This document describes the surgical robot console system based on 3D Slicer for image-guided surgery. Considering the image-guided surgery, since image workstations have complex User Interface (UI) and extra functions, it is supposed that such UI is not suitable for surgeon who is the robot operator. The proposed robot console is designed as a simple UI for the robot operator, which can display the endoscopic video image, the sensor data, the robot status and simple images for guiding the surgery. Therefore, we expect that the surgeon can concentrate on the operation itself by utilizing the robot console. On the other hand, since the robot console system is based on 3D Slicer, the robot console can use the abundant image operation functions. Moreover, it can use the flexibility of tool connectivities by using the OpenIGTLink protocol. In addition, since the video image is captured by using the multifunctional library OpenCV , we can expect the extensibility about the function of the proposed system.

3D Slicer Based Surgical Robot Console System

We present a nearly automatic tool for the accurate segmentation
of vascular structures in volumetric CTA images. Its inputs are a start
and an end seed points inside the vessel. The two-step graph-based energy
minimization method starts by computing the weighted shortest path between
the vessel seed endpoints based on local image and seed intensities and
vessel path geometric characteristics. It then automatically defines a
Vessel Region Of Interest (VROI) from the shortest path and the estimated
vessel radius, and extracts the vessels boundaries by minimize the energy
on a corresponding graph cut.

We evaluate our method within the 2009 MICCAI 3D Segmentation Challenge for
Clinical Applications Workshop. Experimental results on the 46 carotid
bifurcations from clinical CTAs, compared to ground-truth genrated by
averaging three manual annotations, 
yield an average symmetric surface distance of
0.83mm and a Dice similarity of 81.8%, with only three input seeds.
These results indicates that our method is easy to use, produces accurate
segmentations of vessels lumen, and is robust to intensity variations
inside the vessels, radius changes, bifurcations, and nearby anatomical
structures with similar intensity values.

Nearly automatic vessels segmentation using graph-based energy minimization

This document describes a contribution to the Insight Toolkit intended to smooth the values of Field data associated with the nodes of a Spherical Mesh. The Mesh Smoothing filters contributed here do not modify the geometry or the topology of the Mesh. They act only upon the pixel data values associated with the nodes. Two filters are presented, one that smooths scalar field data, and a second one that smooths vector field data.
 This paper is accompanied with the source code, input data, parameters and output data that we used for validating the algorithm described in this paper. This adheres to the fundamental principle that scientific publications must facilitate reproducibility of the reported results.


Iterative Smoothing of Field Data in Spherical Meshes

A vessel lumen centerline extraction method is presented. Its preprocessing and initialization for the application to 3D CT angiography (CTA) image volumes are also described. This approach is based upon the theory of principal curves to finding lumen axis. Meanwhile, it also estimates the lumen local width with an 1D intensity model that depicts an ideal lumen cross-sectional profile. We tested the method on 46 CTA datasets supplied with the Carotid Lumen Segmentation and Stenosis Grading Challenge (CLS) of the ``3D Segmentation in the Clinic: a Grade Challenge'', a 2009 MICCAI Workshop. The evaluation of 31 testing datasets suggests that our method can provide a good basis for post-processing if high accuracy of segmentation and stenosis grading is desired.

Principal Curves: a Technique for Preliminary Carotid Lumen Segmentation and Stenosis Grading

We propose a method for segmenting and labeling the main head and neck vessels (common, internal, external carotid and vertebral arteries) from a contrast enhanced computed tomography angiography (CTA) volume. First, an initial centerline of each vessel is extracted. Next, the vessels are segmented using 3D active objects initialized using the first step. Finally, the true centerline is identified by smoothly deforming it away from the segmented mask edges using a spline-snake. 

We focus particularly on the initial centerline extraction technique. It uses a locally adaptive front propagation algorithm that attempts to find the optimal path connecting the ends of the vessel, typically from the lowest image of the scan to the Circle of Willis in the brain. It uses a patient adapted anatomical model of the different vessels both to initialize and constrain this fast marching, thus eliminating the need for manual selection of seed points. 

The method is evaluated by applying it to the datasets of the MICCAI 2009 carotid bifurcation challenge, for which this paper is the only fully automatic method submitted. 


Fully automated segmentation of carotid and vertebral arteries from CTA

We present a fully automatic method for 3D segmentation of the mandibular bone from CT data. The method includes an adaptation of statistical shape models of the mandible, the skull base and the midfacial bones, followed by a simultaneous graph-based optimization of adjacent deformable models. The adaptation of the models to the image data is performed according to a heuristic model of the typical intensity distribution in the vincinity of the bone boundary, with special focus on an accurate discrimination of adjacent bones in joint regions. An evaluation of our method based on 18 CT scans shows that a manual correction of the automatic segmentations is not necessary in approx. 60% of the axial slices that contain the mandible.

Multi-object Segmentation of Head Bones

The 2009 MICCAI Head and Neck Auto-Segmentation Challenge was aimed at assessing algorithms for automated segmentation of the brain stem and mandible from CT images for use in radiotherapy planning. The organisers provided 10 datasets with associated manual segmentations by experts, and 8 test datasets on which the algorithms had to be run. In two of the test datasets (subjects 13 and 15) the field of view was truncated. The results were independently analysed by the organisers.

To address the problem posed by the challenge we describe a method based on active appearance models (AAMs) which involves four stages: Initialisation with a parts-and-geometry model, search with a global AAM followed by search with local AAMs, then post-processing using linear regressors.

Application of the method to the test images resulted in a mean (excluding subject 13) Dice overlap value of 76.1 +/- 5.1% for the mandible, and 72.9 +/- 24.6% for the brainstem. The method failed to segment both the mandible and brainstem in subject 13, and the whilst giving a successful segmentation of the mandible in subject 15, gave poor results on the brainstem. It takes about 10 minutes to run on a 64 bit Linux workstation with 2GB RAM, and a 2GHz pentium processor. We were encouraged by its performance on this dataset, and believe that its accuracy can be improved with some modifications to the segmentation pipeline.


AAM Segmentation of the Mandible and Brainstem

In this paper, we present an atlas-based level set automatic method for segmenting anatomical structures in head and neck CT data, such as mandible and brainstem. The proposed method is a hybrid method that combines two aspects. First, we register the atlas image to the image to be segmented using an intensity-based non-rigid image registration algorithm based on B-spline, the corresponding binary image of the atlas is also resampled into the reference image coordinate system according to the deformation field obtained from the registration process. Second, based on the initialization of the deformed atlas binary mask, the level set function is evolved to segment the object of interest in the test image. The proposed method was tested on CT images of head and neck and compared with expert segmentation of mandible and brainstem. The evaluation results show the method is available and effective.

Segmentation of Head and Neck CT Scans Using Atlas-based Level Set Method

This paper presents automated segmentation of structures in the Head and Neck (H&N) region, using an active contour-based joint registration and segmentation model. A new atlas selection strategy is also used. Segmentation is performed based on the dense deformation field computed from the registration of selected structures in the atlas image that have distinct boundaries, onto the patient's image. This approach results in robust segmentation of the structures of interest, even in the presence of tumors, or anatomical differences between the atlas and the patient image. For each patient, an atlas image is selected from the available atlas-database, based on the similarity metric value, computed after performing an affine registration between each image in the atlas-database and the patient's image. Unlike many of the previous approaches in the literature, the similarity metric is not computed over the entire image region; rather, it is computed only in the regions of soft tissue structures to be segmented. Qualitative and quantitative evaluation of the results is presented.

Active Contour-Based Segmentation of Head and Neck with Adaptive Atlas Selection

We present a semi-automatic algorithm for Carotid lumen segmentation on CTA images.
Our method is based on a variant of the minimal path method that models the vessel as a centerline and boundary. This is done by adding one dimension for the local radius around the centerline. The crucial step of our method is the definition of the local metrics to minimize. We have chosen to exploit the tubular structure of the vessels one wants to extract to built an anisotropic metric giving higher speed on the center of the vessels and also when the minimal path tangent is coherent with the vessel’s direction. Due to carotid stenosis or occlusions on the provided data, segmentation is refined using a region-based level sets.