ACR, SIIM announce machine learning challenge for detecting pneumothorax
The American College of Radiology (ACR) and the Society for Imaging Informatics in Medicine (SIIM) announced they will host a machine learning challenge on pneumothorax detection and localization.
Both societies are collaborating with the Society of Thoracic Radiology (STR) and Md.ai to put on The Machine Learning Challenge on Pneumothorax Detection and Localization, which will kick-off at the SIIM 2019 Annual Meeting starting June 26 in Aurora, Colorado.
“SIIM is very excited to leverage prior annotation work and share the resulting dataset with ACR in this Challenge” said Steven G. Langer, PhD, co-chair of the SIIM Machine Learning Committee, in an ACR news release.
Participants will be tasked with using publicly-available augmented annotations to create a high-quality algorithm that prioritizes patients for expedited review and treatment while promoting the development of clinically relevant AI use cases, according to the release. All annotations are taken from a National Institutes of Health chest radiograph dataset created using a web-based tool from 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., MD, 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.”
Winning teams will be announced at the 2019 SIIM Conference on Machine Intelligence in Medical Imaging taking place September 22-23 in Austin.
Matt joined Chicago’s TriMed team in 2018 covering all areas of health imaging after two years reporting on the hospital field. He holds a bachelor’s in English from UIC, and enjoys a good cup of coffee and an interesting documentary.