The Society for Imaging Informatics in Medicine (SIIM) and American College of Radiology (ACR) are hosting a new machine learning challenge as part of a collaboration with the Society of Thoracic Radiology (STR) and MD.ai.
The Machine Learning Challenge on Pneumothorax Detection and Localization will use augmented annotations created by SIIM and STR radiologists. All annotations are part of an established National Institute of Health (NIH) dataset. The challenge officially begins at the SIIM 2019 Annual Meeting June 26-28 in Aurora, Colorado, and the winning team will be recognized at the 2019 SIIM Conference on Machine Intelligence in Medicine Imaging September 22-23 in Austin, Texas. The competition will use a web-based tool produced by MD.ai and use cases developed by the ACR Data Science Institute (DSI).
“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,” Bibb Allen Jr., MD, chief medical officer of the ACR DSI, said in a prepared statement. “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,” Carol C. Wu, MD, chair of the STR Big Data Subcommittee, said in the same statement.
Once a winning algorithm is chosen, the ACR DSI and SIIM will both work to help imaging providers implement it in their day-to-day workflows.
Michael has more than 16 years of experience as a professional writer and editor. He has written at length about cardiology, radiology, artificial intelligence and other key healthcare topics.