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

Arterys Receives First FDA Clearance for Oncology Imaging Suite With Deep Learning
Technology | Artificial Intelligence | February 15, 2018
February 15, 2018 — Arterys Inc. announced its fifth 510(k) clearance from the U.S.
NEST Program Names ACR Data Science Institute AI Use Case as Demonstration Project
News | Artificial Intelligence | February 07, 2018
A U.S. Food and Drug Administration (FDA)-funded program to speed safe and effective medical device technologies to...
MedyMatch Receives FDA Device Designation for Intracranial Hemorrhage Software
News | Computed Tomography (CT) | February 01, 2018
February 1, 2018 – MedyMatch Technology, a company focused on helping physicians provide accurate patient assessment
Machine Learning Techniques Generate Clinical Labels of Medical Scans
News | Artificial Intelligence | January 31, 2018
Researchers used machine learning techniques, including natural language processing algorithms, to identify clinical...
Elekta and IBM Watson Health Bringing Artificial Intelligence to Oncology
News | Oncology Diagnostics | January 31, 2018
Elekta announced it is collaborating with IBM Watson Health to offer Watson for Oncology with Elekta’s cancer care...
Small-Cell Lung Cancer Patients Face Barriers to Standard-of-Care Treatment
News | Lung Cancer | January 29, 2018
Despite decades of clinical research establishing chemotherapy with thoracic radiation as the standard-of-care for the...
MedCurrent Rolls Out OrderWise Clinical Decision Support Platform With iRefer Guidelines
Technology | Clinical Decision Support | January 29, 2018
Primary care providers and hospital doctors around the world can now access the imaging referral guidelines from the U....
Deep learning, artificial intelligence in radiology was the prime topic of discussion at the RSNA/AAPM symposium at RSNA 2017.

Deep learning, artificial intelligence in radiology was the prime topic of discussion at the RSNA/AAPM symposium at RSNA 2017.

Feature | RSNA 2017 | January 29, 2018
When considering potential topics for the 2017 Radiological Society of North America (RSNA)/American Association of P
Overlay Init