This study shows that a back-propagation neural network can be used to predict prostate deformation. Further, it is also demonstrated that a combination of ultrasound data, MR images and a neural network can be used as a framework for accurately predicting 3D prostate deformation in real time.

Needle insertion procedures are commonly used to treat and to diagnose prostate cancer. Surgical simulation systems can be used to estimate prostate deformation during pre- and intra-operative needle insertion planning. Such systems require a model that can accurately predict the prostate deformation in real time. In this study, we present a prostate model that incorporates the anatomy of the male pelvic region. The model is used to predict the prostate deformation during needle insertion and it is implemented in the Simulation Open Framework Architecture (SOFA). SOFA simulations are compared with experimental results for two scenarios: indentation and needle insertion. An experimental phantom is developed using anatomically accurate magnetic resonance images and populated with elasticity properties obtained from ultrasound-based Acoustic Radiation Force Impulse imaging technique. Markers are placed on the phantom surface to identify the deformation during indentation experiments. The root mean square error (RMSE) obtained in indentation experiments is 0.36 mm. During the needle insertion, the needle tip position is used to validate the model. The SOFA simulation resulted in a RMSE of 0.14 mm. The results of this study demonstrate that SOFA is a feasible option to be used in surgical simulations for pre-operative planning and training.

Abstract-Through the use of module based software solutions, programming humanoid robots became simple in the sense that detailed knowledge of the underlying software and hardware layers became largely unnecessary. In this paper we argue that the current situation, while being satisfactory for most users, requires improvement for facing situations in which delivery of a complex autonomous behavior is part of the final target. In such case, implementing a dedicated behavior control architecture remains a complex task. In this paper we propose a behavior oriented software framework to be added above the existing modular architecture. This framework is based on centralized integration of sensory data, schematic representation of objects, resource management and intrinsic motivation. It supports code organization, favors code reuse and allows rapid obtention of behaviors that can be easiliy modified or extended. A version of the framework for Aldebaran Nao was developed and tested.