SIIM and ACR Host Machine Learning Challenge

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

A Kaggle competition where winning algorithms are open sourced to benefit radiology

(Leesburg, VA, 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, using 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, PhD, CIIP, Professor of Radiologic Physics and Imaging Informatics at Mayo Clinic and Co-chair of the SIIM Machine Learning Committee.

“We are encouraging participants to use standard Healthcare APIs (FHIR and DICOMweb) in the competition,” added his fellow Co-Chair George Shih, MD, MS, Associate Professor of Clinical Radiology at Weill Cornell Medicine, who is a paid consultant and an equity board member for MD.ai, a company focused in accelerating the application of AI in medicine with a particular focus on medical imaging.

“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., MD, 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, MD, Chair of the STR Big Data Subcommittee.

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 API’s 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.

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

About the Society for Imaging Informatics in Medicine
The Society for Imaging Informatics in Medicine (SIIM) is the leading healthcare professional organization for those interested in the current and future use of informatics in medical imaging. The society’s mission is to advance medical imaging informatics across the enterprise through education, research, and innovation in a multi-disciplinary community.

About the American College of Radiology
The American College of Radiology (ACR), founded in 1924, is a professional medical society dedicated to serving patients and society by empowering radiology professionals to advance the practice, science and professions of radiological care.

About the Society of Thoracic Radiology
The Society of Thoracic Radiology (STR), founded in 1982, is a premier professional organization dedicated to promoting cardiothoracic imaging for the excellence in patient care through research and education.

Contact:
For SIIM: Anna Zawacki, azawacki@siim.org
For ACR: Shawn Farley or Meghan Swope, pr@acr.org
For STR: Carol C. Wu, MD, ccwu1@mdanderson.org