3D-gedruckte Platten für die Versorgung von Lippen- und Gaumenspalten

At its core, the project employs a deep learning model, which was trained on a dataset that Schnabel and Mueller’s team assembled for this specific purpose. “Collecting sufficient data is often the greatest challenge when it comes to machine learning, especially for digital health, because medical data are sensitive and have to be treated confidentially and with the proper data security protocols,” says Till Schnabel. Nevertheless, they were able to gather around 400 scans: about two-thirds of children affected with a one-sided cleft and the other one-third of children with double clefts. “We collected data from old plaster cast imprints, which we digitized via 3D scanning, and we combined it with new data from intraoral scans,” explains Till Schnabel.

The deep learning model trained on this data can automatically recognise and select the principal structures, so-called landmarks, on the digital 3D model of the palate. In the rest of the pipeline, Schnabel and colleagues implemented established methods, such as surface registration and smoothing algorithms. “With the help of the selected landmarks, one can more accurately register a 3D scan, i.e., determine a close correspondence between the template and the input scan.” This method also provides a 3D segmentation differentiating various areas on the intraoral scan. The final step is automated plate computation, which comprises filling the cleft palate area and volumizing the surface to be 3D-printed. In short, these algorithms ensure that the plate is customised to the individual geometry of the baby’s mouth, and mimics, as best as possible, a healthy closed palatal shape.

The pipeline has already been successfully implemented in the clinical routine in two hospitals, where 19 children have been treated with palatal plates that were produced with the digital pipeline. At the University Hospital Basel and Saveetha Medical College and Hospital, Chennai, India, digital intraoral scanning has already reduced the time necessary for conventional impression-taking from over 60 minutes to less than 20 minutes.

“The biggest difference, though, became evident in plate fabrication,” says Till Schnabel. “Previously, it would take close to an hour to make a plate – with our pipeline, the plate was done in less than 5 minutes.” Moreover, it didn’t require a plate specialist to operate complex software but only a few clicks on the computer. In other words, the plates are potentially accessible anywhere, regardless of facility resources. “In India, the workflow was made even more accessible. Hospitals did not need to have the printing infrastructure on site, the pipeline can be decentralised and is compatible with remote printing,” recounts Till Schnabel. “It worked perfectly.”

Schnabel is confident that the team’s automated pipeline will make a big difference in the treatment of cleft lip and palate, especially in low-income countries. “It has the potential to reduce the costs of cleft lip and palate care substantially,” he says, “making treatment accessible for those who might have been excluded so far.”

And thus, one has to emphasise the potential impact of the research. It can reduce the burden of this condition and the devastating effects it can have on children and their families; it can enable more children to heal.