multiple sclerosis

[luantunez]

Hello and thank you very much for sharing your work! I am sorry for the trouble, but I am not being able to find out how to run your model for multiple sclerosis outcome prediction on the pretrained pkl you provide. Would it be possible for you to provide some explanation on how to do so, or a reference to some instructions you have already provided and I am not seeing. From the input required, up to the inference process and the expected output. I thank you enormously in advance. Lucia

[noxtoby]

Quick answer here until someone else has time to followup:

• later in this tutorial notebook you can find patient staging and subtyping, which is how you "score" your patients (using the same input features as in the pickled/pre-trained model)
• then you could perform an association analysis of outcomes as a function of subtype and/or stage

[luantunez]

Thank you very much for your help and quick response! I have read the pkl file and I am getting the following content:

The problem is that I do not fully understand them and wouldn´t know how to set them for inference of MS on a new MRI volume. Could you guide me on that please?

{'ml_sequence': array([[[ 7.],
        [11.],
        [ 6.],
        [10.],
        [ 9.],
        [ 3.],
        [20.],
        [ 8.],
        [22.],
        [19.],
        [21.],
        [23.],
        [24.],
        [33.],
        [ 4.],
        [35.],
        [12.],
        [34.],
        [32.],
        [ 2.],
        [36.],
        [16.],
        [17.],
        [37.],
        [ 1.],
        [15.],
        [14.],
        [ 0.],
        [13.],
        [25.],
        [38.],
        [28.],
        [30.],
        [26.],
        [27.],
        [29.],
        [ 5.],
        [18.],
        [31.]],

       [[ 3.],
        [ 4.],
        [ 0.],
        [12.],
        [25.],
        [38.],
        [13.],
        [ 5.],
        [ 1.],
        [ 2.],
        [17.],
        [15.],
        [16.],
        [14.],
        [11.],
        [18.],
        [ 7.],
        [20.],
        [10.],
        [24.],
        [ 6.],
        [ 9.],
        [ 8.],
        [22.],
        [21.],
        [23.],
        [19.],
        [26.],
        [28.],
        [30.],
        [27.],
        [31.],
        [29.],
        [33.],
        [35.],
        [34.],
        [36.],
        [37.],
        [32.]],

       [[ 3.],
        [ 4.],
        [ 1.],
        [ 2.],
        [ 0.],
        [ 5.],
        [12.],
        [11.],
        [17.],
        [ 7.],
        [16.],
        [10.],
        [20.],
        [ 9.],
        [ 6.],
        [15.],
        [ 8.],
        [22.],
        [19.],
        [21.],
        [23.],
        [24.],
        [14.],
        [25.],
        [38.],
        [13.],
        [33.],
        [35.],
        [34.],
        [32.],
        [36.],
        [37.],
        [30.],
        [28.],
        [18.],
        [31.],
        [26.],
        [29.],
        [27.]]]), 'ml_f': array([[0.34185156],
       [0.25388692],
       [0.40426152]]), 'ml_likelihood': array([-137458.80978643]), 'samples_sequence': array([[[ 7.,  7.,  7., ...,  7.,  7.,  7.],
        [11., 11., 11., ..., 11., 11., 11.],
        [ 6.,  6.,  6., ...,  6.,  6.,  6.],
        ...,
        [ 5.,  5.,  5., ..., 18., 18., 18.],
        [18., 18., 18., ..., 31., 31., 31.],
        [31., 31., 31., ..., 30., 30., 30.]],

       [[ 3.,  3.,  3., ...,  3.,  3.,  3.],
        [ 4.,  4.,  4., ...,  4.,  4.,  4.],
        [ 0.,  0.,  0., ...,  0.,  0.,  0.],
        ...,
        [36., 36., 36., ..., 36., 36., 36.],
        [37., 37., 37., ..., 37., 37., 37.],
        [32., 32., 32., ..., 32., 32., 32.]],

       [[ 3.,  3.,  3., ...,  3.,  3.,  3.],
        [ 4.,  4.,  4., ...,  4.,  4.,  4.],
        [ 1.,  1.,  1., ...,  1.,  1.,  1.],
        ...,
        [26., 26., 26., ..., 31., 31., 31.],
        [29., 29., 29., ..., 29., 29., 29.],
        [27., 27., 27., ..., 27., 27., 27.]]]), 'samples_f': array([[0.34028093, 0.3422053 , 0.3422053 , ..., 0.34814804, 0.34880428,
        0.35054254],
       [0.25384016, 0.25389745, 0.25389745, ..., 0.2540744 , 0.25409394,
        0.2541457 ],
       [0.40587892, 0.40389725, 0.40389725, ..., 0.39777756, 0.39710178,
        0.39531176]]), 'samples_likelihood': array([[-137460.9034704 ],
       [-137460.95568907],
       [-137460.95568907],
       ...,
       [-137468.27126633],
       [-137468.40862701],
       [-137468.82692007]])}

[noxtoby]

Did you look at the tutorial notebook?