Gaze-Contingent 3D Control for Focused Energy Ablation in Robotic Assisted Surgery

Authors:
Danail Stoyanov;George P. Mylonas;Guang-Zhong Yang
Affiliations:
Institute of Biomedical Engineering, Imperial College London, London, UK SW7 2AZ;Institute of Biomedical Engineering, Imperial College London, London, UK SW7 2AZ;Institute of Biomedical Engineering, Imperial College London, London, UK SW7 2AZ
Venue:
MICCAI '08 Proceedings of the 11th International Conference on Medical Image Computing and Computer-Assisted Intervention, Part II
Year:
2008

Citing 6
Cited 1

Multiple view geometry in computer visiond

Multiple view geometry in computer visiond
Mean Shift: A Robust Approach Toward Feature Space Analysis

IEEE Transactions on Pattern Analysis and Machine Intelligence
Mean Shift Based Clustering in High Dimensions: A Texture Classification Example

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
pq-space based non-photorealistic rendering for augmented reality

MICCAI'07 Proceedings of the 10th international conference on Medical image computing and computer-assisted intervention
Soft-tissue motion tracking and structure estimation for robotic assisted MIS procedures

MICCAI'05 Proceedings of the 8th international conference on Medical image computing and computer-assisted intervention - Volume Part II
Gaze-Contingent soft tissue deformation tracking for minimally invasive robotic surgery

MICCAI'05 Proceedings of the 8th international conference on Medical Image Computing and Computer-Assisted Intervention - Volume Part I

Tracking of irregular graphical structures for tissue deformation recovery in minimally invasive surgery

MICCAI'10 Proceedings of the 13th international conference on Medical image computing and computer-assisted intervention: Part III

Quantified Score

Hi-index	0.00

Visualization

Abstract

The use of focused energy delivery in robotic assisted surgery for atrial fibrillation requires accurate prescription of ablation paths. In this paper, an original framework based on fusing human and machine vision for providing gaze-contigent control in robotic assisted surgery is provided. With the proposed method, binocular eye tracking is used to estimate the 3D fixations of the surgeon, which are further refined by considering the camera geometry and the consistency of image features at reprojected fixations. Nonparametric clustering is then used to optimize the point distribution to provide an accurate ablation path. For experimental validation, a study where eight subjects prescribe an ablation path on the right atrium of the heart using only their gaze control is presented. The accuracy of the proposed method is validated using a phantom heart model with known 3D ground truth.