VascuSynth: Vascular Tree Synthesis Software

Jassi, Preet; Hamarneh, Ghassan

doi:10.54294/j0ws9u

Cited by 22 publications

(12 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In both datasets, we use the first segmentation as the ground truth. For the noise sensitivity experiment, we use the VascuSynth dataset [8], which is a simulated 3D dataset. It consists of simulated volumetric images of vascular trees with the corresponding groundtruth segmentations.…”

Section: Methodsmentioning

confidence: 99%

Self-Supervised Vessel Enhancement Using Flow-Based Consistencies

Jena¹,

Singla²,

Batmanghelich³

2021

Preprint

View full text Add to dashboard Cite

Vessel segmenting is an essential task in many clinical applications. Although supervised methods have achieved state-of-art performance, acquiring expert annotation is laborious and mostly limited for two-dimensional datasets with a small sample size. On the contrary, unsupervised methods rely on handcrafted features to detect tubelike structures such as vessels. However, those methods require complex pipelines involving several hyper-parameters and design choices rendering the procedure sensitive, dataset-specific, and not generalizable. Also, unsupervised methods usually underperform supervised methods. We propose a self-supervised method with a limited number of hyperparameters that is generalizable. Our method uses tube-like structure properties, such as connectivity, profile consistency, and bifurcation, to introduce inductive bias into a learning algorithm. To model those properties, we generate a vector field that we refer to as a flow. Our experiments on various datasets in 2D and 3D show that our method reduces the gap between supervised and unsupervised methods. Unlike generic self-supervised methods, the learned features are transferable for supervised approaches, which is essential when the number of annotated data is limited.

show abstract

Section: Methodsmentioning

confidence: 99%

Self-Supervised Vessel Enhancement Using Flow-Based Consistencies

Jena¹,

Singla²,

Batmanghelich³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…In order to demonstrate the usefulness and applicability of the proposed framework, we modify and extend the Vas-cuSynth test data generation software [12] to support efficient generation of larger-than-main memory volumes. The VascuSynth pipeline can be seen as two stages: (1) Vessel tree generation and (2) vessel image generation (cf.…”

Section: Case Study: Extension Of Vascusynth To Large Image Datamentioning

confidence: 99%

“…VascuSynth [9] is a popular tool (see [15], [16], [20], [36], [39]) for synthesis of arterial vessel trees, corresponding noisy volume data and segmentation based on oxygen demand maps. The software implementation [12], however, does not support out-of-core volume generation since it operates completely in memory. VascuSynth was also used as the basis for the generation of pulmonary CT phantoms [13].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Streaming Volumetric Image Generation Framework for Development and Evaluation of Out-of-Core Methods

Drees¹,

Jiang²

2021

Preprint

View full text Add to dashboard Cite

“…Vascusynth The Vascusynth dataset from [16,20] is composed of 120 unordered trees that represent blood vasculatures with different bifurcations numbers. In a tree, each vertex has a continuous label describing the radius r of the corresponding vessel.…”

Section: Biological Datasetsmentioning

confidence: 99%

The Weight Function in the Subtree Kernel is Decisive

Azaïs,

Ingels

2019

Preprint

View full text Add to dashboard Cite

Tree data are ubiquitous because they model a large variety of situations, e.g., the architecture of plants, the secondary structure of RNA, or the hierarchy of XML files. Nevertheless, the analysis of these non-Euclidean data is difficult per se. In this paper, we focus on the subtree kernel that is a convolution kernel for tree data introduced by Vishwanathan and Smola in the early 2000's. More precisely, we investigate the influence of the weight function from a theoretical perspective and in real data applications. We establish on a 2-classes stochastic model that the performance of the subtree kernel is improved when the weight of leaves vanishes, which motivates the definition of a new weight function, learned from the data and not fixed by the user as usually done. To this end, we define a unified framework for computing the subtree kernel from ordered or unordered trees, that is particularly suitable for tuning parameters. We show through eight real data classification problems the great efficiency of our approach, in particular for small datasets, which also states the high importance of the weight function. Finally, a visualization tool of the significant features is derived.

show abstract

VascuSynth: Vascular Tree Synthesis Software

Cited by 22 publications

References 3 publications

Self-Supervised Vessel Enhancement Using Flow-Based Consistencies

Self-Supervised Vessel Enhancement Using Flow-Based Consistencies

A Streaming Volumetric Image Generation Framework for Development and Evaluation of Out-of-Core Methods

The Weight Function in the Subtree Kernel is Decisive

Contact Info

Product

Resources

About