MIT, Boston Children's working to advance 3D modeling

3D printing holds immeasurable promise in healthcare and the latest research collaboration in Boston aims to quickly convert MRI scans into models to help surgeons plan surgery.

Researchers at MIT and Boston Children’s Hospital developed the system and seven cardiac surgeons at the hospital will participate in a study this fall to evalute whether the models improve clinical outcomes.

The 3D modeling process has been time-consuming and complex, according to MIT. But, the models “could provide a more intuitive way for surgeons to assess and prepare for the anatomical idiosyncrasies of individual patients,” according to a statement.

For the clinical study, the surgeons will receive data on 10 patients who have already received treatment at Boston Children’s Hospital. Data will include the raw MRI scans and, on a randomized basis, either a physical model or a computerized 3D model, based, again at random, on either human segmentations or algorithmic segmentations.

“Our collaborators are convinced that this will make a difference,” says Polina Golland, a professor of electrical engineering and computer science at MIT, who led the project. “The phrase I heard is that ‘surgeons see with their hands,’ that the perception is in the touch.”

Golland and her colleagues will share their new system at the International Conference on Medical Image Computing and Computer Assisted Intervention in October. Danielle Pace, an MIT graduate student in electrical engineering and computer science, is first author on the paper and led development of the software that analyzes the MRI scans. Mehdi Moghari, a physicist at Boston Children’s Hospital, developed new procedures that increase the precision of MRI scans tenfold, and Andrew Powell, a cardiologist at the hospital, leads the project’s clinical work.

In the past, researchers have produced printable models of the heart by manually indicating boundaries in MRI scans but it takes eight to 10 hours to transform the approximately 200 cross sections in a high-precision scan. Pace and Golland found a way to fast-track the process by attempting to segment only a small patch of each cross section.

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.