Variational Shape Completion for Virtual Planning of Jaw Reconstructive Surgery
This work addresses the challenge of unknown premorbid jaw geometry for surgical teams, offering a clinically relevant solution for virtual planning in reconstructive surgery, though it is incremental as it builds on existing CVAE methods.
The paper tackles the problem of reconstructing missing mandible segments for jaw surgery by introducing a deep learning framework that uses a voxel-weighted Dice loss and a weighted multi-target probabilistic extension to CVAE, achieving statistically significant improvements over similar algorithms in both deterministic and probabilistic paradigms.
The premorbid geometry of the mandible is of significant relevance in jaw reconstructive surgeries and occasionally unknown to the surgical team. In this paper, an optimization framework is introduced to train deep models for completion (reconstruction) of the missing segments of the bone based on the remaining healthy structure. To leverage the contextual information of the surroundings of the dissected region, the voxel-weighted Dice loss is introduced. To address the non-deterministic nature of the shape completion problem, we leverage a weighted multi-target probabilistic solution which is an extension to the conditional variational autoencoder (CVAE). This approach considers multiple targets as acceptable reconstructions, each weighted according to their conformity with the original shape. We quantify the performance gain of the proposed method against similar algorithms, including CVAE, where we report statistically significant improvements in both deterministic and probabilistic paradigms. The probabilistic model is also evaluated on its ability to generate anatomically relevant variations for the missing bone. As a unique aspect of this work, the model is tested on real surgical cases where the clinical relevancy of its reconstructions and their compliance with surgeon's virtual plan are demonstrated as necessary steps towards clinical adoption.