The new method begins with a human expert who pinpoints an MRI image's boundaries in a few of the cross sections; the computer algorithms take over from there.
The researchers said the best results came when they asked the expert to segment only a small patch equal to one-ninth of the total area of each cross section.
After just 14 patches had been segmented, the algorithm was able to infer the rest with 90% agreement with expert segmentation of the entire collection of 200 cross sections. Human segmentation of just three patches yielded 80% agreement.
"I think that if somebody told me that I could segment the whole heart from eight slices out of 200, I would not have believed them," Golland says. "It was a surprise to us."
The process of using a human expert to segment sample patches and the algorithmic generation of a digital, 3D heart model takes about an hour. The 3D-printing process takes a couple of hours more.
Golland who was referring to surgeons as "collaborators," added that "surgeons see with their hands," and that perception is in the touch.
This fall, seven cardiac surgeons at Boston Children's Hospital will participate in a study intended to evaluate the models' usefulness.
In October, Golland and other researchers will talk about the new imaging and printing system at the International Conference on Medical Image Computing and Computer Assisted Intervention.
The work was funded by both Boston Children's Hospital and by Harvard Catalyst, a consortium aimed at rapidly moving scientific innovation into the clinic.
Sign up for Computerworld eNewsletters.