A Personalized 3D-Printed Model for Obtaining Informed Consent Process for Thyroid Surgery: A Randomized Clinical Study Using a Deep Learning Approach with Mesh-Type 3D Modeling

Abstract

The aim of this study was to evaluate the usefulness of a personalized 3D-printed thyroid model that characterizes a patient’s individual thyroid lesion. The randomized controlled prospective clinical trial (KCT0005069) was designed. Fifty-three of these patients undergoing thyroid surgery were randomly assigned to two groups: with or without a 3D-printed model of their thyroid lesion when obtaining informed consent. We used a U-Net-based deep learning architecture and a mesh-type 3D modeling technique to fabricate the personalized 3D model. The mean 3D printing time was 258.9 min, and the mean price for production was USD 4.23 for each patient. The size, location, and anatomical relationship of the tumor and thyroid gland could be effectively presented using the mesh-type 3D modeling technique. The group provided with personalized 3D-printed models showed significant improvement in all four categories (general knowledge, benefits and risks of surgery, and satisfaction; all p < 0.05). All patients received a personalized 3D model after surgery and found it helpful to understand the disease, operation, and possible complications and their overall satisfaction (all p < 0.05). In conclusion, the personalized 3D-printed thyroid model may be an effective tool for improving a patient’s understanding and satisfaction during the informed consent process.