News | Artificial Intelligence | June 03, 2019

SIIM and ACR Host Machine Learning Challenge for Pneumothorax Detection and Localization

Competition will see teams design artificial intelligence-based algorithms, with winning algorithms open sourced to benefit radiology

SIIM and ACR Host Machine Learning Challenge for Pneumothorax Detection and Localization

June 3, 2019 — The Society for Imaging Informatics in Medicine (SIIM) and the American College of Radiology (ACR) are collaborating with the Society of Thoracic Radiology (STR) and MD.ai to host a Machine Learning Challenge on Pneumothorax Detection and Localization on Kaggle. The challenge will use augmented annotations on the public chest radiograph dataset from the National Institutes of Health (NIH). The augmented annotations were created by radiologists from SIIM and STR using a commercial web-based tool from MD.ai, and follow the ACR Data Science Institute’s structured artificial intelligence (AI) use case for pneumothorax detection.

“SIIM is very excited to leverage prior annotation work and share the resulting dataset with ACR in this challenge” said Steven G. Langer, Ph.D., CIIP, professor of radiologic physics and imaging informatics at Mayo Clinic and co-chair of the SIIM Machine Learning Committee.

Challenge participants will develop high-quality pneumothorax detection algorithms to prioritize patients for expedited review and treatment and promote the development of clinically relevant use cases for AI. Standards-based healthcare application programming interfaces (APIs) will be used to reduce the interoperability barriers to clinical implementation post-competition.

The ACR DSI and SIIM will use their respective talents and resources to promote deployment of the winning algorithm(s) into clinical use for the benefit of the greater medical imaging community, improving quality and efficiency in healthcare.

“We are encouraging participants to use standard healthcare APIs (FHIR and DICOMweb) in the competition,” added his fellow Co-Chair George Shih, M.D., MS, associate professor of clinical radiology at Weill Cornell Medicine, who is a paid consultant and an equity board member for MD.ai.

“This Kaggle competition will result in open source algorithms to help solve a serious healthcare problem that can lead to death if not identified and treated quickly,” said Bibb Allen Jr., M.D., FACR, ACR Data Science Institute chief medical officer. “By co-hosting this challenge to engage data scientists in solving real clinical problems defined in a structured AI use case, we are bringing together the radiology and technical communities to generate new healthcare solutions and improve patient care.”

“The STR is excited to participate in the augmentation of the NIH dataset by providing our subspecialty expertise in the annotation and adjudication process,” said Carol C. Wu, M.D., chair of the STR Big Data Subcommittee.

SIIM and the ACR will kick off the Pneumothorax Detection Challenge at the SIIM 2019 Annual Meeting, June 26-28, in Aurora, Colo., and award the winning teams at the 2019 SIIM Conference on Machine Intelligence in Medical Imaging (C-MIMI), Sept. 22-23 in Austin, Texas.

For more information: www.siim.org

Related Content

Newly released study results present a strong case for lung cancer screening in New Zealand — particularly for Māori whose mortality rates are between three and four times higher than other ethnic groups.

Image courtesy of Siemens Healthineers

News | Lung Imaging | September 30, 2020
September 30, 2020 — Newly released study results present a strong case for...
The artificial intelligence-driven Caption Guidance software guides point of care ultrasound (POCUS) users to get optimal cardiac ultrasound images. The AI software is an example of a FDA-cleared software that is helping improve imaging, even when used by less experienced users.

The artificial intelligence-driven Caption Guidance software guides point of care ultrasound (POCUS) users to get optimal cardiac ultrasound images. The AI software is an example of a FDA-cleared software that is helping improve imaging, even when used by less experienced users.

Feature | Artificial Intelligence | September 29, 2020 | Joe Fornadel, J.D., and Wes Moran, J.D.
The number of Federal Drug Administration (FDA)-approved AI-based algorithms is significant and has grown at a steady
Lung and respiratory health pioneer paves way for more precise care of complex respiratory conditions
News | Artificial Intelligence | September 25, 2020
September 25, 2020 — VIDA Diagnostics, Inc. announced that it has received 510(k) clearance from the Food and Drug Ad
EchoGo Pro automates cardiac ultrasound measurements for heart functions, but also empower physicians to predict the occurrence of coronary artery disease (CAD).

EchoGo Pro automates cardiac ultrasound measurements for heart functions, but also empower physicians to predict the occurrence of coronary artery disease (CAD).

News | Cardiovascular Ultrasound | September 25, 2020
September 25, 2020 — Based on its recent analysis of the global...
RADLogics AI-Powered solution in use: chest X-ray of COVID-19 positive case with heatmap key image.

RADLogics AI-Powered solution in use: chest X-ray of COVID-19 positive case with heatmap key image.

News | Artificial Intelligence | September 23, 2020
September 23, 2020 — RADLogics