@@ -48,7 +48,8 @@ Use *compute_features.py* to extract different morphological features from the p
```
python ./FLASH/compute_features.py
```
Note: The script outputs a feature table for all structures in a *.csv* file. Each row contains features from a different instance and can thus be used to identify the instances.
Note: The script outputs a feature table for all structures in a *.csv* file. Each row contains features from a different instance and can thus be used to identify the instances.<br>
We applied this whole pipeline to multiple cohorts including AC_B, AC_N, HuBMAP, KPMP, and VALIGA, extracting about 40M features in total. We share those in the file *NGM_DataRepository.zip*.
<br>
<br>
Besides, you can also apply the trained network to our provided exemplary image patches contained in the folder *exemplaryData*. These patches show various pathologies and are listed below including our ground-truth annotation:
...
...
@@ -63,6 +64,10 @@ Besides, you can also apply the trained network to our provided exemplary image