With money on the table, AI inches closer to aiding lung-cancer diagnosis
A contest with a $1 million kitty has brought out the best in research teams competing to develop algorithms for finding lung cancers in low-dose CT images.
The winning team, from Tsinghua University in China, used a neural network and broke the challenge into two parts—identifying nodules and then diagnosing cancer, according to coverage posted May 9 in MIT Technology Review.
A member of the team says the two-pronged approach “seems to be what human experts would do.”
Meanwhile a program director at the National Cancer Institute, which supplied imaging data for the contest, tells the outlet he doesn’t expect algorithms to replace humans in performing the medical task at hand.
“Deep learning will help digest large amounts of data,” he says. “I don’t think [algorithms] are going to replace doctors or radiologists.”
Read the article:
Dave P. has worked in journalism, marketing and public relations for more than 30 years, frequently concentrating on hospitals, healthcare technology and Catholic communications. He has also specialized in fundraising communications, ghostwriting for CEOs of local, national and global charities, nonprofits and foundations.