A Probabilistic Framework for Tracking Deformable Soft Tissue in Minimally Invasive Surgery

Mountney, Peter; Lo, Benny; Thiemjarus, Surapa; Stoyanov, Danail; Zhong-Yang, Guang

doi:10.1007/978-3-540-75759-7_5

Cited by 47 publications

(40 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is because a typical image of biological soft tissue only contains a limited number of features due to conditions such as free-form tissue deformation, specular highlights and interreflecting lighting conditions [12]. An important future application of the device is to use positional information from the robot actuators to initialize and provide a priori information to the mosaicing algorithm.…”

Section: Experimental Setup and Resultsmentioning

confidence: 99%

Laser-Induced Fluorescence and Reflected White Light Imaging for Robot-Assisted MIS

Noonan¹,

Elson²,

Mylonas³

et al. 2009

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

Abstract-This paper presents an articulated robotic controlled device to facilitate large area in vivo tissue imaging and characterization through the integration of miniaturized reflected white light and fluorescence intensity imaging for Minimally Invasive Surgery (MIS). The device is comprised of a long, rigid shaft with a robotically controlled distal tip featuring three degrees of inplane articulation and one degree of rotational freedom. The constraints imposed by the articulated section, coupled with the small footprint available in MIS devices, require a novel optical configuration to ensure effective target illumination and image acquisition. A tunable coherent supercontinuum laser source is used to provide sequential white light and fluorescence illumination through a multi-mode fibre (200μm diameter) and the reflected images are transmitted to an image acquisition system using a 10,000 pixel flexible fibre image guide (590μm diameter). By using controlled joint actuation to trace overlapping trajectories, the device allows effective imaging of a larger field-of-view than a traditional dual-mode laparoscope. A first generation prototype of the device and its initial phantom and ex-vivo tissue characterization results are described. The results demonstrate the potential of the device to be used as a new platform for in vivo tissue characterization and navigation for MIS.

show abstract

Section: Experimental Setup and Resultsmentioning

confidence: 99%

Laser-Induced Fluorescence and Reflected White Light Imaging for Robot-Assisted MIS

Noonan¹,

Elson²,

Mylonas³

et al. 2009

IEEE Trans. Biomed. Eng.

View full text Add to dashboard Cite

show abstract

“…In the work of Mountney et al [18], the authors propose a Bayesian framework for fusing keypoint descriptors. In their approach, a first training step selects amongst a set of keypoint descriptors those that are most discriminative.…”

Section: Keypoint Fusionmentioning

confidence: 99%

Keypoint descriptor fusion with Dempster–Shafer theory

Mondéjar-Guerra

Muñoz-Salinas

Marín-Jiménez

et al. 2015

International Journal of Approximate Reasoning

View full text Add to dashboard Cite

Keypoint matching is the task of accurately finding the location of a scene point in two images. Many keypoint descriptors have been proposed in the literature aiming at providing robustness against scale, translation and rotation transformations, each having advantages and disadvantages. This paper proposes a novel approach to fuse the information from multiple keypoint descriptors using Dempster-Shafer Theory of evidence [1], which has proven particularly efficient in combining sources of information providing incomplete, imprecise, biased, and conflictive knowledge. The matching results of each descriptor are transformed into an evidence distribution on which a confidence factor is computed making use of its entropy. Then, the evidence distributions are fused using Dempster-Shafer Theory (DST), considering its confidence. As result of the fusion, a new evidence distribution that improves the result of the best descriptor is obtained. Our method has been tested with SIFT, SURF, ORB, BRISK and FREAK descriptors using all possible combinations of them. Results on the Oxford keypoint dataset [2] shows that the proposed approach obtains an improvement of up to 10% compared to the best one (FREAK).

show abstract

“…To this end, feature tracking techniques have been used (Ortmaier et al, 2005) (Mountney et al, 2007). In these approaches, features or salient regions are detected on the tissue surface.…”

Section: Introductionmentioning

confidence: 99%

Context specific descriptors for tracking deforming tissue

Mountney¹,

Yang²

2012

Medical Image Analysis

Self Cite

View full text Add to dashboard Cite

Abstract.In minimally invasive surgery, deployment of motion compensation, dynamic active constraints and adaptive intra-operative guidance require accurate estimation of deforming tissue in 3D. To this end, the use of vision-based techniques is advantageous in that it does not require the integration of additional hardware to the existing surgical settings.Deformation can be recovered by tracking features on the surface of the tissue. Existing methods are mostly based on ad hoc machine vision techniques that have generally been developed for rigid scenes or use pre-determined models with parameters fine tuned to specific surgical settings. In this work, we propose a novel tracking technique based on a context specific feature descriptor. The descriptor can adapt to its surroundings and identify the most discriminate information for tracking. The feature descriptor is represented as a decision tree and the tracking process is formulated as a classification problem for which log likelihood ratios are used to improve classifier training. A recursive tracking algorithm is used to obtain examples of tissue deformation used to train the classifier. Additional training data is generated by geometric and appearance modeling. Experimental results have shown that the proposed context specific descriptor is robust to drift, occlusion, and changes in orientation and scale. The performance of the algorithm is compared with existing tracking algorithms and validated with both simulated and in vivo datasets.

show abstract

A Probabilistic Framework for Tracking Deformable Soft Tissue in Minimally Invasive Surgery

Cited by 47 publications

References 10 publications

Laser-Induced Fluorescence and Reflected White Light Imaging for Robot-Assisted MIS

Laser-Induced Fluorescence and Reflected White Light Imaging for Robot-Assisted MIS

Keypoint descriptor fusion with Dempster–Shafer theory

Context specific descriptors for tracking deforming tissue

Contact Info

Product

Resources

About