Feature | Information Technology | June 27, 2019 | By Greg Freiherr

Smart Algorithm Extracts Data from Radiology Reports

SIIM talk details early experience with data mining

Smart Algorithm Extracts Data from Radiology Reports
Greg Freiherr

Greg Freiherr

Radiology reports may contain information essential to figuring out a patient’s condition. But this information is often locked in free text, which can make it difficult to search, analyze and summarize report data.  That’s where natural language processing (NLP) might come in.

On June 26, 2019, IBM researcher Ashutosh Jadhav, Ph.D., described at the annual meeting of the Society for Imaging Informatics in Medicine (SIIM) in Denver an algorithm that uses artificial intelligence to extract information from the free text of radiology reports.

 “There is a lot of information hidden in these reports,” Jadhav told ITN after his presentation during the Natural Language Processing session. Included in that information are things like the physician’s findings. The extracted data might be used to automatically populate data fields in PACS.

Automatic structuring of radiology reports could unleash the power of information otherwise locked in these reports, he told an audience attending his presentation titled “Automatic Extraction of Structured Radiology Reports.” Jadhav and his colleagues are working to further improve the prototype, he said, noting that he cannot predict if or when the algorithm will be productized. “Our work is majorly focused on the research aspect,” he told ITN after his presentation. Jadhav is a research staff member at IBM Research Almaden, IBM's Silicon Valley innovation lab.

 

Extensive Research

In developing the NLP algorithm, Jadhav and colleagues had to overcome challenges including missing section labels, inconsistent section ordering, and inconsistent section formatting. Differences among institutions and individual radiologists should not be issues, he told ITN, because “we have a really big sample size and we are processing reports from multiple institutes.”

Radiology reports from more than 200,000 chest X-rays were used to develop the algorithm. These reports were randomly split into training and testing data sets. The training data set, comprised of about 80 percent of these reports, was used to develop NLP rules. The remaining 20 percent comprised the data set used for testing. Some 200 reports, randomly selected from the testing set, were used to determine how well the algorithm identified sections and corresponding section texts.

 

Greg Freiherr is a contributing editor to Imaging Technology News (ITN). Over the past three decades, he has served as business and technology editor for publications in medical imaging, as well as consulted for vendors, professional organizations, academia, and financial institutions.

 

Editor’s note: This article is the seventh piece in a content series by Greg Freiherr covering the Society for Imaging Informatics in Medicine (SIIM) conference in June.

 

Related content:

Why Blockchain Matters In Medical Imaging

DeepAAA Uses AI to Look Automatically For Aneurysms

Making AI Safe, Effective and Humane for Imaging

Cinebot: Efficient Creation of Movies and Animated Gifs for Presentation and Education Directly from PACS

5 Low-Cost Ways To Slow Hackers

Imaging on Verge of Game-changing Transformation

How to Fix Your Enterprise Imaging Network

Imaging on Verge of Game-changing Transformation

VIDEO: AI That Second Reads Radiology Reports and Deals With Incidental Findings

AI Detects Unsuspected Lung Cancer in Radiology Reports, Augments Clinical Follow-up 

Related Content

New Module Creates a Warped MRI Scan that Matches Real-Time Ultrasound Results (Graphic: Business Wire)

New Module Creates a Warped MRI Scan that Matches Real-Time Ultrasound Results (Graphic: Business Wire)

News | Artificial Intelligence | May 07, 2021
Building the right infrastructure today will ensure the needed tools are there tomorrow, whatever the challenge may be

Getty Images

Feature | Radiology Business | May 05, 2021 | By Tom Cheesewrite in collaboration with Ludger Philippsen
The COVID-19 pandemic came as a shock, but not a
#DDR allows #clinicians to observe movement like never before. This enhanced version of a standard digital radiographic system can acquire up to 15 sequential #radiographs per second resulting in 20 seconds of motion and multiple individual #radiographic images. #DDR is not fluoroscopy; it is #cineradiography, or #Xray that moves.

DDR allows clinicians to observe movement like never before. This enhanced version of a standard digital radiographic system can acquire up to 15 sequential radiographs per second resulting in 20 seconds of motion and multiple individual radiographic images. DDR is not fluoroscopy; it is cineradiography, or X-ray that moves. The resulting images provide clinicians with a 4-D data set (a video) that depicts physiological movement. 

Sponsored Content | Case Study | Digital Radiography (DR) | May 05, 2021
Musculoskeletal injuries can be difficult to diagnose with a traditional X-ray because X-rays only reveal a static im
With the growing adoption of #data #analytics in #healthcare, we are seeing more clearly that there are two sides of data
Feature | Artificial Intelligence | May 05, 2021 | By Sundararajan Mani
With the growing adoption of...
As key technological advancements become more pronounced, prolific developments are anticipated to be on the future horizon

Getty Images

Feature | Teleradiology | May 05, 2021 | By Abizer Shaikhmahmud
Teleradiology is grabbing significant eyeballs,