Coronary Centerline Extraction Using Multiple Hypothesis Tracking and Minimal Paths

Friman, Ola; Kuehnel, C.; Peitgen, Heinz‐Otto

doi:10.54294/euk5y1

Cited by 17 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A multiple hypothesis tracking approach based on a mathematical template vessel model combined with standard minimal paths method was used by [7] to extract coronary artery centerlines. Standard minimal path-based methods experience shortcut issues and may require a lot of interaction to extract the entire vessel tree.…”

Section: A State Of the Artmentioning

confidence: 99%

“…Standard minimal path-based methods experience shortcut issues and may require a lot of interaction to extract the entire vessel tree. At the time of this publication, [7]'s method ranked first on MICCAI 2008 Coronary Artery Centerline Extraction Challenge (CAT08) as an interactive method. It requires 2.6 points on average per vessel and takes 6 min to extract four coronary arteries per CCTA image.…”

Section: A State Of the Artmentioning

confidence: 99%

See 1 more Smart Citation

Multi-Resolution 3D Convolutional Neural Networks for Automatic Coronary Centerline Extraction in Cardiac CT Angiography Scans

Salahuddin¹,

Lenga²,

Nickisch³

2020

Preprint

View full text Add to dashboard Cite

We propose a deep learning-based automatic coronary artery tree centerline tracker (AuCoTrack) extending the vessel tracker by [23]. A dual pathway Convolutional Neural Network (CNN) operating on multi-scale 3D inputs predicts the direction of the coronary arteries as well as the presence of a bifurcation. A similar multi-scale dual pathway 3D CNN is trained to identify coronary artery endpoints for terminating the tracking process. Two or more continuation directions are derived based on the bifurcation detection. The iterative tracker detects the entire left and right coronary artery trees based on only two ostium landmarks derived from a model-based segmentation of the heart [4]. The 3D CNNs were trained on a proprietary dataset consisting of 43 CCTA scans. An average sensitivity of 87.1% and clinically relevant overlap of 89.1% was obtained relative to a refined manual segmentation. In addition, the MICCAI 2008 Coronary Artery Tracking Challenge (CAT08) training and test datasets were used to benchmark the algorithm and to assess its generalization. An average overlap of 93.6% and a clinically relevant overlap of 96.4% were obtained. The proposed method achieved better overlap scores than the current state-of-the-art automatic centerline extraction techniques on the CAT08 dataset with a vessel detection rate of 95%.

show abstract

Section: A State Of the Artmentioning

confidence: 99%

Section: A State Of the Artmentioning

confidence: 99%

Multi-Resolution 3D Convolutional Neural Networks for Automatic Coronary Centerline Extraction in Cardiac CT Angiography Scans

Salahuddin¹,

Lenga²,

Nickisch³

2020

Preprint

View full text Add to dashboard Cite

show abstract

“…The challenge organisers allow methods to compete in three categories based on the extent of user interaction per vessel: automatic (no seed points), semi-automatic (one seed point) and interactive (more than one seed point). A version of the original MHT method, used along with a minimal path algorithm used in an interactive setting [23], [30], has remained the best performing method in the Coronary Artery Challenge [24]. We evaluate the original and modified MHT methods as stand-alone, semi-automatic methods and compare to the results of Friman et al [23].…”

Section: B Coronary Artery Extractionmentioning

confidence: 99%

“…We closely adhere to the preprocessing performed in the original MHT method [23], [30]. Unsigned integers are used to represent the voxel intensities as gray value (GV), under 2 http://coronary.bigr.nl/centerlines/index.php a simple transformation of the corresponding Hounsfield Unit (HU): HU (x) = GV (x) − 1024.…”

Section: B Coronary Artery Extractionmentioning

confidence: 99%

Extracting tree structures in CT data by tracking multiple statistically ranked hypotheses

et al. 2019

View full text Add to dashboard Cite

Purpose In this work, we adapt a method based on multiple hypothesis tracking (MHT) that has been shown to give state‐of‐the‐art vessel segmentation results in interactive settings, for the purpose of extracting trees. Methods Regularly spaced tubular templates are fit to image data forming local hypotheses. These local hypotheses are then used to construct the MHT tree, which is then traversed to make segmentation decisions. Some critical parameters in the method, we base ours on, are scale‐dependent and have an adverse effect when tracking structures of varying dimensions. We propose to use statistical ranking of local hypotheses in constructing the MHT tree which yields a probabilistic interpretation of scores across scales and helps alleviate the scale dependence of MHT parameters. This enables our method to track trees starting from a single seed point. Results The proposed method is evaluated on chest computed tomography data to extract airway trees and coronary arteries and compared to relevant baselines. In both cases, we show that our method performs significantly better than the Original MHT method in semiautomatic setting. Conclusions The statistical ranking of local hypotheses introduced allows the MHT method to be used in noninteractive settings yielding competitive results for segmenting tree structures.

show abstract

“…Among the original 13 algorithms submitted within the grand challenge, the top performer implemented a multiple hypothesis tracking (MHT) framework [19,22], and according to the standardized RCAAEF evaluation criteria, had a mean overlap (OV), overlap until first error (OF), overlap with the clinically relevant part of the vessel (OT), and average inside (AI) of 98.5%, 83.1%, 98.7%, and 0.23 mm, respectively [6]. However, despite performing very well, the MHT method was a category 3 (interactive extraction) algorithm, whereas the top-performing category 1 (fully automatic extraction) algorithm [23] had a substantially lower OV (84.7%), OF (65.3%), and OT (87.0%), and a higher AI (0.28 mm).…”

Section: Introductionmentioning

confidence: 99%

Automated Coronary Artery Tracking with a Voronoi-Based 3D Centerline Extraction Algorithm

Dalvit Carvalho da Silva,

Soltanzadeh,

Figley

2023

J. Imaging

View full text Add to dashboard Cite

Coronary artery disease is one of the leading causes of death worldwide, and medical imaging methods such as coronary artery computed tomography are vitally important in its detection. More recently, various computational approaches have been proposed to automatically extract important artery coronary features (e.g., vessel centerlines, cross-sectional areas along vessel branches, etc.) that may ultimately be able to assist with more accurate and timely diagnoses. The current study therefore validated and benchmarked a recently developed automated 3D centerline extraction method for coronary artery centerline tracking using synthetically segmented coronary artery models based on the widely used Rotterdam Coronary Artery Algorithm Evaluation Framework (RCAAEF) training dataset. Based on standard accuracy metrics and the ground truth centerlines of all 32 coronary vessel branches in the RCAAEF training dataset, this 3D divide and conquer Voronoi diagram method performed exceptionally well, achieving an average overlap accuracy (OV) of 99.97%, overlap until first error (OF) of 100%, overlap of the clinically relevant portion of the vessel (OT) of 99.98%, and an average error distance inside the vessels (AI) of only 0.13 mm. Accuracy was also found to be exceptionally for all four coronary artery sub-types, with average OV values of 99.99% for right coronary arteries, 100% for left anterior descending arteries, 99.96% for left circumflex arteries, and 100% for large side-branch vessels. These results validate that the proposed method can be employed to quickly, accurately, and automatically extract 3D centerlines from segmented coronary arteries, and indicate that it is likely worthy of further exploration given the importance of this topic.

show abstract

Coronary Centerline Extraction Using Multiple Hypothesis Tracking and Minimal Paths

Cited by 17 publications

References 5 publications

Multi-Resolution 3D Convolutional Neural Networks for Automatic Coronary Centerline Extraction in Cardiac CT Angiography Scans

Multi-Resolution 3D Convolutional Neural Networks for Automatic Coronary Centerline Extraction in Cardiac CT Angiography Scans

Extracting tree structures in CT data by tracking multiple statistically ranked hypotheses

Automated Coronary Artery Tracking with a Voronoi-Based 3D Centerline Extraction Algorithm

Contact Info

Product

Resources

About