lindawangg / COVID-Net

COVID-Net Open Source Initiative
Other
1.15k stars 478 forks source link

Issue with Create_COVIDx for COVIDx8A #181

Open Electro1111 opened 3 years ago

Electro1111 commented 3 years ago

these lines seem to be meant to discard certain patients in the sirm dataset from the COVIDx dataset

discard = ['100', '101', '102', '103', '104', '105', '110', '111', '112', '113', '122', '123', '124', '125', '126', '217']

for idx, row in sirm_csv.iterrows(): patientid = row['FILE NAME'] print(patientid) print(patientid[patientid.find('(')+1:patientid.find(')')]) if row['URL'] not in cohen and patientid[patientid.find('(')+1:patientid.find(')')] not in discard:

but this part: patientid[patientid.find('(')+1:patientid.find(')')] not in discard:

doesn't actually do anything because there are no parenthesis in the patient ID's in the latest version of the sirm dataset metadatafile.

furthermore, all the patientIDs in the 'discard' list all appear in the text file for covidx8a as well so they seem to be a part of the training label sets. what is the reason for discarding this images in the first place?