K-Diag

The official code for "K-Diag: Knowledge-enhanced Disease Diagnosis in Radiographic Imaging"

Paper Web

Arxiv Version

Guidance:

• Please Check src/models/xmbert/README.md to download our pre-trained knowledge encoder.

• In Whole_dataset dir we provide all split we used for experiments.

• You can check src/results/README.md to download our model trained on CXR-Mix. For more model versions you may reproduce our training procedure on corresponding datasets.

Datasets:

The download link of each dataset we used in paper is listed below:

Dataset Name	Link	Access
VinDr-Mammo	https://www.physionet.org/content/vindr-mammo/1.0.0/	Credentialed Access
VinDr-SpineXR	https://www.physionet.org/content/vindr-spinexr/1.0.0/	Credentialed Access
VinDr-PCXR	https://physionet.org/content/vindr-pcxr/1.0.0/	Credentialed Access
MIMIC-CXR	https://physionet.org/content/mimic-cxr/2.0.0	Credentialed Access
VinDr-CXR	https://physionet.org/content/vindr-cxr/1.0.0/	Credentialed Access
NIH ChestXray14	https://nihcc.app.box.com/v/ChestXray-NIHCC/folder/36938765345	Open Access
CheXpert	https://aimi.stanford.edu/chexpert-chest-x-rays	Open Access
Covid-CXR2	https://www.kaggle.com/datasets/andyczhao/covidx-cxr2	Open Access
NLM-TB	Montgomery, ChinaSet	Open Access
Object-CXR	https://web.archive.org/web/20201127235812/https://jfhealthcare.github.io/object-CXR/	Open Access
OpenI	https://www.kaggle.com/datasets/raddar/chest-xrays-indiana-university	Open Access
RSNA	https://www.rsna.org/education/ai-resources-and-training/ai-image-challenge/rsna-pneumonia-detection-challenge-2018	Open Access
SIIM-ACR	https://www.kaggle.com/datasets/jesperdramsch/siim-acr-pneumothorax-segmentation-data	Open Access

Contact

If you have any question, please feel free to contact wtzxxxwcy02@sjtu.edu.cn.