Full Program »
Automated Computer-aided Design of Cranial Implants using a Deep Volumetric Convolutional Denoising Autoencoder
Computer-aided Design (CAD) software enables the design of patient-specific cranial implants, but it often requires a lot of manual user-interactions. This paper proposes a Deep Learning (DL) approach towards the automated CAD of cranial implants, allowing the design process to be less user-dependent and even less time-consuming. The problem of reconstructing a cranial defect, which is essentially filling in a region in a skull, was posed as a 3D shape completion task and, to solve it, a Volumetric Convolutional Denoising Autoencoder was implemented using the open-source DL framework PyTorch. The autoencoder was trained on 3D skull models obtained by processing an open-access dataset of Magnetic Resonance Imaging (MRI) brain scans. The 3D skull models were represented as binary voxel occupancy grids and experiments were carried out for different voxel resolutions. For each experiment, the autoencoder was evaluated in terms of quantitative and qualitative 3D shape completion performance. The obtained results showed that the implemented Deep Neural Network (DNN) is able to perform shape completion on 3D models of defected skulls, allowing for an efficient and automatic reconstruction of cranial defects.