Abhir Bhalerao

Tissue classification based on 3D local intensity structures for volume rendering

This paper describes a novel approach to tissue classification using three-dimensional (3D) derivative features in the volume rendering pipeline. In conventional tissue classification for a scalar volume, tissues of interest are characterized by an opacity transfer function defined as a one-dimensional (1D) function of the original volume intensity. To overcome the limitations inherent in conventional 1D opacity functions, we propose a tissue classification method that employs a multidimensional opacity function, which is a function of the 3D derivative features calculated from a scalar volume as well as the volume intensity. Tissues of interest are characterized by explicitly defined classification rules based on 3D filter responses highlighting local structures, such as edge, sheet, line, and blob, which typically correspond to tissue boundaries, cortices, vessels, and nodules, respectively, in medical volume data. The 3D local structure filters are formulated using the gradient vector and Hessian matrix of the volume intensity function combined with isotropic Gaussian blurring. These filter responses and the original intensity define a multidimensional feature space in which multichannel tissue classification strategies are designed. The usefulness of the proposed method is demonstrated by comparisons with conventional single-channel classification using both synthesized data and clinical data acquired with CT (computed tomography) and MRI (magnetic resonance imaging) scanners. The improvement in image quality obtained using multichannel classification is confirmed by evaluating the contrast and contrast-to-noise ratio in the resultant volume-rendered images with variable opacity values.

Analysis of Retinal Vasculature Using a Multiresolution Hermite Model

This paper presents a vascular representation and segmentation algorithm based on a multiresolution Hermite model (MHM). A two-dimensional Hermite function intensity model is developed which models blood vessel profiles in a quad-tree structure over a range of spatial resolutions. The use of a multiresolution representation simplifies the image modeling and allows for a robust analysis by combining information across scales. Estimation over scale also reduces the overall computational complexity. As well as using MHM for vessel labelling, the local image modeling can accurately represent vessel directions, widths, amplitudes, and branch points which readily enable the global topology to be inferred. An expectation-maximization (EM) type of optimization scheme is used to estimate local model parameters and an information theoretic test is then applied to select the most appropriate scale/feature model for each region of the image. In the final stage, Bayesian stochastic inference is employed for linking the local features to obtain a description of the global vascular structure. After a detailed description and analysis of MHM, experimental results on two standard retinal databases are given that demonstrate its comparative performance. These show MHM to perform comparably with other retinal vessel labelling methods

Computer-assisted Surgical Planning for Cerebrovascular Neurosurgery

OBJECTIVE We used three-dimensional reconstructed magnetic resonance images for planning the operations of 16 patients with various cerebrovascular diseases. We studied the cases of these patients to determine the advantages and current limitations of our computer-assisted surgical planning system as it applies to the treatment of vascular lesions. METHODS Magnetic resonance angiograms or thin slice gradient echo magnetic resonance images were processed for three-dimensional reconstruction. The segmentation, based on the signal intensities and voxel connectivity, separated each anatomic structure of interest, such as the brain, vessels, and skin. A three-dimensional model was then reconstructed by surface rendering. This three-dimensional model could be colored, made translucent, and interactively rotated by a mouse-controlled cursor on a workstation display. In addition, a three-dimensional blood flow analysis was performed, if necessary. The three-dimensional model was used to assist in three stages of surgical planning, as follows: 1) to choose the best method of intervention, 2) to evaluate surgical risk, 3) to select a surgical approach, and 4) to localize lesions. RESULTS The generation of three-dimensional models allows visualization of pathological anatomy and its relationship to adjacent normal structures, accurate lesion volume determination, and preoperative computer-assisted visualization of alternative surgical approaches. CONCLUSION Computer-assisted surgical planning is useful for patients with cerebrovascular disease at various stages of treatment. Lesion identification, therapeutic and surgical option planning, and intraoperative localization are all enhanced with these techniques.

The Bhattacharyya space for feature selection and its application to texture segmentation

A feature selection methodology based on a novel Bhattacharyya space is presented and illustrated with a texture segmentation problem. The Bhattacharyya space is constructed from the Bhattacharyya distances of different measurements extracted with sub-band filters from training samples. The marginal distributions of the Bhattacharyya space present a sequence of the most discriminant sub-bands that can be used as a path for a wrapper algorithm. When this feature selection is used with a multiresolution classification algorithm on a standard set of texture mosaics, it produces the lowest misclassification errors reported.

Towards electronically assisted peer assessment: a case study

One of the primary goals of formative assessment is to give informative feedback to the learner on their progress and attainment of the learning objectives. However, when the student/tutor ratios are large, effective and timely feedback is hard to achieve. Many testing systems have been developed that use multiple choice questions (MCQ), which are easy to mark automatically. MCQ tests are simple to develop and administer through Web-based technologies (browsers, Internet and Web servers). One of the principal drawbacks of current systems is that the testing format is limited to MCQ and general questions requiring free responses are not included because marking cannot be easily automated. Consequently, many learning tasks, such as the correctness and style of solutions to programming problems, cannot be assessed automatically. Our approach is a hybrid system combining MCQ testing with free response questions. Our system, OASYS, marks MCQs automatically and then controls the anonymous distribution of completed scripts amongst learners for peer assessment of free response answers. We briefly describe the design and implementation of OASYS, which is built on freely available technologies. We present and discuss findings from a case study which used OASYS for 240 students taking a programming class involving four assessed programming laboratories in groups of approximately forty students

Using local 3D structure for segmentation of bone from computer tomography images

In this paper we focus on using local 3D structure for segmentation. A tensor descriptor is estimated for each neighbourhood, i.e. for each voxel in the data set. The tensors are created from a combination of the outputs form a set of 3D quadrature filters. The shape of the tensors describe locally the structure of the neighbourhood in terms of how much it is like a plane, a line, and a sphere. We apply this to segmentation of bone from Computer Tomography data (CT). Traditional methods are based purely on gray-level value discrimination and have difficulties in recovering thin bone structures due to so called partial voluming, a problem which is present in all such sampled data. We illuminate the partial voluming problem by showing that thresholding creates complicated artifacts even if the signal is densely enough sampled and can be perfectly reconstructed. The unwanted effects of thresholding can be reduced by a change of the signal basis. We show that by using additional local structure information can significantly reduce the degree of sampling artifacts. Evaluation of the method on a clinical case is presented, the segmentation of a human skull from a CT volume. The method shows that many of the thin bone structures which disappear in a pure thresholding can be recovered.

Kernel designs for efficient multiresolution edge detection and orientation estimation

Deals with the design of filter kernels having specified radial and angular frequency responses based on combined optimization and frequency sampling. This is used to generate small-radius, low-pass, and edge-detection kernels for multiresolution pyramids. The performance of the new kernels in estimating orientation is shown to be significantly better than that of other commonly used pyramid kernels. >

Volumetric Texture Segmentation by Discriminant Feature Selection and Multiresolution Classification

In this paper, a multiresolution volumetric texture segmentation (M-VTS) algorithm is presented. The method extracts textural measurements from the Fourier domain of the data via subband filtering using an orientation pyramid (Wilson and Spann, 1988). A novel Bhattacharyya space, based on the Bhattacharyya distance, is proposed for selecting the most discriminant measurements and producing a compact feature space. An oct tree is built of the multivariate features space and a chosen level at a lower spatial resolution is first classified. The classified voxel labels are then projected to lower levels of the tree where a boundary refinement procedure is performed with a three-dimensional (3-D) equivalent of butterfly filters. The algorithm was tested with 3-D artificial data and three magnetic resonance imaging sets of human knees with encouraging results. The regions segmented from the knees correspond to anatomical structures that can be used as a starting point for other measurements such as cartilage extraction

Tensor Controlled Local Structure Enhancement of CT Images for Bone Segmentation

This paper addresses the problem of segmenting bone from Computed Tomography (CT) data. In clinical practice, identification of bone is done by thresholding, a method which is simple and fast. Unfortunately, thresholding alone has significant limitations. In particular, segmentation of thin bone structures and of joint spaces is problematic. This problem is particularly severe for thin bones such as in the skull (the paranasal sinus and around the orbit). Another area where current techniques often fail is automatic, reliable and robust identification of individual bones, which requires precise separation of the joint spaces. This paper presents a novel solution to these problems based on three-dimensional filtering techniques. Improvement of the segmentation results in more accurate 3D models for the purpose of surgical planning and intraoperative navigation.

Unsupervised Image Segmentation Combining Region and Boundary Estimation

An integrated approach to image segmentation is presented that combines region and boundary information using maximum a posteriori estimation and decision theory. The algorithm employs iterative, decision-directed estimation performed on a novel multiresolution representation. The use of a multiresolution technique ensures both robustness in noise and efficiency of computation, while the model-based estimation and decision process is flexible and spatially local, thus avoiding assumptions about global homogeneity or size and number of regions. A comparative evaluation of the method against region-only and boundary-only methods is presented and is shown to produce accurate segmentations at quite low signal-to-noise ratios.