News | Artificial Intelligence | October 10, 2017

NIH Clinical Center Releases 100,000-Plus Chest X-ray Datasets to Scientific Community

Compiled from scans of more than 30,000 patients, datasets are intended to help train artificial intelligence algorithms to aid radiologists in diagnosis

NIH Clinical Center Releases 100,000-Plus Chest X-ray Datasets to Scientific Community

October 10, 2017 — The National Institutes of Health (NIH) Clinical Center recently released over 100,000 anonymized chest X-ray images and their corresponding data to the scientific community. The release will allow researchers across the country and around the world to freely access the datasets and increase their ability to teach computers how to detect and diagnose disease. Ultimately, this artificial intelligence mechanism can lead to clinicians making better diagnostic decisions for patients. 

NIH compiled the dataset of scans from more than 30,000 patients, including many with advanced lung disease. Patients at the NIH Clinical Center, the nation’s largest hospital devoted entirely to clinical research, are partners in research and voluntarily enroll to participate in clinical trials. With patient privacy being paramount, the dataset was rigorously screened to remove all personally identifiable information before release.

Reading and diagnosing chest X-ray images may be a relatively simple task for radiologists but, in fact, it is a complex reasoning problem that often requires careful observation and knowledge of anatomical principles, physiology and pathology. Such factors increase the difficulty of developing a consistent and automated technique for reading chest X-ray images while simultaneously considering all common thoracic diseases.

By using this free dataset, the hope is that academic and research institutions across the country will be able to teach a computer to read and process extremely large amounts of scans, to confirm the results radiologists have found and potentially identify other findings that may have been overlooked.

In addition, this advanced computer technology may also be able to:

  • Help identify slow changes occurring over the course of multiple chest X-rays that might otherwise be overlooked;
  • Benefit patients in developing countries that do not have access to radiologists to read their chest X-rays; and 
  • Create a virtual radiology resident that can later be taught to read more complex images like computed tomography (CT) and magnetic resonance imaging (MRI) in the future.

The NIH research hospital anticipates adding a large dataset of CT scans to be made available as well in the coming months.

For more information: www.clinicalcenter.nih.gov

 

Related Content on Artificial Intelligence in Radiology

Artificial Intelligence Could Learn From the Medical Imaging Goldmine of the NHS Archives

VIDEO: Machine Learning and the Future of Radiology

How Artificial Intelligence Will Change Medical Imaging

Must Radiologists Be Prepared To Delegate ... To Smart Machines?

Related Content

The study finds it's possible to use commercial facial recognition software to identify people from brain MRI that includes imagery of the face
News | Magnetic Resonance Imaging (MRI) | November 15, 2019
November 15, 2019 — Though identifying data typically are removed from medical image files before they are shared for
62-year-old woman with pure ground-glass nodules (GGN). PET/CT fusion image shows pure GGN with tumor maximum standardized uptake value of 2.8 (circle).

62-year-old woman with pure ground-glass nodules (GGN). PET/CT fusion image shows pure GGN with tumor maximum standardized uptake value of 2.8 (circle).

News | PET-CT | November 15, 2019
November 15, 2019 — According to an article published ahead-of-print in the...
EchoGo uses artificial intelligence (AI) to calculate cardiac ultrasound left ventricular ejection fraction (EF), the most frequently used measurement of heart function, left ventricular volumes (LV) and, for the first time for an AI application, automated cardiac strain.

EchoGo uses artificial intelligence (AI) to calculate cardiac ultrasound left ventricular ejection fraction (EF), the most frequently used measurement of heart function, left ventricular volumes (LV) and, for the first time for an AI application, automated cardiac strain.

News | Cardiovascular Ultrasound | November 14, 2019
November 14, 2019 — Ultromics has received 510(k) clearance from the U.S.
 MaxQ AI
News | Artificial Intelligence | November 13, 2019
November 13, 2019 – MaxQ AI announced a new partnership agreement with...
The ALS produces various wavelengths of bright light that can be used to explore the microscopic chemistry, structure, and other properties of samples

Two researchers from Cairo University in Egypt brought 32 bone samples and two soil samples to study using X-ray and infrared light-based techniques at Berkeley Lab's Advanced Light Source (ALS). The ALS produces various wavelengths of bright light that can be used to explore the microscopic chemistry, structure, and other properties of samples. Image courtesy of Marilyn Sargent/Berkeley Lab

News | Radiology Imaging | November 13, 2019
November 13, 2019 — Experiments at the Department of Energy's Lawrence Berkeley National Laboratory (...
 Paxera Ultima 360
News | Enterprise Imaging | November 12, 2019
November 12, 2019 — Medical Imaging developer PaxeraHealth will showcase the
 Lunit RSNA
News | Artificial Intelligence | November 12, 2019
November 12, 2019 — Lunit, a leading medical AI software company devoted to provi
 Laurel Bridge Machine Learning workflow
News | Artificial Intelligence | November 08, 2019
November 8, 2019 — Laurel Bridge Software announces the new Laurel Bridge