Crowds Cure Cancer at RSNA 2017


Martinos News

Can crowdsourcing provide us with a cure for cancer? We hope to find out. Join us in an experiment at the RSNA annual meeting next week, where just a few minutes of your time could move us closer to this ever-elusive goal.

Advances in artificial intelligence and machine learning have broad potential for cancer prevention, diagnosis, monitoring and treatment, especially when combined with images from radiology. The Cancer Imaging Archive—a large repository of publicly available images—is a rich resource that could be used to this end. But the images in the archive often lack the necessary labels. This is where you come in.

During the meeting, researchers with the MGH Martinos Center and elsewhere will be recruiting attendees to help label tumors by marking their largest diameter. Their goal: to annotate more than 500 cases of a variety of cancer types, enlisting as many domain experts as possible to do so. You can use computers set up at the “Crowds Cure Cancer” booth—or even your laptops, tablets or mobile phones—to spend a few minutes identifying tumors in cancer patients. Your collective efforts will help in developing better, AI-based tools for cancer diagnosis and prognosis.

All of the annotation data collected will be made accessible to the research community via the Cancer Imaging Archive. In addition, when you participate, you will receive a ribbon announcing your role in this exciting experiment.

Read more about Crowds Cure Cancer and other Cancer Imaging Archive sessions at the RSNA meeting here.