Intraoperative estimation of liver boundary conditions from multiple partial surfaces

A computer-assisted surgical system must provide up-to-date and accurate information of the patient's anatomy during the procedure to improve clinical outcome. It is therefore essential to consider the tissue deformations, and a patient-specific biomechanical model (PBM) is usually adopted. The predictive capability of the PBM is highly influenced by proper definition of attachments to the surrounding anatomy, which are difficult to estimate preoperatively.

We propose to predict the location of attachments using a deep neural network fed with multiple partial views of the intraoperative deformed organ surface directly encoded as point clouds. Compared to previous works, providing a sequence of deformed views as input allows the network to consider the temporal evolution of deformations and to handle the intrinsic ambiguity of estimating attachments from a single view.

The method is applied to computer-assisted hepatic surgery and tested on both a synthetic and in vivo human open-surgery scenario. The network is trained on a patient-specific synthetic dataset in less than 5 h and produces a more accurate intraoperative estimation of attachments than applying the ones generally used in liver surgery (i.e., fixing vena cava or falciform ligament). The obtained results show 26% more accurate predictions than other solution previously proposed.

Trained with patient-specific simulated data, the proposed network estimates the attachments in a fast and accurate manner also considering the temporal evolution of the deformations, improving patient-specific intraoperative guidance in computer-assisted surgical systems.