B. Moberts

Bio: B. Moberts is an academic researcher. The author has contributed to research in topics: Similarity measure & Cluster analysis. The author has an hindex of 1, co-authored 2 publications receiving 188 citations.

Evaluation of fiber clustering methods for diffusion tensor imaging

Abstract: Fiber tracking is a standard approach for the visualization of the results of diffusion tensor imaging (DTI). If fibers are reconstructed and visualized individually through the complete white matter, the display gets easily cluttered making it difficult to get insight in the data. Various clustering techniques have been proposed to automatically obtain bundles that should represent anatomical structures, but it is unclear which clustering methods and parameter settings give the best results. We propose a framework to validate clustering methods for white-matter fibers. Clusters are compared with a manual classification which is used as a ground truth. For the quantitative evaluation of the methods, we developed a new measure to assess the difference between the ground truth and the clusterings. The measure was validated and calibrated by presenting different clusterings to physicians and asking them for their judgement. We found that the values of our new measure for different clusterings match well with the opinions of physicians. Using this framework, we have evaluated different clustering algorithms, including shared nearest neighbor clustering, which has not been used before for this purpose. We found that the use of hierarchical clustering using single-link and a fiber similarity measure based on the mean distance between fibers gave the best results.

Evaluation of white matter fiber clustering methods for diffusion tensor imaging

Abstract: Fiber tracking is a standard approach for the visualization of the results of Diffusion Tensor Imaging (DTI). Individual fibers are reconstructed from the tensor information by tracing streamlines. Usually fibers are defined by manually setting seed points. In this case, the result is biased by the user and therefore not easily reproducible. Some methods propose to seed through the whole volume to avoid manual seeding. However, white matter is a complex structure and the image gets easily cluttered. This makes it difficult to see meaningful structures. Fibers form anatomically entities called bundles. Several authors have proposed to use clustering techniques for fibers, such that the enormous amount of individual fibers is reduced to a limited number of logical fiber clusters that are more manageable and understandable. Clustering might also be used to explore and obtain quantitative comparisons by unbiased measurements in anatomically structures. Different clustering algorithms and different options within a clustering algorithm (e.g., similarity measure between fibers) can be chosen. Furthermore, clustering algorithms have parameters to tune such as the amount of clusters to obtain. It is not clear which method or distance measure produces the best results. Many combinations exist and therefore it is also not viable that physicians evaluate all possible combinations. We present the results of the evaluation of different similarity measures and clustering techniques using the framework presented by Moberts et al

Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool

Abstract: Medical Image segmentation is an important image processing step. Comparing images to evaluate the quality of segmentation is an essential part of measuring progress in this research area. Some of the challenges in evaluating medical segmentation are: metric selection, the use in the literature of multiple definitions for certain metrics, inefficiency of the metric calculation implementations leading to difficulties with large volumes, and lack of support for fuzzy segmentation by existing metrics. First we present an overview of 20 evaluation metrics selected based on a comprehensive literature review. For fuzzy segmentation, which shows the level of membership of each voxel to multiple classes, fuzzy definitions of all metrics are provided. We present a discussion about metric properties to provide a guide for selecting evaluation metrics. Finally, we propose an efficient evaluation tool implementing the 20 selected metrics. The tool is optimized to perform efficiently in terms of speed and required memory, also if the image size is extremely large as in the case of whole body MRI or CT volume segmentation. An implementation of this tool is available as an open source project. We propose an efficient evaluation tool for 3D medical image segmentation using 20 evaluation metrics and provide guidelines for selecting a subset of these metrics that is suitable for the data and the segmentation task.

Automatic Tractography Segmentation Using a High-Dimensional White Matter Atlas

Abstract: We propose a new white matter atlas creation method that learns a model of the common white matter structures present in a group of subjects. We demonstrate that our atlas creation method, which is based on group spectral clustering of tractography, discovers structures corresponding to expected white matter anatomy such as the corpus callosum, uncinate fasciculus, cingulum bundles, arcuate fasciculus, and corona radiata. The white matter clusters are augmented with expert anatomical labels and stored in a new type of atlas that we call a high-dimensional white matter atlas. We then show how to perform automatic segmentation of tractography from novel subjects by extending the spectral clustering solution, stored in the atlas, using the Nystrom method. We present results regarding the stability of our method and parameter choices. Finally we give results from an atlas creation and automatic segmentation experiment. We demonstrate that our automatic tractography segmentation identifies corresponding white matter regions across hemispheres and across subjects, enabling group comparison of white matter anatomy.

QuickBundles, a Method for Tractography Simplification

Abstract: Diffusion MR data sets produce large numbers of streamlines which are hard to visualize, interact with, and interpret in a clinically acceptable time scale, despite numerous proposed approaches. As a solution we present a simple, compact, tailor-made clustering algorithm, QuickBundles (QB), that overcomes the complexity of these large data sets and provides informative clusters in seconds. Each QB cluster can be represented by a single centroid streamline; collectively these centroid streamlines can be taken as an effective representation of the tractography. We provide a number of tests to show how the QB reduction has good consistency and robustness. We show how the QB reduction can help in the search for similarities across several subjects.

Visualization in Medicine: Theory, Algorithms, and Applications

Abstract: Visualization in Medicine is the first book on visualization and its application to problems in medical diagnosis, education, and treatment. The book describes the algorithms, the applications and their validation (how reliable are the results?), and the clinical evaluation of the applications (are the techniques useful?). It discusses visualization techniques from research literature as well as the compromises required to solve practical clinical problems. The book covers image acquisition, image analysis, and interaction techniques designed to explore and analyze the data. The final chapter shows how visualization is used for planning liver surgery, one of the most demanding surgical disciplines. The book is based on several years of the authors' teaching and research experience. Both authors have initiated and lead a variety of interdisciplinary projects involving computer scientists and medical doctors, primarily radiologists and surgeons. * A core field of visualization and graphics missing a dedicated book until now * Written by pioneers in the field and illustrated in full color * Covers theory as well as practice