RSNA 2019 News

AI enhances evaluation of chest x-rays

By staff writers
December 3, 2019

The use of artificial intelligence (AI) can significantly improve the interpretation of chest x-rays, overcoming the limitations of traditional chest radiography through the use of large, diverse datasets, according to research published on December 3 in Radiology.

Researchers at Google Health made use of two large datasets, one consisting of more than 750,000 images from India and the other consisting of 112,120 images from the U.S. National Institutes of Health. Their goal was to form, train, and test AI models to tackle challenges such as interreader variability and subpar sensitivity in detecting key clinical findings on chest x-rays, an area of interpretation in radiology that can involve qualitative assessment.

A panel of radiologists was assembled to produce reference standards for specific abnormalities discernible on chest x-rays used to train the AI models.

Trials of the deep-learning models demonstrated that they function as well as radiologists in identifying four findings on frontal chest x-rays: fractures, masses or nodules, opacity, and pneumothorax.

Radiologist adjudication resulted in greater expert consensus of the labels used for model tuning and performance evaluation: The overall consensus rose from slightly more than 41% after the initial read of the x-ray to close to 97% subsequent to adjudication.

AI needs robust clinical evaluation in healthcare
It's not enough for a healthcare artificial intelligence (AI) algorithm to be highly accurate. To be widely adopted in clinical use, it must demonstrate...
Deep-learning model characterizes PET/CT findings
An artificial intelligence algorithm shows a promising level of accuracy for identifying normal and abnormal results on FDG-PET/CT exams, and it could...
Can AI find brain hemorrhage as well as radiologists?
An artificial intelligence (AI) algorithm was able to accurately identify acute intracranial hemorrhage on head CT scans and even find some tiny hemorrhages...
AI tops recent imaging informatics highlights
Artificial intelligence (AI) has been the driving force behind the most important recent advances achieved in imaging informatics, according to a presentation...
Video from SIIM 2019: Dr. Howard Chen on recent advances in imaging informatics
DENVER - What were the key developments in imaging informatics in 2018? Dr. Howard Chen of the Cleveland Clinic highlights five significant trends...

Copyright © 2019

Last Updated np 12/2/2019 6:19:51 PM