search

raidionics / Raidionics

Software for automatic segmentation and generation of standardized clinical reports of brain tumors from MRI volumes
https://raidionics.github.io/
BSD 2-Clause "Simplified" License
31 stars 4 forks source link

radionics error #68

Open deem32 opened 6 months ago

deem32 commented 6 months ago

Describe the bug Radionics gives the following error from the first working phase. I tried to install different versions but it did not fix it. I'm a bit newbie, I'd be glad if you could help me.

Computer settings (please complete the following information):

Error messages 12/02/2024 08.55 ; urllib3.connectionpool ; DEBUG ; https://objects.githubusercontent.com:443 "GET /github-production-release-asset-2e65be/601122702/f9880a6e-df1d-493c-9888-d61f9ba21d31?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Credential=AKIAVCODYLSA53PQK4ZA%2F20240212%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20240212T055511Z&X-Amz-Expires=300&X-Amz-Signature=4defd513959de48174e9140a08566089d33aa94a1fcd1a69a80e82f7bcf8ce83&X-Amz-SignedHeaders=host&actor_id=0&key_id=0&repo_id=601122702&response-content-disposition=attachment%3B%20filename%3DRaidionics-MRI_Brain-ONNX-v12.zip&response-content-type=application%2Foctet-stream HTTP/1.1" 200 69134888 12/02/2024 08.55 ; root ; ERROR ; Pipeline process for patient 61161, for task Segmentation_Brain_T0 failed with: multiprocessing.pool.RemoteTraceback: """ Traceback (most recent call last): File "raidionicsrads\Pipelines\SegmentationStep.py", line 71, in setup ValueError: No radiological volume for {'timestamp': 0, 'sequence': 'T1-CE', 'labels': None, 'space': {'timestamp': 0, 'sequence': 'T1-CE'}}. During handling of the above exception, another exception occurred: Traceback (most recent call last): File "multiprocessing\pool.py", line 125, in worker File "multiprocessing\pool.py", line 48, in mapstar File "utils\backend_logic.py", line 187, in run_pipeline_wrapper run_rads(params[0], params[1]) File "raidionicsrads\compute.py", line 30, in run_rads File "raidionicsrads\Pipelines\PipelineStructure.py", line 90, in execute File "raidionicsrads\Pipelines\SegmentationStep.py", line 147, in setup ValueError: [SegmentationStep] setup failed. """ The above exception was the direct cause of the following exception: Traceback (most recent call last): File "utils\backend_logic.py", line 126, in run_pipeline ret = result.get()[0] File "multiprocessing\pool.py", line 771, in get ValueError: [SegmentationStep] setup failed. 12/02/2024 08.55 ; root ; INFO ; Saving patient results in: C:\Users\monster.raidionics\patients\roy_quintana Screenshots If applicable, add screenshots to help explain your problem. image

dbouget commented 6 months ago

Hi @deem32,

It appears that no contrast-enhanced T1-weighted MR scan has been loaded for the current patient, and the Brain segmentation model expects to find one. I assume you tried running a custom action for segmenting the brain on MR scans available at timestamp T0?

You have to make sure that the correct Sequence type is selected for each MR scan you have loaded (in the right-hand side panel showing the Data). If you have multiple MR scans (with different sequence types) loaded for one patient, you might want to try with simply loading a single MR scan (i.e., the one you want to segment) and see if it works there.

If you haven't already, you could have a look and run the simple example to make sure everything is set up properly on your machine. Simply go through the following tutorial.

Let me know if you succeeded or if you have further info to provide in order to narrow down the issue!

deem32 commented 6 months ago

[image: image.png]

David Bouget @.***>, 12 Şub 2024 Pzt, 17:26 tarihinde şunu yazdı:

Hi @deem32 https://github.com/deem32,

It appears that no contrast-enhanced T1-weighted MR scan has been loaded for the current patient, and the Brain segmentation model expects to find one. I assume you tried running a custom action for segmenting the brain on MR scans available at timestamp T0?

You have to make sure that the correct Sequence type is selected for each MR scan you have loaded (in the right-hand side panel showing the Data). If you have multiple MR scans (with different sequence types) loaded for one patient, you might want to try with simply loading a single MR scan (i.e., the one you want to segment) and see if it works there.

If you haven't already, you could have a look and run the simple example to make sure everything is set up properly on your machine. Simply go through the following tutorial https://github.com/raidionics/Raidionics/wiki/Frequently-Asked-Questions-(FAQ)#0-verification-test .

Let me know if you succeeded or if you have further info to provide in order to narrow down the issue!

— Reply to this email directly, view it on GitHub https://github.com/raidionics/Raidionics/issues/68#issuecomment-1938780364, or unsubscribe https://github.com/notifications/unsubscribe-auth/BGC2BKH7A6M4CBRIB75TL73YTIRCZAVCNFSM6AAAAABDEFZI5GVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTSMZYG44DAMZWGQ . You are receiving this because you were mentioned.Message ID: @.***>

deem32 commented 6 months ago

Following your suggestion, I applied the test data and the discount steps exactly. Unfortunately, I was not successful again. I added the error code, I would be happy if you help.

dr deem @.***>, 12 Şub 2024 Pzt, 16:43 tarihinde şunu yazdı:

[image: image.png]

David Bouget @.***>, 12 Şub 2024 Pzt, 17:26 tarihinde şunu yazdı:

Hi @deem32 https://github.com/deem32,

It appears that no contrast-enhanced T1-weighted MR scan has been loaded for the current patient, and the Brain segmentation model expects to find one. I assume you tried running a custom action for segmenting the brain on MR scans available at timestamp T0?

You have to make sure that the correct Sequence type is selected for each MR scan you have loaded (in the right-hand side panel showing the Data). If you have multiple MR scans (with different sequence types) loaded for one patient, you might want to try with simply loading a single MR scan (i.e., the one you want to segment) and see if it works there.

If you haven't already, you could have a look and run the simple example to make sure everything is set up properly on your machine. Simply go through the following tutorial https://github.com/raidionics/Raidionics/wiki/Frequently-Asked-Questions-(FAQ)#0-verification-test .

Let me know if you succeeded or if you have further info to provide in order to narrow down the issue!

— Reply to this email directly, view it on GitHub https://github.com/raidionics/Raidionics/issues/68#issuecomment-1938780364, or unsubscribe https://github.com/notifications/unsubscribe-auth/BGC2BKH7A6M4CBRIB75TL73YTIRCZAVCNFSM6AAAAABDEFZI5GVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMYTSMZYG44DAMZWGQ . You are receiving this because you were mentioned.Message ID: @.***>

dbouget commented 6 months ago

Hi @deem32,

It seems the last upload of your error code did not succeed, the image itself does not show.

The test data provided inside Raidionics should enable running the preoperative segmentation process without any error. At the moment, I am not able to reproduce your error. If you have the possibility, you can also send me the MRI scan you tried using initially, maybe it will help me figuring out the potential problem.

What you can also verify inside the settings (Settings > Preferences > Inputs/Outputs), is that the Use manual MRI sequences box is ticked. The sequence type that you manually associated to each MRI scan that you loaded will then be used. Otherwise, a classification model will be run automatically, but the model hasn't been thoroughly assessed and cannot be highly trusted.