In this paper, we introduce a new concept of surgical navigation which processes information interactively between the real and virtual spaces, namely, updating preoperative images using the positional information of surgical tools. Although the organs are deformed by operative procedures during surgery, surgical navigation systems usually do not change the reference images that are taken prior to surgery. It is useful to generate deformed reference images during surgery while it progresses. We develop a skull base surgery navigation system that updates the preoperative images during surgery. To estimate the resected regions, our proposed system utilizes the positional information of the surgical tools that can be tracked by a surgical navigation system. Our proposed system reflects the bone removal on preoperative images by changing the voxel values of the preoperative images using the positional information of the tracked tools. The updated reference images are generated by visualizing the updated preoperative images using a volume rendering method. We evaluated the proposed system on a skull phantom created from CT images by a 3D printer. The experimental results showed that the proposed system updated the reference images in real time based on the surgical tasks including bone removal process. The accuracy of our proposed method was about 1 mm. It is very useful for surgeons to drill into such complex bone structure as the skull base.

Skull Base Surgery Navigation System Based on Updating Preoperative Images Using Positional Information of Surgical Tools

This document describes the Image-based Vascular Analysis Toolkit (IvanTk), a set of cross-platform C++ open source software libraries for the detection, extraction and modeling of vessels in 2D/3D medical images based on the Insight Toolkit. We provide an overview of the libraries and their purpose and describe their functional modules and future directions of the toolkit.

The Image-based Vascular Analysis Toolkit (IvanTk)

In this paper we applied one of our regularly used processing pipelines for fully automated brain tissue segmentation. Brain tissue was segmented in cerebrospinal fluid (CSF), gray matter (GM) and white matter (WM). Our algorithms for skull stripping, tissue segmentation and white matter lesion (WML) detection were slightly adapted and applied to twelve data sets within the MRBrainS13 brain tissue segmentation challenge. Skull stripping is performed using non-rigid registration of 5 atlas masks. Our tissue segmentation is based on an automatically trained kNN-classifier. Training samples were obtained by non-rigid registration of 5 manually labeled scans followed by a pruning step in feature space to remove any residual erroneously sampled tissue voxels. The kNN-classification incorporates voxel intensities from a T1-weighted scan and a FLAIR scan. The white matter lesion detection is based on an automatically determined threshold on the FLAIR scan. The application of the algorithms on the data from the MRBrainS13 Challenge showed that our pipeline produces acceptable segmentations. Average resulting Dice scores were 77.86 (CSF), 81.22 (GM), 87.27 (WM), 93.78 (total parenchyma), and 96.26 (all intracranial structures). Total processing time was about 2 hours per subject.

Auto-kNN: Brain Tissue Segmentation using Automatically Trained k-Nearest-Neighbor Classification

This paper describes an automated algorithm for segmentation
of brain structures (CSF, white matter, and gray matter) in MR
images. We employ machine learning, i.e. k-Nearest Neighbors, of features
derived from k-means, Canny edge detection, and Tourist Walks
to fully automate the seeding process of the Random Walker algorithm.
We test our methods on a dataset of 12 diabetes patients with atrophy
and varying degrees of white matter lesions provided by the MRBrainS13
Challenge, and find encouraging segmentation performance.

Automated Walks using Machine Learning for Segmentation

This study investigates a method for brain tissue segmentation from 3D T1 weighted (T1w) MR images via convex relaxation with a hierarchical ordering constraint. It employs a multi-atlas-based initialization from 5 training images and is tested on 12 T1w MR images provided by the MICCAI 2013 MRBrainS segmentation challenge. The registered atlas images, fully segmented into eight different brain structures, are used to formulate shape and intensity priors for a Maximum A-Posteriori (MAP) energy that is subsequently minimized with a dual hierarchical max-flow computation. The algorithm makes use of a hierarchical label ordering constraint to regularize label families individually and its inherently globally optimal results guarantee robust segmentations. Major parts of the image processing pipeline are implemented using General-Purpose Programming on Graphics Processing Units (GPGPU) for a substantial increase in computation speed.

Multi-Atlas-based Segmentation with Hierarchical Max-Flow

 A fully automatic brain segmentation method is presented. First the skull is stripped using a model-based level set on T1-weighted inversion recovery images, then the brain ventricles and basal ganglia are segmented using the same method on T1-weighted images. The central white matter is segmented using a regular level set method but with high curvature regulation. To segment the cortical gray matter, a skeleton-based model is created by extracting the mid-surface of the gray matter from a preliminary segmentation using a threshold-based level set. An implicit model is then built by defining the thickness of the gray matter to be 2.7 mm. This model is incorporated into the level set framework and used to guide a second round more precise segmentation. Preliminary experiments show that the proposed method can provide relatively accurate results compared with the segmentation done by human observers. The processing time is considerably shorter than most conventional automatic brain segmentation methods. 

Fully automatic brain segmentation using model-guided level sets and skeleton-based models

We propose a new MAP-based technique for the unsupervised segmentation of different brain structures (white matter, gray matter, etc.) from T1-weighted MR brain images. In this paper, we follow a procedure like most conventional approaches, in which T1-weighted MR brain images and desired maps of regions (white matter, gray matter, etc.) are modeled by a joint Markov-Gibbs Random Field model (MGRF) of independent image signals and interdependent region labels. However, we specifically focus on the most accurate model identification that can be achieved. The proposed joint MGRF model accounts for the following three descriptors: i) a 1st-order visual appearance descriptor(empirical distribution of signal intensity), ii) a 3D probabilistic shape prior, and iii) a 3D spatially invariant 2nd-order homogeneity descriptor. To better specify the 1st-order visual appearance descriptor, each empirical distribution of signals is precisely approximated by a Linear Combination of Discrete Gaussians (LCDG) having both positive and negative components. The 3D probabilistic shape prior is learned using a subset of 3D co-aligned training T1-weighted MR brain images. The 2nd-order homogeneity descriptor is modeled by a 2nd-order translation and rotation invariant MGRF of 3D T1-weighted MR brain region labels with analytically estimated potentials. The initial segmentation, based on a 1st-order visual appearance and 3D probabilistic shape, is then iteratively refined using a 3D MGRF model with analytically estimated potentials. Experiments on twelve 3D T1-weighted MR brain images confirm the high accuracy of the proposed approach.

MAP–Based Framework for Segmentation of MR Brain Images Based on Visual Appearance and Prior Shape

Segmentation of the human cerebrum from magnetic resonance images (MRI) into its component tissues has been a defining problem in medical imaging. Until recently, this has been solved as the tissue classification of the T1-weighted (T1-w) MRI, with numerous solutions for this problem having appeared in the literature. The clinical demands of understanding lesions, which are indistinguishable from gray matter in T1-w images, has necessitated the incorporation of T2-weighted Fluid Attenuated Inversion Recovery (FLAIR) images to improve segmentation of the cerebrum. Many of the existing methods fail to handle the second data channel gracefully, because of assumptions about their model. In our new approach, we explore a model free algorithm which uses a classification technique based on ensembles of decision trees to learn the mapping from an image feature to the corresponding tissue label. We use corresponding image patches from a registered set of T1-w and FLAIR images with a manual segmentation to construct our decision
tree ensembles. Our method is efficient, taking less than two minutes on a 240x240x48 volume. We conduct experiments on five training sets in a leave-one-out fashion, as well as validation on an additional twelve subjects, and a landmark validation experiment on another cohort of five
subjects.

MR Brain Segmentation using Decision Trees

This work presents an automatic brain MRI segmentation method which can classify brain voxels into one of three main tissue types: gray matter (GM), white matter (WM) and Cerebro-spinal Fluid (CSF). Intensity-model based classification of MR images has proven problematic. The statistical approach does not carry any spatial, textural and neighborhood information in it. We propose to use a computationally fast and novel feature-set to facilitate voxel wise classification based on regional intensity, texture, spatial location of voxels in addition to posterior probability estimates. Information available through T1-weighted (T1), T1-weighted inversion recovery (IR) and T2-weighted FLAIR (FLAIR) MRI sequences was also leveraged. An aggregate overlap of 90.21% for all intracranial structures was reported between the automatic classification and available expert annotation as measured by the DICE coefficient.

Gaussian Intensity Model with Neighborhood Cues for Fluid-Tissue Categorization of Multi-Sequence MR Brain Images

We present a method for automated brain-tissue segmentation through voxelwise classification. Our algorithm uses manually labeled training images to train a support vector machine (SVM) classifier, which is then used for the segmentation of target images. The classification incorporates voxel intensities from a T1-weighted scan, an IR scan, and a FLAIR scan; features to encode the voxel position in the image; and Gaussian-scale-space features and Gaussian-derivative features at
multiple scales to facilitate a smooth segmentation.
An experiment on data from the MRBrainS13 brain-tissue-segmentation challenge showed that our algorithm produces reasonable segmentations in a reasonable amount of time.