PadChest: A large chest x-ray image dataset with multi-label annotated reports
By Aurelia Bustos, Antonio Pertusa, Jose María Salinas, Maria de la Iglesia-Vayá. 2019
828 citations recorded by the source corpus.
We present a labeled large-scale, high resolution chest x-ray dataset for the automated exploration of medical images along with their associated reports. This dataset includes more than 160,000 images obtained from 67,000 patients that were interpreted and reported by radiologists at San Juan Hospital (Spain) from 2009 to 2017, covering six different position views and additional information on image acquisition and patient demography. The reports were labeled with 174 different radiographic findings, 19 differential diagnoses and 104 anatomic locations organized as a hierarchical taxonomy and mapped onto standard Unified Medical Language System (UMLS) terminology. Of these reports, 27% were manually annotated by trained physicians and the remaining set was labeled using a supervised method based on a recurrent neural network with attention mechanisms. The labels generated were then validated in an independent test set achieving a 0.93 Micro-F1 score. To the best of our knowledge, this is one of the largest public chest x-ray databases suitable for training supervised models concerning radiographs, and the first to contain radiographic reports in Spanish. The PadChest dataset can be downloaded from http://bimcv.cipf.es/bimcv-projects/padchest/.
Subfields: Artificial Intelligence, Radiology, Nuclear Medicine and Imaging, Medical Imaging
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Percy Liang
- Mohit Bansal
- Yoshua Bengio
- Luke S. Zettlemoyer
- Christopher D. Manning
- Jianfeng Gao
- Quoc V. Le
- Hannaneh Hajishirzi
In Radiology, Nuclear Medicine and Imaging
- Pranav Rajpurkar
- Matthew P. Lungren
- B. van Ginneken
- Daniel Rueckert
- Marzyeh Ghassemi
- Ronald M. Summers
- Hayit Greenspan
- Andrew Y. Ng
In Medical Imaging
- Matthew P. Lungren
- Kai Yi
- Anant Madabhushi
- Daniel Rueckert
- Boyang Albert Li
- Han Guo
- Mohamed Elhoseiny
- Jun Chen
Citations in the corpus
- VisualGPT: Data-efficient Adaptation of Pretrained Language Models for Image Captioning (2021, background): “In addition to its scientific value, the task finds practical applications such as facilitating people with impaired vision [7, 11] and generating medical imaging reports under human supervision [47, 10].”
- CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT (2020, background): “Bustos et al. (2019) trained both recurrent and convolutional networks in combination with attention mechanisms on 27,593 physician-labeled radiology reports and apply their labeler to generate labels.”
- MoCo Pretraining Improves Representation and Transferability of Chest X-ray Models (2020, background): “The recent introduction of large datasets (size 100k-500k) of chest X-rays (Irvin et al., 2019; Johnson et al., 2019; Bustos et al., 2020) has driven the development of deep learning models that can detect diseases at a level comparable to radiologists (Rajpurkar et al., 2020).”
- VinDr-CXR: An open dataset of chest X-rays with radiologist’s annotations (2020, background): “These labels were divided into 2 categories: local labels (1-22) and global labels (23-28).”
- A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises (2020, methodology): “This trend has been driven by the availability of large public datasets, such as ChestXRay14 [54], CheXpert [96], MIMIC [97] and PadChest [98], totaling 868k images.”
- Transformers in Medical Imaging: A Survey (2022, neutral): “Image ReportDataset Number Modality View* Length* Language Cases IU X-ray [341] 7,470 X-Ray 2 32.5 Eng. 2,955 MIMIC-CXR [352] 377,110 X-Ray 1 53.2 Eng. 276,778 PadChest [355] 160,868 X-Ray 2 - Es 22,710 CX-CHR [356] 45,598 X-Ray 2 66.9 Zh 40,410 DIARETDB1 [357] 89 CFP 1 - Eng 89 MESSIDOR [261] 1,200”
- Clinically Accurate Chest X-Ray Report Generation (2019, neutral): “Radiologists are trained to simultaneously identify various radiological findings (e.g., diseases), according to the details of the radiograph and the patient’s clinical history, then summarize these findings and their overall impression in reports for clinical commu-2 2015), Chest-XRay8 (Wang et al.,”
- COVIDGR Dataset and COVID-SDNet Methodology for Predicting COVID-19 Based on Chest X-Ray Images (2020, neutral): “• PadChest dataset [16].”
- Making the Most of Text Semantics to Improve Biomedical Vision-Language Processing (2022, background): “Importantly, while many remain private, some paired clinical datasets have been released to the research community including MIMIC-CXR [33], Open-I [14], and PadChest [3].”
- Self-supervised Image-text Pre-training With Mixed Data In Chest X-rays (2021, neutral): “Taking Chest X-rays for an example, we find several hospital-scale (in the scale of hundreds of thousands) datasets that are publicly accessible, e.g ., NIH14-CXR [38], CheXpert [17], MIMIC-CXR [18], PadChest [3], and OpenI-CXR [9].”
- RadGraph: Extracting Clinical Entities and Relations from Radiology Reports (2021, background): “PadChest [15] consists of chest radiographs and reports labeled with 174 different radiographic findings, 19 differential diagnoses, and 104 anatomic locations.”
- Deep learning in generating radiology reports: A survey (2020, neutral): “PadChest [37], however, is labeled with the largest number of annotations including 174 radiology findings, 19 diagnoses, and 104 anatomic locations.”
- CheXclusion: Fairness gaps in deep chest X-ray classifiers (2020, background): “Deeplearning based medical image classifiers are one potential solution, with much work targeting chest X-rays specifically [25, 39, 45, 48], leveraging large-scale publicly available datasets [4, 11, 22, 45], and”
- COVID-19 Image Data Collection: Prospective Predictions Are the Future (2020, background): “…of large-scale public CXR datasets created with ML in mind (e.g. CheXpert [Irvin et al., 2019], Chest-xray8 [Wang et al., 2017], PadChest [Bustos et al., 2019] or MIMIC-CXR [Johnson et al., 2019]), neural networks have even reported being able to achieve performance near radiologist…”
- A Survey of Large Language Models for Healthcare: from Data, Technology, and Applications to Accountability and Ethics (2023, neutral): “6M image-caption pairs Homepage CheXpert [299] Multimodel 224,316 chest radiographs with associated reports Homepage PadChest [300] Multimodel 160,000 images with related text Homepage MIMIC-CXR Multimodel 227,835 imaging studies for 64,588 patients Homepage PMC-15M [239] Multimodel 15 million Figur”
- Can we trust deep learning models diagnosis? The impact of domain shift in chest radiograph classification (2019, neutral): “This shows that clinicians should expect a decrease in the reported performances of machine learning models when applying them in real-world scenarios.”