hust-eic-ai-lab / ucadi Goto Github PK

Basically Summarise the Reported Sensitivity, Dataset in CT-based COVID-19 Diagnosis

Does it require to build the matrix_op?

https://github.com/HUST-EIC-AI-LAB/COVID-19-Fedrated-Learning-Framework/blob/d3714e76b3bc408fa79ed9e89372414701953b61/server/LWE_based_PHE/matrix_op/matrix_op.py#L2

Or I think you are using an alternative solution as here:
https://github.com/HUST-EIC-AI-LAB/COVID-19-Fedrated-Learning-Framework/blob/d3714e76b3bc408fa79ed9e89372414701953b61/server/LWE_based_PHE/cuda_test.py#L7-L12

I notice that the raw data collected in UK has something like this:

Storage type.....: 1.2.840.10008.5.1.4.1.1.2

Patient's name...: W-YL-1, 
Patient id.......: W-YL-1
Modality.........: CT
Study Date.......: 20200120
Image size.......: 512 x 512, 524288 bytes
Pixel spacing....: [0.781, 0.781]
Slice location...: -221.5

Storage type.....: 1.2.840.10008.5.1.4.1.1.2

Patient's name...: W-YL-1, 
Patient id.......: W-YL-1
Modality.........: CT
Study Date.......: 20200120
Image size.......: 512 x 512, 524288 bytes
Pixel spacing....: [0.781, 0.781]
Slice location...: -88.5

Slices at different area has quite different brightness/magnitude, Does it matter?

• why we need no bias decay in the model update
  https://github.com/HUST-EIC-AI-LAB/COVID-19-Fedrated-Learning-Framework/blob/d8ca89a7f328bf4ec5353785385f21298f232aea/client/client1_main.py#L56-L60

• what if the model is not received from the server successfully
  https://github.com/HUST-EIC-AI-LAB/COVID-19-Fedrated-Learning-Framework/blob/d8ca89a7f328bf4ec5353785385f21298f232aea/client/client1_main.py#L84-L85
  https://github.com/HUST-EIC-AI-LAB/COVID-19-Fedrated-Learning-Framework/blob/d8ca89a7f328bf4ec5353785385f21298f232aea/client/client1_main.py#L90

• Why we need this?
  https://github.com/HUST-EIC-AI-LAB/COVID-19-Fedrated-Learning-Framework/blob/d8ca89a7f328bf4ec5353785385f21298f232aea/client/client1_main.py#L144-L150

• Why we need this? since there are warmup scheduler already...
  https://github.com/HUST-EIC-AI-LAB/COVID-19-Fedrated-Learning-Framework/blob/d8ca89a7f328bf4ec5353785385f21298f232aea/client/train.py#L34-L37

• Will the scheduler work? (Checking on myself...) -> Checked, it is the same (memory location)
  https://github.com/HUST-EIC-AI-LAB/COVID-19-Fedrated-Learning-Framework/blob/d8ca89a7f328bf4ec5353785385f21298f232aea/client/train.py#L87
  https://github.com/HUST-EIC-AI-LAB/COVID-19-Fedrated-Learning-Framework/blob/d8ca89a7f328bf4ec5353785385f21298f232aea/client/client1_main.py#L156-L159

• Why break?
  https://github.com/HUST-EIC-AI-LAB/COVID-19-Fedrated-Learning-Framework/blob/d8ca89a7f328bf4ec5353785385f21298f232aea/client/train.py#L76

Will do in next PR, along with test scripts and improvements on the network communication.

I noticed that A lot of places in Client1_main.py and Client2_main.py are implemented differently, i.e. the first 70 lines are pretty much similar(except register the client), while the remaining parts are quite different. So I am wondering should I modify Client2_main.py w.r.t. Client1_main.py, right?

Or they are designed to be with different settings.

as the title.