Evaluation of center-line extraction algorithms in quantitative coronary angiography

Greenspan, Hayit; Laifenfeld, Moshe; Einav, Shmuel; Barnea, Ofer

doi:10.1109/42.952730

Cited by 49 publications

(26 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Analysis on the vessel level includes tasks such as segmentation of blood vessel regions [1], [2], [3] and vessel center extraction [4], [5]. Analysis and tracking of circulating cells/particles includes the detection and/or tracking of leukocytes (white cells) [6], [7], [8], [9], [1], [10] and erythrocytes (red blood cells) [11].…”

Section: A Backgroundmentioning

confidence: 99%

See 1 more Smart Citation

An automated method for analysis of flow characteristics of circulating particles from in vivo video microscopy

Eden

Waisman²,

Rudzsky³

et al. 2005

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

The behavior of white and red blood cells, platelets and circulating injected particles is one of the main focuses in physiological studies. Most methods used to analyze the circulatory patterns of cells are time consuming. We describe a system named CellTrack, designed for a fully automated tracking of circulating cells and micro-particles and retrieval of their behavioral characteristics.The task of automated blood cell tracking in vessels from in-vivo video is particularly challenging because of the blood cells' non-rigid shapes, the instability inherent in in-vivo videos, the abundance of moving objects and their frequent superposition.To tackle this, the CellTrack system operates on two levels: first, a global processing module extracts vessel borders and center lines based on color and temporal patterns. This enables the computation of the approximate direction of the blood flow in each vessel. Second, a local processing module extracts the locations and velocities of circulating cells. This is performed by artificial neural network classifiers that are designed to detect specific types of blood cells and micro-particles. The motion correspondence problem is then resolved by a novel algorithm that incorporates both the local and the global information. The system has been tested on a series of in-vivo color video recordings of rat mesentery. Our results show that the synergy between the global and local information enables CellTrack to overcome many of the difficulties inherent in tracking methods that rely solely on local information. A comparison was made between manual measurements and the automatically extracted measurements of leukocytes and fluorescent microspheres circulatory velocities. This comparison revealed an accuracy of 97%. CellTrack also enabled a much larger volume of sampling in a fraction of time compared to the manual measurements. All these results suggest that our method can in fact constitute a reliable replacement for manual extraction of blood flow characteristics from in-vivo videos.

show abstract

Section: A Backgroundmentioning

confidence: 99%

“…As a pre-processing step the vessel center-line is extracted. A good review on vessel center-line extraction is given in [4]. After testing several approaches we found that the skeleton algorithms proposed in [5], [30] are simple for implementation and yield robust and accurate results (see Fig.…”

Section: 'Virtual Flow' Computationmentioning

confidence: 99%

An automated method for analysis of flow characteristics of circulating particles from in vivo video microscopy

Eden

Waisman²,

Rudzsky³

et al. 2005

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

show abstract

“…Traditionally, digital subtraction angiography (DSA) projection images have been the gold standard for stenosis grading. The shortcomings of visual assessment of these types of images have motivated the development of automated techniques to support vessel analysis [1,2], which has resulted in programs such as quantitative coronary angiography (QCA) [3]. Nowadays, the required image data for diagnostic purposes regarding vessels is increasingly acquired using techniques such as magnetic resonance angiography (MRA) and computed tomography angiography (CTA) [4,5], which are minimally invasive and yield three-dimensional (3D) image data.…”

Section: Introductionmentioning

confidence: 99%

Evaluation of an improved technique for automated center lumen line definition in cardiovascular image data

et al. 2005

View full text Add to dashboard Cite

The aim of the study was to evaluate a new method for automated definition of a center lumen line in vessels in cardiovascular image data. This method, called VAMPIRE, is based on improved detection of vessel-like structures. A multiobserver evaluation study was conducted involving 40 tracings in clinical CTA data of carotid arteries to compare VAMPIRE with an established technique. This comparison showed that VAMPIRE yields considerably more successful tracings and improved handling of stenosis, calcifications, multiple vessels, and nearby bone structures. We conclude that VAMPIRE is highly suitable for automated definition of center lumen lines in vessels in cardiovascular image data.

show abstract

“…However, 3D central lines on surfaces in paleontological context, especially for fossil oysters using photogrammetric technology, are not yet reported in the literature. Our algorithm is similar to the algorithms that use Delaunay (1934) triangulation andVoronoi (1908) The terms central line, skeleton and medial axis are used often in literature to describe related things (Greenspan et al, 2001;Palagyi et al, 2001). The terms central line and medial axis appear most often concerning thinning of the object on the surface such as road (Doucette et al, 2004).…”

Section: Related Workmentioning

confidence: 99%

3d Central Line Extraction of Fossil Oyster Shells

Djuricic¹,

Puttonen²,

Harzhauser³

et al. 2016

ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci.

View full text Add to dashboard Cite

ABSTRACT:Photogrammetry provides a powerful tool to digitally document protected, inaccessible, and rare fossils. This saves manpower in relation to current documentation practice and makes the fragile specimens more available for paleontological analysis and public education. In this study, high resolution orthophoto (0.5 mm) and digital surface models (1 mm) are used to define fossil boundaries that are then used as an input to automatically extract fossil length information via central lines. In general, central lines are widely used in geosciences as they ease observation, monitoring and evaluation of object dimensions. Here, the 3D central lines are used in a novel paleontological context to study fossilized oyster shells with photogrammetric and LiDAR-obtained 3D point cloud data. 3D central lines of 1121 Crassostrea gryphoides oysters of various shapes and sizes were computed in the study. Central line calculation included: i) Delaunay triangulation between the fossil shell boundary points and formation of the Voronoi diagram; ii) extraction of Voronoi vertices and construction of a connected graph tree from them; iii) reduction of the graph to the longest possible central line via Dijkstra's algorithm; iv) extension of longest central line to the shell boundary and smoothing by an adjustment of cubic spline curve; and v) integration of the central line into the corresponding 3D point cloud. The resulting longest path estimate for the 3D central line is a size parameter that can be applied in oyster shell age determination both in paleontological and biological applications. Our investigation evaluates ability and performance of the central line method to measure shell sizes accurately by comparing automatically extracted central lines with manually collected reference data used in paleontological analysis. Our results show that the automatically obtained central line length overestimated the manually collected reference by 1.5% in the test set, which is deemed sufficient for the selected paleontological application, namely shell age determination.

show abstract

Evaluation of center-line extraction algorithms in quantitative coronary angiography

Cited by 49 publications

References 22 publications

An automated method for analysis of flow characteristics of circulating particles from in vivo video microscopy

An automated method for analysis of flow characteristics of circulating particles from in vivo video microscopy

Evaluation of an improved technique for automated center lumen line definition in cardiovascular image data

3d Central Line Extraction of Fossil Oyster Shells

Contact Info

Product

Resources

About