CHANGED
@@ -1,7 +1,8 @@
1
  {
2
  "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20220324.json",
3
- "version": "0.0.6",
4
  "changelog": {
 
5
  "0.0.6": "adapt to BundleWorkflow interface",
6
  "0.0.5": "add name tag",
7
  "0.0.4": "Fix evaluation",
 
1
  {
2
  "schema": "https://github.com/Project-MONAI/MONAI-extra-test-data/releases/download/0.8.1/meta_schema_20220324.json",
3
+ "version": "0.0.7",
4
  "changelog": {
5
+ "0.0.7": "Update with figure links",
6
  "0.0.6": "adapt to BundleWorkflow interface",
7
  "0.0.5": "add name tag",
8
  "0.0.4": "Fix evaluation",
docs/README.md CHANGED
@@ -14,7 +14,7 @@ The training dataset is from https://warwick.ac.uk/fac/cross_fac/tia/data/hovern
14
  wget https://warwick.ac.uk/fac/cross_fac/tia/data/hovernet/consep_dataset.zip
15
  unzip -q consep_dataset.zip
16
  ```
17
- ![](images/dataset.jpeg)<br/>
18
 
19
  ## Training configuration
20
  The training was performed with the following:
@@ -51,8 +51,8 @@ As part of pre-processing, the following steps are executed.
51
 
52
  - Crop and Extract each nuclei Image + Label (128x128) based on the centroid given in the dataset.
53
  - Combine classes 3 & 4 into the epithelial class and 5,6 & 7 into the spindle-shaped class.
54
- - Update the label index for the target nuclie based on the class value
55
- - Other cells which are part of the patch are modified to have label idex = 255
56
 
57
  Example dataset.json
58
  ```json
@@ -95,7 +95,7 @@ Example dataset.json
95
  - 0 = Background
96
  - 1 = Nuclei
97
 
98
- ![](images/train_in_out.jpeg)
99
 
100
  ## Scores
101
  This model achieves the following Dice score on the validation data provided as part of the dataset:
@@ -107,13 +107,13 @@ This model achieves the following Dice score on the validation data provided as
107
  ## Training Performance
108
  A graph showing the training Loss and Dice over 50 epochs.
109
 
110
- ![](images/train_loss.jpeg) <br>
111
- ![](images/train_dice.jpeg) <br>
112
 
113
  ## Validation Performance
114
  A graph showing the validation mean Dice over 50 epochs.
115
 
116
- ![](images/val_dice.jpeg) <br>
117
 
118
 
119
  ## commands example
 
14
  wget https://warwick.ac.uk/fac/cross_fac/tia/data/hovernet/consep_dataset.zip
15
  unzip -q consep_dataset.zip
16
  ```
17
+ ![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_dataset.jpeg)<br/>
18
 
19
  ## Training configuration
20
  The training was performed with the following:
 
51
 
52
  - Crop and Extract each nuclei Image + Label (128x128) based on the centroid given in the dataset.
53
  - Combine classes 3 & 4 into the epithelial class and 5,6 & 7 into the spindle-shaped class.
54
+ - Update the label index for the target nuclei based on the class value
55
+ - Other cells which are part of the patch are modified to have label idx = 255
56
 
57
  Example dataset.json
58
  ```json
 
95
  - 0 = Background
96
  - 1 = Nuclei
97
 
98
+ ![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_train_in_out.jpeg)
99
 
100
  ## Scores
101
  This model achieves the following Dice score on the validation data provided as part of the dataset:
 
107
  ## Training Performance
108
  A graph showing the training Loss and Dice over 50 epochs.
109
 
110
+ ![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_train_loss.jpeg) <br>
111
+ ![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_train_dice.jpeg) <br>
112
 
113
  ## Validation Performance
114
  A graph showing the validation mean Dice over 50 epochs.
115
 
116
+ ![](https://developer.download.nvidia.com/assets/Clara/Images/monai_pathology_nuclick_annotation_val_dice.jpeg) <br>
117
 
118
 
119
  ## commands example