NIH to provide one of largest chest x-ray datasets for research

A chest X-ray identifying a lung mass, pictured, is one of more than 100,00 such X-rays the National Institutes of Health Clinical Center is releasing to the scientific community for research purposes as part of one of the largest publicly available chest X-ray datasets. Photo courtesy NIH

Sept. 30 (UPI) — The National Institutes of Health Clinical Center has released more than 100,000 chest X-ray images and data for use in research by the scientific community.

This release will allow researchers throughout the United States and the world to freely access the datasets and increase their ability to teach computers how to detect and diagnose disease.

NIH compiled the dataset of scans from more than 30,000 patients, including many with advanced lung disease. The NIH Clinical Center is the nation’s largest hospital devoted entirely to clinical research and partners with researchers to voluntarily enroll participants in clinical trials.

The release is detailed in a paper published by the Computer Vision Foundation.

The challenge for researchers is the observation and knowledge of anatomical principles, physiology and pathology that goes into reading and diagnosing a chest X-ray. These factors increase the difficulty of developing a consistent and automated technique for reading images while taking into account all common thoracic diseases.

The dataset will help academic and research institutions across the country be able to teach a computer to read and process extremely large amounts of scans to confirm results and possibly identify other findings that may be overlooked.

The advanced computer technology will also help create a virtual radiology resident that can be taught to read more complex images like CT and MRI scans, identify slow changes occurring over the course of multiple chest X-rays and benefit patients in developing countries that do not have access to radiologists to read and interpret X-rays.

LEAVE A REPLY