chenwwweixiang / diagnosis_covid19 Goto Github PK

Could not get good results by running the testengine.py script with the trained model from https://cloud.tsinghua.edu.cn/f/545d5552e3254d8996e9/ on the MosMed data.
Are there additional preprocessing steps required?

Hello
In data/dataset.py line 6:
from radiomics import featureextractor
where is featureextractor?

In the file data/get_train_jpgs.py, why did you only use one every 10 slices in the CT scans for training but not all slices?

    for idx, i in enumerate(range(0,V.shape[0],10)):
        if not 'healthy' in set_name and False:
            if not i in sums2:
                continue
        data=V[i,:,:]
        data[data>500]=500
        data[data<-1200]=-1200#-1200~500
        data=data*255.0/1700
        data=data-data.min()

        data=np.stack([data,M[i,:,:]*data,M[i,:,:]*255],-1)#mask one channel
        data = data.astype(np.uint8)

        cv2.imwrite(os.path.join(output_path_slices,'nor_'+set_name+'_'
                                 +name.split(',')[0].split('/')[-1].split('.nii')[0]
                                 +'_'+str(int(i/(V.shape[0])*100))+'.jpg'),data)

Hello
thanks for sharing your code.
I have a question.
for segmentation part in predict.py
where is lung_checkpoint.pth?

Hello.
for testing model in main.py and testengine.py:
where is 'pretrainedmodelpath': 'weights/weak_super.pt' ?

Thank you for sharing your nice work!
I would like to test your weak_super.pt #5 model on a dataset containing ct scans of Covid and CAP patients.
What should be the settings in the test.toml for this classification task? mod=?