Skip to main content
. 2022 Mar 8;14(6):1370. doi: 10.3390/cancers14061370

Table 2.

Summary of frequently used datasets for model training.

Database Year Material Volume Features
JSRT [87] 1998 CXR 154 Contains 100 CXRs with malignant nodule, 54 CXRs with benigh nodule, and 93 normal CXRs
Shenzhen CXR set [88] 2012 CXR 662 Contains 326 normal CXRs, and 336 CXRs with tuberculosis. Ribs were labeled.
Montgomery CXR set [88] 2014 CXR 138 Contains 80 normal CXRs, and 58 CXRs with tuberculosis. Ribs were labeled.
ChestXray8 [89] 1992–2015 CXR 108,948 Classified into 8 features: atelectasis, cardiomegaly, effusion, infiltration, mass, nodule, normal, pneumonia, and pneumothorax
ChestXray14 [89] 1992–2015 CXR Classified into 14 features: atelectasis, cardiomegaly, consolidation, edema, effusion, emphysema, fibrosis, hernia, infiltration, mass, nodule, pleural thickening, pneumonia, pneumothorax.
PadChest [90] 2009–2017 CXR >160,000 Labeled with 174 different radiographic findings, 19 differential diagnoses and 104 anatomic locations
LIDC [91] 2011 LDCT 1018 Nodules were annotated and labeled with nodule sizes
LUNA16 [23] 2016 LDCT 888 Adapted from LIDC, with additional nodules found during model training.
1186 lung nodules annotated in 888 CT scans
MIMIC-CXR [92] 2011–2016 CXR 377,110 Classified into 14 labels derived from two natural language processing tools.
ChestXpert [93] 2019 CXR 224,316 Labeled with 14 features: no finding, enlarged cardiom, cardiomegaly, lung opacity, lung lesion, edema, consolidation, pneumonia, atelectasis, pneumothorax, pleural effusion, pleural other, fracture, support devices
VinDr-RibCXR [94] 2020 CXR 18,000 Rib suppression images
RadGraph [95] 2021 CXR 500 Inference dataset of MMIC-CXR and reports
REFLACX [96] 2021 CXR 3032 Labeled by 5 radiologists and synchronized sets of eye-tracking data and timestamped report transcriptions

CXR: chest CX-ray set, JSRT: Japanese Society of Radiological Technology, LIDC: Lung Image Database Consortium, LUNA: LUng Nodule Analysis, REFLACX: Reports and Eye-Tracking Data for Localization of Abnormalities in Chest X-rays.