fix: adapt the filenames of the predictions in pred_masks as per targ…

…et_suffix (#1173)

Fixes #1135

Currently, `--test` command doesn't support multiple annotations for 
the ground truth. So, adding a test to document this behaviour.

Co-authored-by: mariehbourget <54086142+mariehbourget@users.noreply.github.com>

ivadomed/main.py

@@ -98,7 +98,7 @@ def check_multiple_raters(is_train, loader_params):
         if not is_train:
             logger.error(
                 "Please provide only one annotation per class in 'target_suffix' when not training a model.\n")
-            exit()
+            sys.exit()
 
 
 def film_normalize_data(context, model_params, ds_train, ds_valid, path_output):

ivadomed/testing.py

@@ -223,7 +223,7 @@ def run_inference(test_loader, model, model_params, testing_params, ofolder, cud
                     # save the completely processed file as a NifTI file
                     if ofolder:
                         fname_pred = str(Path(ofolder, Path(fname_ref).name))
-                        fname_pred = fname_pred.rsplit("_", 1)[0] + '_pred.nii.gz'
+                        fname_pred = fname_pred.split(testing_params['target_suffix'][0])[0] + '_pred.nii.gz'
                         # If Uncertainty running, then we save each simulation result
                         if testing_params['uncertainty']['applied']:
                             fname_pred = fname_pred.split('.nii.gz')[0] + '_' + str(i_monte_carlo).zfill(2) + '.nii.gz'

testing/unit_tests/test_main.py

@@ -0,0 +1,14 @@
+import pytest
+
+from ivadomed.main import check_multiple_raters
+
+@pytest.mark.parametrize(
+    'is_train, loader_params', [
+       (False, {"target_suffix":
+           [["_seg-axon-manual1", "_seg-axon-manual2"],
+            ["_seg-myelin-manual1", "_seg-myelin-manual2"]]
+           }) 
+])
+def test_check_multiple_raters(is_train, loader_params):
+    with pytest.raises(SystemExit):
+        check_multiple_raters(is_train, loader_params)

testing/unit_tests/test_testing.py

@@ -211,5 +211,100 @@ def test_inference_2d_microscopy(download_data_testing_test_files, transforms_di
     assert len([x for x in __output_dir__.iterdir() if x.name.endswith(".png")]) == 2*len(test_lst)
 
 
+@pytest.mark.parametrize('transforms_dict', [{
+        "CenterCrop": {
+                "size": [128, 128]
+            },
+        "NormalizeInstance": {"applied_to": ["im"]}
+    }])
+@pytest.mark.parametrize('test_lst',
+    [['sub-rat3_ses-01_sample-data9_SEM.png', 'sub-rat3_ses-02_sample-data10_SEM.png']])
+@pytest.mark.parametrize('target_lst', [["_seg-axon_manual", "_seg-myelin_manual"]])
+@pytest.mark.parametrize('roi_params', [{"suffix": None, "slice_filter_roi": None}])
+@pytest.mark.parametrize('testing_params', [{
+    "binarize_maxpooling": {},
+    "uncertainty": {
+        "applied": False,
+        "epistemic": False,
+        "aleatoric": False,
+        "n_it": 0
+    }}])
+def test_inference_target_suffix(download_data_testing_test_files, transforms_dict, test_lst, target_lst, roi_params,
+        testing_params):
+    """
+    This test checks if the filename(s) of the prediction(s) saved as NifTI file(s) in the pred_masks
+    dir conform to the target_suffix or not. Thus, independent of underscore(s) in the target_suffix. As a result,
+    _seg-axon-manual or _seg-axon_manual should yield the same filename(s).
+    (c.f: https://github.com/ivadomed/ivadomed/issues/1135)
+    """
+    cuda_available, device = imed_utils.define_device(GPU_ID)
+
+    model_params = {"name": "Unet", "is_2d": True, "out_channel": 3}
+    loader_params = {
+        "transforms_params": transforms_dict,
+        "data_list": test_lst,
+        "dataset_type": "testing",
+        "requires_undo": True,
+        "contrast_params": {"contrast_lst": ['SEM'], "balance": {}},
+        "path_data": [str(Path(__data_testing_dir__, "microscopy_png"))],
+        "bids_config": f"{path_repo_root}/ivadomed/config/config_bids.json",
+        "target_suffix": target_lst,
+        "extensions": [".png"],
+        "roi_params": roi_params,
+        "slice_filter_params": {"filter_empty_mask": False, "filter_empty_input": True},
+        "patch_filter_params": {"filter_empty_mask": False, "filter_empty_input": False},
+        "slice_axis": SLICE_AXIS,
+        "multichannel": False
+    }
+    loader_params.update({"model_params": model_params})
+
+    # restructuring the dataset 
+    gt_path = f'{loader_params["path_data"][0]}/derivatives/labels/'
+    for file_path in Path(gt_path).rglob('*.png'):
+      src_filename = file_path.resolve()
+      dst_filename = '_'.join(str(src_filename).rsplit('-', 1))
+      src_filename.rename(Path(dst_filename))
+
+    bids_df = BidsDataframe(loader_params, __tmp_dir__, derivatives=True)
+
+    ds_test = imed_loader.load_dataset(bids_df, **loader_params)
+    test_loader = DataLoader(ds_test, batch_size=BATCH_SIZE,
+                             shuffle=False, pin_memory=True,
+                             collate_fn=imed_loader_utils.imed_collate,
+                             num_workers=0)
+
+    # Undo transform
+    val_undo_transform = imed_transforms.UndoCompose(imed_transforms.Compose(transforms_dict))
+
+    # Update testing_params
+    testing_params.update({
+        "slice_axis": loader_params["slice_axis"],
+        "target_suffix": loader_params["target_suffix"],
+        "undo_transforms": val_undo_transform
+    })
+
+    # Model
+    model = imed_models.Unet(out_channel=model_params['out_channel'])
+
+    if cuda_available:
+        model.cuda()
+    model.eval()
+
+    if not __output_dir__.is_dir():
+        __output_dir__.mkdir(parents=True, exist_ok=True)
+
+    preds_npy, gt_npy = imed_testing.run_inference(test_loader=test_loader,
+                                                   model=model,
+                                                   model_params=model_params,
+                                                   testing_params=testing_params,
+                                                   ofolder=str(__output_dir__),
+                                                   cuda_available=cuda_available)
+
+    for x in __output_dir__.iterdir():
+      if x.name.endswith('_pred.nii.gz'):
+        assert x.name.rsplit('_', 1)[0].endswith(loader_params['contrast_params']['contrast_lst'][-1]), ( 
+            'Incompatible filename(s) of the prediction(s) saved as NifTI file(s)!'
+        )
+
 def teardown_function():
     remove_tmp_dir()