diff --git a/prediction/src/tests/test_classification.py b/prediction/src/tests/test_classification.py
index dbe9c11..3ba3bdb 100644
--- a/prediction/src/tests/test_classification.py
+++ b/prediction/src/tests/test_classification.py
@@ -5,7 +5,13 @@ def test_classify_predict_load(metaimage_path, model_path):
     assert not trained_model.predict(metaimage_path, [], model_path)
 
 
-def test_classify_predict_inference(metaimage_path, luna_nodule, model_path):
+def test_classify_dicom(dicom_paths, nodule_locations, model_path):
+    predicted = trained_model.predict(dicom_paths, nodule_locations, model_path)
+    assert predicted
+    assert 0 <= predicted[0]['p_concerning'] <= 1
+
+
+def test_classify_luna(metaimage_path, luna_nodule, model_path):
     predicted = trained_model.predict(metaimage_path, [luna_nodule], model_path)
     assert predicted
     assert 0 <= predicted[0]['p_concerning'] <= 1
diff --git a/prediction/src/tests/test_identification.py b/prediction/src/tests/test_identification.py
index 914fe2b..5098701 100644
--- a/prediction/src/tests/test_identification.py
+++ b/prediction/src/tests/test_identification.py
@@ -5,7 +5,7 @@ from ..algorithms.identify import trained_model
 
 
 @skip_if_slow
-def test_identify_nodules_001(dicom_path, nodule_001):
+def test_identify_dicom_001(dicom_path, nodule_001):
     predicted = trained_model.predict(dicom_path)
     first = predicted[0]
     dist = np.sqrt(np.sum([(first[s] - nodule_001[s]) ** 2 for s in ["x", "y", "z"]]))
@@ -13,8 +13,16 @@ def test_identify_nodules_001(dicom_path, nodule_001):
 
 
 @skip_if_slow
-def test_identify_nodules_003(dicom_path_003, nodule_003):
+def test_identify_dicom_003(dicom_path_003, nodule_003):
     predicted = trained_model.predict(dicom_path_003)
     first = predicted[0]
     dist = np.sqrt(np.sum([(first[s] - nodule_003[s]) ** 2 for s in ["x", "y", "z"]]))
     assert (dist < 10)
+
+
+@skip_if_slow
+def test_identify_luna(metaimage_path, luna_nodule):
+    predicted = trained_model.predict(metaimage_path)
+    first = predicted[0]
+    dist = np.sqrt(np.sum([(first[s] - luna_nodule[s]) ** 2 for s in ["x", "y", "z"]]))
+    assert (dist < 10)
diff --git a/prediction/src/tests/test_segmentation.py b/prediction/src/tests/test_segmentation.py
index 1ecf7eb..0896bdc 100644
--- a/prediction/src/tests/test_segmentation.py
+++ b/prediction/src/tests/test_segmentation.py
@@ -22,13 +22,20 @@ def test_segment_predict_load(dicom_path):
     assert predicted['volumes'] == []
 
 
-def test_segment_predict_inference(dicom_path, nodule_locations):
+def test_segment_dicom(dicom_path, nodule_locations):
     predicted = predict(dicom_path, nodule_locations)
     assert isinstance(predicted['binary_mask_path'], str)
     assert predicted['volumes']
     assert predicted['volumes'][0] > 0
 
 
+def test_segment_luna(metaimage_path, luna_nodule):
+    predicted = predict(metaimage_path, [luna_nodule])
+    assert isinstance(predicted['binary_mask_path'], str)
+    assert predicted['volumes']
+    assert predicted['volumes'][0] > 0
+
+
 @skip_if_slow
 def test_lung_segmentation(dicom_paths):
     """Test whether the annotations of the LIDC images are inside the segmented lung masks.