What do you get when you put AI together with 3D printing?

According to Niall Haslam, CTO for Axial3D, a medical 3D printing company based in Northern Ireland, you get the ability to provide safe, detailed surgical plans for upwards of 8 million patients whose impending surgeries aren’t well served by plans using a compilation of 2D images.

“A 3D anatomical model removes unnecessary variability from one surgeon’s anatomical interpretation from another - standardizing the approach in interpreting the patient’s anatomical detail,” Haslam explained in a recent commentary. “The models can be held in the surgeon’s hands and fully scrutinized, allowing them to define and simulate a surgical plan before they set foot in the operating theatre - reducing the risk to the patient.”

To be sure, Haslam notes, using 3D printing to create patient-specific models for pre-operative planning “is still in its infancy,” with a recent Gartner study finding that just about 3 percent of hospitals and research institutions currently have 3D printing capabilities on site.

But in addition to a lack of investment in the necessary technology, another impediment to adoption has been a limited availability of the radiologists or biomedical engineers need to “segment” 2D images.

“The segmentation process is the partitioning of an image into multiple labelled regions to locate objects and areas of interest in images. This can be an extremely time-consuming process and take clinicians away from treating patients for hours at a time,” Haslam explained.

But this is where AI can provide a critical component to move efforts forward.  According to Haslam, “(p)roducing a 3D printable model from 2D images currently takes anywhere between four to ten hours per printed model,” but tapping into machine learning algorithms allows engineers “to deliver near-instantaneous results.”

Specifically, he says, his company has “developed an online ordering portal that allows surgeons to easily and quickly place orders to request a 3D printed model. The anonymised data is then given a unique identifier code and uploaded and managed on AWS Cloud, allowing us to deal with large volumes of medical images quickly and securely. All of this speeds up the process of producing and shipping the patient-specific 3D anatomical models to meet our delivery guarantee of 48 hours.”

As he sums up the incorporation of AI, “the effect this has on patient care is game-changing.”

Time is money, of course, and the combination of AI and 3D printing is saving both, as well as, most importantly, improving necessary care for millions of patients a year.