update evaluation

taigw · taigw · commit 9068c2463ee6 · 2022-12-06T10:42:30.000+08:00
update evaluation
diff --git a/seg_nll/JSRT/README.md b/seg_nll/JSRT/README.md
@@ -128,7 +128,7 @@ pymic_run test config/unet_dast.cfg
 Use `pymic_eval_seg config/evaluation.cfg` for quantitative evaluation of the segmentation results. You need to edit `config/evaluation.cfg` first, for example:
 
 ```bash
-metric = dice
+metric_list = [dice, assd]
 label_list = [255]
 organ_name = lung
 
diff --git a/seg_nll/JSRT/config/evaluation.cfg b/seg_nll/JSRT/config/evaluation.cfg
@@ -1,10 +1,10 @@
 [evaluation]
-metric = dice
+metric_list = [dice, assd]
 label_list = [255]
 organ_name = lung
 
 ground_truth_folder_root  = ../../PyMIC_data/JSRT
-segmentation_folder_root  = result/unet_ce
+segmentation_folder_root  = result/unet_dast
 evaluation_image_pair     = config/data/jsrt_test_gt_seg.csv
 
 
diff --git a/seg_ssl/ACDC/README.md b/seg_ssl/ACDC/README.md
@@ -265,7 +265,7 @@ pymic_ssl test config/unet2d_cps.cfg
 Use `pymic_eval_seg config/evaluation.cfg` for quantitative evaluation of the segmentation results. You need to edit `config/evaluation.cfg` first, for example:
 
 ```bash
-metric = dice
+metric_list = [dice, hd95]
 label_list = [1,2,3]
 organ_name = heart
 ground_truth_folder_root  = ../../PyMIC_data/ACDC/preprocess
diff --git a/seg_ssl/ACDC/config/evaluation.cfg b/seg_ssl/ACDC/config/evaluation.cfg
@@ -1,9 +1,9 @@
 [evaluation]
-metric = dice
+metric_list = [dice, hd95]
 label_list = [1,2,3]
 organ_name = heart
 
 ground_truth_folder_root  = ../../PyMIC_data/ACDC/preprocess
-segmentation_folder_root  = result/unet2d_cps
+segmentation_folder_root  = result/unet2d_urpc
 evaluation_image_pair     = config/data/image_test_gt_seg.csv
 
diff --git a/seg_wsl/ACDC/README.md b/seg_wsl/ACDC/README.md
@@ -216,7 +216,7 @@ pymic_run test config/unet2d_dmpls.cfg
 Use `pymic_eval_seg config/evaluation.cfg` for quantitative evaluation of the segmentation results. You need to edit `config/evaluation.cfg` first, for example:
 
 ```bash
-metric = dice
+metric_list = [dice, hd95]
 label_list = [1,2,3]
 organ_name = heart
 ground_truth_folder_root  = ../../PyMIC_data/ACDC/preprocess
diff --git a/seg_wsl/ACDC/config/evaluation.cfg b/seg_wsl/ACDC/config/evaluation.cfg
@@ -1,9 +1,9 @@
 [evaluation]
-metric = dice
+metric_list = [dice, hd95]
 label_list = [1,2,3]
 organ_name = heart
 
 ground_truth_folder_root  = ../../PyMIC_data/ACDC/preprocess
-segmentation_folder_root  = ./result/unet2d_ms
+segmentation_folder_root  = [./result/unet2d_baseline, ./result/unet2d_em, ./result/unet2d_tv, ./result/unet2d_gcrf, ./result/unet2d_ustm, ./result/unet2d_dmpls]
 evaluation_image_pair     = ./config/data/image_test_gt_seg.csv
 
diff --git a/segmentation/JSRT/README.md b/segmentation/JSRT/README.md
@@ -37,4 +37,4 @@ pymic_run test config/unet.cfg
 pymic_eval_seg config/evaluation.cfg
 ```
 
-The obtained average Dice score by default setting should be close to 97.989%. If setting `ckpt_mode` to 1 during testing, the average Dice would be around 97.997%. You can set `metric = assd` in `config/evaluation.cfg` and run the evaluation command again to get average symmetric surface distance (assd) evaluation results.
+The obtained average Dice score by default setting should be close to 97.989%. If setting `ckpt_mode` to 1 during testing, the average Dice would be around 97.997%. 
diff --git a/segmentation/JSRT/config/evaluation.cfg b/segmentation/JSRT/config/evaluation.cfg
@@ -1,7 +1,7 @@
 [evaluation]
-metric = dice
-label_list = [255]
-organ_name = lung
+metric_list = [dice, assd]
+label_list  = [255]
+organ_name  = lung
 
 ground_truth_folder_root  = ../../PyMIC_data/JSRT
 segmentation_folder_root  = result
diff --git a/segmentation/JSRT2/config/evaluation.cfg b/segmentation/JSRT2/config/evaluation.cfg
@@ -1,5 +1,5 @@
 [evaluation]
-metric = dice
+metric_list = [dice, assd]
 label_list = [255]
 organ_name = lung
 
diff --git a/segmentation/fetal_hc/README.md b/segmentation/fetal_hc/README.md
@@ -36,6 +36,6 @@ pymic_run test config/unet.cfg
 pymic_eval_seg config/evaluation.cfg
 ```
 
-The obtained average Dice score by default setting should be close to 97.07%. You can set `metric = assd` in `config/evaluation.cfg` and run the evaluation command again to get Average Symmetric Surface Distance (ASSD) evaluation results. 
+The obtained average Dice score by default setting should be close to 97.07%. The Average Symmetric Surface Distance (ASSD) is also calculated. 
 
 3. Set `tta_mode = 1` in `config/unet.cfg` to enable test time augmentation, and run the testing and evaluation code again, we find that the average Dice will be increased to around 97.22%.
diff --git a/segmentation/fetal_hc/config/evaluation.cfg b/segmentation/fetal_hc/config/evaluation.cfg
@@ -1,5 +1,5 @@
 [evaluation]
-metric = dice
+metric_list = [dice, assd]
 label_list = [255]
 organ_name = brain
 
diff --git a/segmentation/prostate/README.md b/segmentation/prostate/README.md
@@ -37,5 +37,5 @@ pymic_run test config/unet3d.cfg
 pymic_eval_seg config/evaluation.cfg
 ```
 
-The obtained average Dice score by default setting should be close to 87.92%. You can set `metric = assd` in `config/evaluation.cfg` and run the evaluation command again. You will get Average Symmetric Surface Distance (ASSD) evaluation results. You can try your efforts to improve the performance with different networks or training strategies by changing the configuration file `config/unet3d.cfg`.
+The obtained average Dice score by default setting should be close to 87.92%, and the Average Symmetric Surface Distance (ASSD) is 1.45 mm. You can try your efforts to improve the performance with different networks or training strategies by changing the configuration file `config/unet3d.cfg`.
 
diff --git a/segmentation/prostate/config/evaluation.cfg b/segmentation/prostate/config/evaluation.cfg
@@ -1,5 +1,5 @@
 [evaluation]
-metric = dice
+metric_list = [dice, assd]
 label_list = [1]
 organ_name = prostate
 
