search

ysmiura / ifcc

The code of Improving Factual Completeness and Consistency of Image-to-text Radiology Report Generation
Apache License 2.0
87 stars 19 forks source link

about CheXpert&NegBio #6

Closed newbietuan closed 2 years ago

newbietuan commented 2 years ago

Hello, ysmiura Thanks for opening your source code. It's very nice works. when i running the code，i have a few questions, it's mainly about the data preprocessing. i notice the sections file createed by create_sections_file.py are IMPRESSIONS instead FINDINGS, is that right？ and if i should merge mimic_cxr_number_labeled.csv to one csv file and zip it to mimic-cxr-2.0.0-chexpert.csv.gz? and if the negbio(https://github.com/MIT-LCP/mimic-cxr/tree/master/txt/negbio) in the ifcc code is necessary？

the other question is i have applied the license of mimic_cxr, while i have not seen the mimic-cxr-2.0.0-metadata.csv.gz and mimic-cxr-2.0.0-split.csv.gz, could you please tell me where i can find it?

thank you very much, best wishes

ysmiura commented 2 years ago

Hi, mimic_cxr_sectioned.csv.gz includes both FINDINGS and IMPRESSION. You can extract either section by specifying a corresponding csv column. I am not sure about number-labeled csvs but you can find mimic-cxr-2.0.0-chexpert.csv.gz, mimic-cxr-2.0.0-metadata.csv.gz and mimic-cxr-2.0.0-split.csv.gz in MIMIC-CXR-JPG (and NOT in MIMIC-CXR).

newbietuan commented 2 years ago

Hi, mimic_cxr_sectioned.csv.gz includes both FINDINGS and IMPRESSION. You can extract either section by specifying a corresponding csv column. I am not sure about number-labeled csvs but you can find mimic-cxr-2.0.0-chexpert.csv.gz, mimic-cxr-2.0.0-metadata.csv.gz and mimic-cxr-2.0.0-split.csv.gz in MIMIC-CXR-JPG (and NOT in MIMIC-CXR).

i see it! thank you very much.