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.
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,” says Steven G. Langer, PhD, CIIP, professor of radiologic physics and imaging informatics at Mayo Clinic and co-chair of the SIIM Machine Learning Committee.
“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,” says 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.”
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 program interfaces will be used to reduce the interoperability barriers to clinical implementation post-competition.
The ACR DSI and SIIM will use their respective 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, Colo., and award the winning teams at the 2019 SIIM Conference on Machine Intelligence in Medical Imaging, which will take place from September 22-23 in Austin, Texas.