News | Artificial Intelligence | October 08, 2019

Competitors will use data set of more than 25,000 head CT scans to develop artificial intelligence algorithms to detect intracranial hemorrhage

RSNA Announces Intracranial Hemorrhage AI Challenge

October 8, 2019 — The Radiological Society of North America (RSNA) recently launched its third annual artificial intelligence (AI) challenge: the RSNA Intracranial Hemorrhage Detection and Classification Challenge.

The AI Challenge is a competition among researchers to create applications that perform a defined task according to specified performance measures. Last year’s pneumonia detection challenge had more than 1,400 teams.

“The goal of an AI challenge is to explore and demonstrate the ways AI can benefit radiology and improve clinical diagnostics,” said Luciano Prevedello, M.D., MPH, chair of the Machine Learning Steering Subcommittee of the RSNA Radiology Informatics Committee. “By organizing these data challenges, RSNA plays a critical role in demonstrating the capabilities of machine learning and fostering the development of AI in improving patient care.”

This year, researchers are working to develop algorithms that can identify and classify subtypes of hemorrhages on head computed tomography (CT) scans. The data set, which comprises more than 25,000 head CT scans contributed by several research institutions, is the first multiplanar dataset used in an RSNA AI Challenge.

The Machine Learning Steering Subcommittee worked with volunteer specialists from the American Society of Neuroradiology (ASNR) to label these exams for the presence of five subtypes of intracranial hemorrhage — an effort of unprecedented scope in the radiology community, the association said.

The challenge is being run on a platform provided by Kaggle Inc. (a subsidiary of Alphabet Inc., also the parent company of Google). Kaggle has recognized the RSNA Intracranial Hemorrhage Detection and Classification Challenge as a public good and will award $25,000 to the winning entries.

On Sept. 3, 2019, the first wave of data was released to researchers who are working to develop and “train” algorithms. The training phase runs through Nov. 4. During this phase, participants will use a training dataset that includes the radiologists’ labels to develop algorithms that replicate those annotations.

During the evaluation phase, from Nov. 4 to Nov. 11, participants will apply their algorithms to the testing portion of the dataset, which is provided to them with the annotations withheld.

Their results will then be compared to the annotations on the testing dataset, and an evaluation metric will be applied to rate their accuracy and determine the winners.

Results will be announced in November and the top submissions will be recognized in the AI Showcase Theater during the RSNA 2019 annual meeting, Dec. 1-6, in Chicago. 

For more information: www.rsna.org/AI-image-challenge


Related Content

Videos | Information Technology

A discussion on macro trends and the future of medical imaging with Jef Williams, managing partner, Paragon Consulting ...

Time February 07, 2023
arrow
News | Radiation Therapy

February 6, 2023 — Varian, a Siemens Healthineers company, announced that it has received 510(k) clearance from the U.S ...

Time February 06, 2023
arrow
News | Radiation Therapy

February 2, 2023 — DenseBreast-info.org (DBI) announced the results of the study, “Effect of an Educational Intervention ...

Time February 02, 2023
arrow
News | Radiation Therapy

February 1, 2023 — Radiotherapy is a crucial component of cancer treatment, used to shrink or destroy tumors with high ...

Time February 01, 2023
arrow
Feature | Radiology Business | By Melinda Taschetta-Millane

Here is a recap of what ITN viewers found most interesting during the month of January: 1. A Look at the Changes in 2023 ...

Time February 01, 2023
arrow
News | Computed Tomography (CT)

January 30, 2023 — Photon-counting detector CT reduces the amount of contrast needed for CT angiography (CTA) while ...

Time January 30, 2023
arrow
Webinar | Information Technology

Postpandemic staffing shortages and increased volumes require radiologists to do more with less, exacerbating burnout ...

Time January 30, 2023
arrow
News | Digital Pathology

January 27, 2023 — Fujifilm has completed its asset purchase of Inspirata, Inc.’s digital pathology business effective ...

Time January 27, 2023
arrow
Videos | PACS

Konica Minolta Healthcare recently announced it is working with Amazon Web Services to offer its cloud-based Exa ...

Time January 27, 2023
arrow
News | Artificial Intelligence

January 26, 2023 — MedCognetics, Inc., an Artificial Intelligence (AI) software firm, announced that it has been awarded ...

Time January 26, 2023
arrow
Subscribe Now