V–Bundles: Clustering Fiber Trajectories from Diffusion MRI in Linear Time

Reichenbach, A.; Goldau, Mathias; Heine, Christian; Hlawitschka, Mario

doi:10.1007/978-3-319-24553-9_24

Cited by 7 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The unsupervised approach, usually called fiber clustering , is one of the most widely used tractogram segmentation technique in the literature (Shimony et al, 2002 ; Garyfallidis et al, 2012 ; Tunç et al, 2014 ; Reichenbach et al, 2015 ). The purpose of clustering is to group the streamlines according to their mutual geometrical similarity (or distance).…”

Section: Introductionmentioning

confidence: 99%

White Matter Tract Segmentation as Multiple Linear Assignment Problems

2018

View full text Add to dashboard Cite

Diffusion magnetic resonance imaging (dMRI) allows to reconstruct the main pathways of axons within the white matter of the brain as a set of polylines, called streamlines. The set of streamlines of the whole brain is called the tractogram. Organizing tractograms into anatomically meaningful structures, called tracts, is known as the tract segmentation problem, with important applications to neurosurgical planning and tractometry. Automatic tract segmentation techniques can be unsupervised or supervised. A common criticism of unsupervised methods, like clustering, is that there is no guarantee to obtain anatomically meaningful tracts. In this work, we focus on supervised tract segmentation, which is driven by prior knowledge from anatomical atlases or from examples, i.e., segmented tracts from different subjects. We present a supervised tract segmentation method that segments a given tract of interest in the tractogram of a new subject using multiple examples as prior information. Our proposed tract segmentation method is based on the idea of streamline correspondence i.e., on finding corresponding streamlines across different tractograms. In the literature, streamline correspondence has been addressed with the nearest neighbor (NN) strategy. Differently, here we formulate the problem of streamline correspondence as a linear assignment problem (LAP), which is a cornerstone of combinatorial optimization. With respect to the NN, the LAP introduces a constraint of one-to-one correspondence between streamlines, that forces the correspondences to follow the local anatomical differences between the example and the target tract, neglected by the NN. In the proposed solution, we combined the Jonker-Volgenant algorithm (LAPJV) for solving the LAP together with an efficient way of computing the nearest neighbors of a streamline, which massively reduces the total amount of computations needed to segment a tract. Moreover, we propose a ranking strategy to merge correspondences coming from different examples. We validate the proposed method on tractograms generated from the human connectome project (HCP) dataset and compare the segmentations with the NN method and the ROI-based method. The results show that LAP-based segmentation is vastly more accurate than ROI-based segmentation and substantially more accurate than the NN strategy. We provide a Free/OpenSource implementation of the proposed method.

show abstract

Section: Introductionmentioning

confidence: 99%

White Matter Tract Segmentation as Multiple Linear Assignment Problems

2018

View full text Add to dashboard Cite

show abstract

“…QBX is an advanced, unsupervised machine learning algorithm that substantially improves over its predecessor QuickBundles (QB) (Garyfallidis et al, 2012). QuickBundles is one of the most efficient algorithms for clustering streamlines using streamline distances (Reichenbach et al, 2015), with a complexity of O(kN ). k is the number of clusters, and N is the number of streamlines.…”

Section: Accessing Advanced Machine Learning Data Structuresmentioning

confidence: 99%

Horizon, closing the gap between cinematic visualization and medical imaging

Guerra

Koudoro

Garyfallidis

2023

Preprint

View full text Add to dashboard Cite

Medical imaging has become a fascinating field with detailed visualizations of the body's internal environments. Although the field has grown fast and is sensitive to new technologies, it does not use the latest rendering techniques available in other domains, such as day-to-day movie production or game development. In this work, we bring forward Horizon, a new engine that provides cinematic rendering capabilities in real-time for quality controlling medical data. In addition, Horizon is provided as free, open-source software to be used as a foundation stone for building the next generation of medical imaging applications. In this introductory paper, we focus on the extensive development of advanced shaders, which can be used to highlight untapped features of the data and allow fast interaction with machine learning algorithms. In addition, Horizon provides physically-based rendering capabilities, the epitome of advanced visualization, adapted for the needs of medical imaging analysis practices.

show abstract

“…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. Reichenbach et al [5] came up with the V-Bundles clustering which is linear in the number of line segments in the fiber data and can cluster large datasets without the use of random sampling or complex multi-pass procedures. It copes with interrupted streamlines and allows multi-subject comparisons.…”

Section: Introductionmentioning

confidence: 99%

“…Metrics under evaluation and their characteristicMetricCharacteristics Undirected Euclidean (EUC)[5]: Fast to compute -O(k)  Assumes both fibers have k points  Hence, 2 similar & close fibers, where one is shorter (i.e due to faulty tractography), will automatically be far from each other Minimum average Direct-Flip (MDF) [3]:  Fast to compute -O(k)  Assumes both fibers have k points  Penalizes distance between curves of different lengths (corresponding points may not be close to each other).…”

mentioning

confidence: 99%

Coresets vs clustering: comparison of methods for redundancy reduction in very large white matter fiber sets

et al. 2016

View full text Add to dashboard Cite

Recent advances in Diffusion Weighted Magnetic Resonance Imaging (DW-MRI) of white matter in conjunction with improved tractography produce impressive reconstructions of White Matter (WM) pathways. These pathways (fiber sets) often contain hundreds of thousands of fibers, or more. In order to make fiber based analysis more practical, the fiber set needs to be preprocessed to eliminate redundancies and to keep only essential representative fibers. In this paper we demonstrate and compare two distinctive frameworks for selecting this reduced set of fibers. The first framework entails pre-clustering the fibers using k-means, followed by Hierarchical Clustering and replacing each cluster with one representative. For the second clustering stage seven distance metrics were evaluated. The second framework is based on an efficient geometric approximation paradigm named coresets. Coresets present a new approach to optimization and have huge success especially in tasks requiring large computation time and/or memory. We propose a modified version of the coresets algorithm, Density Coreset. It is used for extracting the main fibers from dense datasets, leaving a small set that represents the main structures and connectivity of the brain. A novel approach, based on a 3D indicator structure, is used for comparing the frameworks. This comparison was applied to High Angular Resolution Diffusion Imaging (HARDI) scans of 4 healthy individuals. We show that among the clustering based methods, that cosine distance gives the best performance. In comparing the clustering schemes with coresets, Density Coreset method achieves the best performance.

show abstract

V–Bundles: Clustering Fiber Trajectories from Diffusion MRI in Linear Time

Cited by 7 publications

References 8 publications

White Matter Tract Segmentation as Multiple Linear Assignment Problems

White Matter Tract Segmentation as Multiple Linear Assignment Problems

Horizon, closing the gap between cinematic visualization and medical imaging

Coresets vs clustering: comparison of methods for redundancy reduction in very large white matter fiber sets

Contact Info

Product

Resources

About