Open Source Imaging Consortium Launches $55,000 AI Competition To Help Pulmonary Fibrosis Patients

0
990
  • The competition is administered by data science community platform Kaggle and will run through sixth October 2020
  • Challenge participants will be given a CT scan of idiopathic pulmonary fibrosis (IPF) patient’s lungs and asked to use machine learning techniques to predict the severity of lung function decline

The Open Source Imaging Consortium (OSIC) has announced the launch of the $55,000 OSIC Pulmonary Fibrosis Progression. It is an AI-focused challenge to predict lung function decline in people living with pulmonary fibrosis. The competition is administered by data science community platform Kaggle and will run through sixth October 2020.

OSIC was created to enable rapid advances in the fight against fibrosing interstitial lung diseases (ILDs) such as idiopathic pulmonary fibrosis (IPF), and other respiratory conditions including emphysema. It aims to bring together radiologists, clinicians, and computational scientists from around the world to improve imaging-based approaches to diagnosis, prognosis, and therapy.

Elizabeth Estes, the consortium’s executive director said, “OSIC was created to bring divergent groups together to look at new ways of fighting complex lung disease. In addition to utilizing expertise from academia, industry and philanthropy, we wanted to introduce clinicians to the broader artificial intelligence and machine learning community to see if new eyes and new tools could help us move forward, faster. We are excited to see the progress that can be made for patients all over the world.”

Machine learning techniques

IPF has no known cause and no known cure. It is characterised by scarring of the lungs leading to an irreversible decline in pulmonary function that is easily identified on computerised tomographic (CT) chest imaging. People living with IPF have an average life expectancy of three to five years after diagnosis.

Challenge participants will be given a CT scan of an IPF patient’s lungs and asked to use machine learning techniques to predict the severity of lung function decline, as measured by spirometry. The challenge is lead by Dr. Simon Walsh, National Heart and Lung Institute, Imperial College London & OSIC’s lead radiologist, and Dr. David Barber, University College London & OSIC’s lead computational scientist.

Dr. Kevin Brown, National Jewish Health & OSIC’s lead pulmonologist said, “The heterogeneity of outcome in this disease complicates clinical decision making for individual patients, increasing their anxiety and fear,” said Dr. Kevin Brown, National Jewish Health & OSIC’s lead pulmonologist. Success in this challenge will help clinicians provide clarity to our patients, and ultimately improve treatment trial design and accelerate the clinical development of novel therapies.”

LEAVE A REPLY

Please enter your comment!
Please enter your name here