What is 'image_in' for the monailabel logic class?

[hourglassnam]

Hello!
I am trying to run the autosegmentation of MONAILabel using the Slicer Python Interactor with the information provided by this discussion, but I could not figure out what 'image_in' should be.

I read that image_in is the filepath for sending the image to the server as part of session creation and I tried to figuring it out with the log I got.

[2022-10-03 21:52:26,744] [5972] [MainThread] [INFO] (monailabel.endpoints.session:68) - Uncompress: False; Expiry: 0
[2022-10-03 21:52:26,745] [5972] [MainThread] [INFO] (monailabel.endpoints.session:69) - Request Files: [<starlette.datastructures.UploadFile object at 0x0000024220E56850>]
[2022-10-03 21:52:26,772] [5972] [MainThread] [INFO] (monailabel.endpoints.session:83) - 1 => <starlette.datastructures.UploadFile object at 0x0000024220E56850> => C:\Users\njy95\AppData\Local\Temp\tmpp5yetwth\tmpcuhnhxk1.nii.gz
[2022-10-03 21:52:26,774] [5972] [MainThread] [INFO] (monailabel.utils.sessions:154) - ++ Time consumed to add session 3bacba06-431a-11ed-ac57-e0d464948715: 0.0009903907775878906
[2022-10-03 21:52:26,777] [5972] [MainThread] [INFO] (monailabel.endpoints.session:95) - Session ID: 3bacba06-431a-11ed-ac57-e0d464948715; Info: {"name": "3bacba06-431a-11ed-ac57-e0d464948715", "path": "C:\\Users\\njy95\\.cache\\monailabel\\sessions\\3bacba06-431a-11ed-ac57-e0d464948715", "image": "C:\\Users\\njy95\\.cache\\monailabel\\sessions\\3bacba06-431a-11ed-ac57-e0d464948715\\tmpcuhnhxk1.nii.gz", "meta": {}, "create_ts": 1664801546, "last_access_ts": 1664801546, "expiry": 3600}
[2022-10-03 21:52:26,821] [5972] [MainThread] [INFO] (monailabel.endpoints.infer:160) - Infer Request: {'model': 'deepedit_seg', 'image': 'C:\\Users\\njy95\\.cache\\monailabel\\sessions\\3bacba06-431a-11ed-ac57-e0d464948715\\tmpcuhnhxk1.nii.gz', 'result_extension': '.nrrd', 'result_dtype': 'uint8', 'client_id': 'user-xyz', 'session': {'name': '3bacba06-431a-11ed-ac57-e0d464948715', 'path': 'C:\\Users\\njy95\\.cache\\monailabel\\sessions\\3bacba06-431a-11ed-ac57-e0d464948715', 'image': 'C:\\Users\\njy95\\.cache\\monailabel\\sessions\\3bacba06-431a-11ed-ac57-e0d464948715\\tmpcuhnhxk1.nii.gz', 'meta': {}, 'create_ts': 1664801546, 'last_access_ts': 1664801546, 'expiry': 3600}}
[2022-10-03 21:52:26,822] [5972] [MainThread] [INFO] (monailabel.interfaces.tasks.infer:279) - Infer Request (final): {'model': 'deepedit_seg', 'image': 'C:\\Users\\njy95\\.cache\\monailabel\\sessions\\3bacba06-431a-11ed-ac57-e0d464948715\\tmpcuhnhxk1.nii.gz', 'result_extension': '.nrrd', 'result_dtype': 'uint8', 'client_id': 'user-xyz', 'session': {'name': '3bacba06-431a-11ed-ac57-e0d464948715', 'path': 'C:\\Users\\njy95\\.cache\\monailabel\\sessions\\3bacba06-431a-11ed-ac57-e0d464948715', 'image': 'C:\\Users\\njy95\\.cache\\monailabel\\sessions\\3bacba06-431a-11ed-ac57-e0d464948715\\tmpcuhnhxk1.nii.gz', 'meta': {}, 'create_ts': 1664801546, 'last_access_ts': 1664801546, 'expiry': 3600}, 'description': 'A DeepEdit model for volumetric (3D) segmentation over 3D Images', 'save_label': False, 'device': 'cuda'}
[2022-10-03 21:52:26,828] [5972] [MainThread] [INFO] (monailabel.interfaces.utils.transform:63) - PRE - Run Transform(s)[2022-10-03 21:52:26,851] [5972] [MainThread] [INFO] (monailabel.interfaces.utils.transform:64) - PRE - Input Keys: ['model', 'image', 'result_extension', 'result_dtype', 'client_id', 'session', 'description', 'save_label', 'device', 'image_path']
[2022-10-03 21:52:30,180] [5972] [MainThread] [INFO] (monailabel.interfaces.utils.transform:109) - PRE - Transform (LoadImaged): Time: 3.3258; image: (549, 541, 324)(torch.float32)
[2022-10-03 21:52:30,182] [5972] [MainThread] [INFO] (monailabel.interfaces.utils.transform:109) - PRE - Transform (EnsureChannelFirstd): Time: 0.001; image: (1, 549, 541, 324)(torch.float32)
[2022-10-03 21:52:30,381] [5972] [MainThread] [INFO] (monailabel.interfaces.utils.transform:109) - PRE - Transform (Orientationd): Time: 0.1957; image: (1, 549, 541, 324)(torch.float32)
[2022-10-03 21:52:30,649] [5972] [MainThread] [INFO] (monailabel.interfaces.utils.transform:109) - PRE - Transform (ScaleIntensityRanged): Time: 0.2667; image: (1, 549, 541, 324)(torch.float32)
[2022-10-03 21:52:30,864] [5972] [MainThread] [INFO] (monailabel.interfaces.utils.transform:109) - PRE - Transform (Resized): Time: 0.2133; image: (1, 128, 128, 128)(torch.float32)
[2022-10-03 21:52:31,006] [5972] [MainThread] [INFO] (monailabel.interfaces.utils.transform:109) - PRE - Transform (DiscardAddGuidanced): Time: 0.142; image: (5, 128, 128, 128)(torch.float32)
[2022-10-03 21:52:32,097] [5972] [MainThread] [INFO] (monailabel.interfaces.utils.transform:109) - PRE - Transform (EnsureTyped): Time: 1.0914; image: (5, 128, 128, 128)(torch.float32)
[2022-10-03 21:52:32,098] [5972] [MainThread] [INFO] (monailabel.interfaces.tasks.infer:447) - Inferer:: cuda => SimpleInferer => {}
[2022-10-03 21:52:32,100] [5972] [MainThread] [INFO] (monailabel.interfaces.tasks.infer:396) - Infer model path: C:\Users\njy95\MONAILabel\sample-apps\histology_morph\model\deepedit_dynunet.pt
[2022-10-03 21:52:33,581] [5972] [MainThread] [INFO] (monailabel.interfaces.utils.transform:63) - INV - Run Transform(s)[2022-10-03 21:52:33,581] [5972] [MainThread] [INFO] (monailabel.interfaces.utils.transform:64) - INV - Input Keys: ['model', 'image', 'result_extension', 'result_dtype', 'client_id', 'session', 'description', 'save_label', 'device', 'image_path', 'image_meta_dict', 'latencies', 'pred']
[2022-10-03 21:52:33,586] [5972] [MainThread] [INFO] (monailabel.interfaces.utils.transform:109) - INV - Transform (Resized): Time: 0.003; image: (4, 549, 541, 324)(torch.float32); pred: (4, 128, 128, 128)(torch.float32)
[2022-10-03 21:52:33,710] [5972] [MainThread] [INFO] (monailabel.interfaces.utils.transform:109) - INV - Transform (Orientationd): Time: 0.122; image: (4, 549, 541, 324)(torch.float32); pred: (4, 128, 128, 128)(torch.float32)
[2022-10-03 21:52:33,712] [5972] [MainThread] [INFO] (monailabel.interfaces.utils.transform:63) - POST - Run Transform(s)
[2022-10-03 21:52:33,712] [5972] [MainThread] [INFO] (monailabel.interfaces.utils.transform:64) - POST - Input Keys: ['model', 'image', 'result_extension', 'result_dtype', 'client_id', 'session', 'description', 'save_label', 'device', 'image_path', 'image_meta_dict', 'latencies', 'pred']
[2022-10-03 21:52:33,713] [5972] [MainThread] [INFO] (monailabel.interfaces.utils.transform:109) - POST - Transform (EnsureTyped): Time: 0.0; image: (5, 128, 128, 128)(torch.float32); pred: (4, 549, 541, 324)(torch.float32)
[2022-10-03 21:52:33,719] [5972] [MainThread] [INFO] (monailabel.interfaces.utils.transform:109) - POST - Transform (Activationsd): Time: 0.0; image: (5, 128, 128, 128)(torch.float32); pred: (4, 549, 541, 324)(torch.float32)
[2022-10-03 21:52:33,723] [5972] [MainThread] [INFO] (monailabel.interfaces.utils.transform:109) - POST - Transform (AsDiscreted): Time: 0.003; image: (5, 128, 128, 128)(torch.float32); pred: (1, 549, 541, 324)(torch.float32)
[2022-10-03 21:52:33,723] [5972] [MainThread] [INFO] (monailabel.interfaces.utils.transform:109) - POST - Transform (SqueezeDimd): Time: 0.0; image: (5, 128, 128, 128)(torch.float32); pred: (549, 541, 324)(torch.float32)
[2022-10-03 21:52:33,878] [5972] [MainThread] [INFO] (monailabel.interfaces.utils.transform:109) - POST - Transform (ToNumpyd): Time: 0.1557; image: (5, 128, 128, 128)(torch.float32); pred: (549, 541, 324)(float32)
[2022-10-03 21:52:33,879] [5972] [MainThread] [INFO] (monailabel.interfaces.utils.transform:109) - POST - Transform (Restored): Time: 0.0; image: (5, 128, 128, 128)(torch.float32); pred: (549, 541, 324)(float32)
[2022-10-03 21:52:33,882] [5972] [MainThread] [INFO] (monailabel.interfaces.tasks.infer:479) - Writing Result...
[2022-10-03 21:52:33,889] [5972] [MainThread] [INFO] (monailabel.transform.writer:188) - Result ext: .nrrd; write_to_file: True; dtype: uint8
[2022-10-03 21:52:34,536] [5972] [MainThread] [INFO] (monailabel.interfaces.tasks.infer:311) - ++ Latencies => Total: 7.7141; Pre: 5.2736; Inferer: 1.4813; Invert: 0.1300; Post: 0.1727; Write: 0.6535
[2022-10-03 21:52:34,537] [5972] [MainThread] [INFO] (monailabel.interfaces.tasks.infer:335) - Result File: C:\Users\njy95\AppData\Local\Temp\tmpfncd8p_3.nrrd
[2022-10-03 21:52:34,539] [5972] [MainThread] [INFO] (monailabel.interfaces.tasks.infer:336) - Result Json Keys: ['label_names', 'latencies']
[2022-10-03 21:54:40,592] [5972] [Thread-5] [INFO] (monailabel.utils.sessions:68) - Removing expired; current ts: 1664801680
{"name": "304b027f-40c3-11ed-8e6e-e0d464948715", "path": "C:\\Users\\njy95\\.cache\\monailabel\\sessions\\304b027f-40c3-11ed-8e6e-e0d464948715", "image": "C:\\Users\\njy95\\.cache\\monailabel\\sessions\\304b027f-40c3-11ed-8e6e-e0d464948715\\tmp7jt13461.nii.gz", "meta": {}, "create_ts": 1664544259, "last_access_ts": 1664544622, "expiry": 3600}

If I am understanding the log corretly, the image_in seems to be 'C:\Users\njy95\.cache\monailabel\sessions\3bacba06-431a-11ed-ac57-e0d464948715\tmpcuhnhxk1.nii.gz'.
However, this seems like a temporary folder that changes every time.

This is how far I got but I could not figure out the rest.

#MONAILABEL
logic = slicer.util.getModuleLogic('MONAILabel')
# connect to server
server_add = "http://127.0.0.1:8000"
logic.setServer(server_url=server_add)
#check if Monailabel is connected correctly
MONAILabelClient = logic.info()
print(MONAILabelClient)
#Run infer
result_file, params = logic.infer("deepedit_seg", CANNOT FIGURE OUT THE image_in)

What is image_in and how can I make the auto segmentation to run with the python interactor in the Slicer?

Thank you always for all the help!

[diazandr3s]

Hi @hourglassnam,

Thanks for opening this discussion.

I am trying to run the autosegmentation of MONAILabel using the Slicer Python Interactor

MONAI Label is a server with a REST API. To run autosegmentation you could make a REST API call to the server using the image you want to perform inference on.

What's the use case or reason behind making a REST API call via the Slicer Python interpreter?